Menu
EN

Vyhledávání

Lidé

prof. Dr. Michal Pěchouček, MSc.

Všechny publikace

Hardening networks against strategic attackers using attack graph games

  • DOI: 10.1016/j.cose.2019.101578
  • Odkaz: https://doi.org/10.1016/j.cose.2019.101578
  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    We consider the problem faced by a network administrator (defender) when deploying limited security resources to protect a network against a strategic attacker. To evaluate the effectiveness of a defense strategy, one must consider possible counterattacks that an attacker can choose. We use game theory to model the interaction between the defender and the attacker. Game theory provides relevant concepts and algorithms for computing optimal strategies in environments with multiple decision makers. To model the space of attacker's possible actions, we use attack graphs, that compactly represent all known sequences of attacker's action that may lead to successful attack for a given network. We demonstrate our approach on a specific type of defense actions, where the defender deploys deceptive hosts and services (honeypots) to detect and mitigate attacks. We assume the worst-case attacker who has a complete knowledge of the (typically randomized) defense strategy. We seek the optimal defense strategy against this attacker in the form of a Stackelberg equilibrium. Computing this solution exactly using standard techniques has limited scalability, so we investigate several approaches for increasing scalability to realistic problems. We introduce optimization methods for finding exact solutions for these games and then propose a variety of polynomial heuristic algorithms that scale to significantly larger games. We analyze the scalability and the quality of these heuristic solutions on realistic network topologies. We show that the strategies found by the heuristics are often near-optimal and that they outperform non-game-theoretic baselines. Finally, we show how attack graph games can be used to answer various research questions relevant to network security administrators.

Approximating Maxmin Strategies in Imperfect Recall Games Using A-loss Recall Property

  • DOI: 10.1016/j.ijar.2017.11.010
  • Odkaz: https://doi.org/10.1016/j.ijar.2017.11.010
  • Pracoviště: Katedra počítačů, Centrum umělé inteligence
  • Anotace:
    Extensive-form games with imperfect recall are an important model of dynamic games where the players are allowed to forget previously known information. Often, imperfect recall games result from an abstraction algorithm that simplifies a large game with perfect recall. Solving imperfect recall games is known to be a hard problem, and thus it is useful to search for a subclass of imperfect recall games which offers sufficient memory savings while being efficiently solvable. The abstraction process can then be guided to result in a game from this class. We focus on a subclass of imperfect recall games called A-loss recall games. First, we provide a complete picture of the complexity of solving imperfect recall and A-loss recall games. We show that the A-loss recall property allows us to compute a best response in polynomial time (computing a best response is NP-hard in imperfect recall games). This allows us to create a practical algorithm for approximating maxmin strategies in two-player games where the maximizing player has imperfect recall and the minimizing player has A-loss recall. This algorithm is capable of solving some games with up to 5⋅109 states in approximately 1 hour. Finally, we demonstrate that the use of imperfect recall abstraction can reduce the size of the strategy representation to as low as 0.03% of the size of the strategy representation in the original perfect recall game without sacrificing the quality of the maxmin strategy obtained by solving this abstraction.

Combining Incremental Strategy Generation and Branch and Bound Search for Computing Maxmin Strategies in Imperfect Recall Games

  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    Extensive-form games with imperfect recall are an important model of dynamic games where the players are allowed to forget previously known information. Often, imperfect recall games are the result of an abstraction algorithm that simplifies a large game with perfect recall. Unfortunately, solving an imperfect recall game has fundamental problems since a Nash equilibrium does not have to exist. Alternatively, we can seek maxmin strategies that guarantee an expected outcome. The only existing algorithm computing maxmin strategies in two-player imperfect recall games without absentmindedness, however, requires approximating a bilinear mathematical program that is proportional to the size of the whole game and thus has a limited scalability. We propose a novel algorithm for computing maxmin strategies in this class of games that combines this approximate algorithm with an incremental strategy-generation technique designed previously for extensive-form games with perfect recall. Experimental evaluation shows that the novel algorithm builds only a fraction of the game tree and improves the scalability by several orders of magnitude. Finally, we demonstrate that our algorithm can solve an abstracted variant of a large game faster compared to the algorithms operating on the unabstracted perfect-recall variant.

Combining Incremental Strategy Generation and Branch and Bound Search for Computing Maxmin Strategies in Imperfect Recall Games

  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    Extensive-form games with imperfect recall are an important model of dynamic games where the players are allowed to forget previously known information. Often, imperfect recall games are the result of an abstraction algorithm that simplifies a large game with perfect recall. Unfortunately, solving an imperfect recall game has fundamental problems since a Nash equilibrium does not have to exist. Alternatively, we can seek maxmin strategies that guarantee an expected outcome. The only existing algorithm computing maxmin strategies in two-player imperfect recall games without absentmindedness, however, requires approximating a bilinear mathematical program that is proportional to the size of the whole game and thus has a limited scalability. We propose a novel algorithm for computing maxmin strategies in this class of games that combines this approximate algorithm with an incremental strategy-generation technique designed previously for extensive-form games with perfect recall. Experimental evaluation shows that the novel algorithm builds only a fraction of the game tree and improves the scalability by several orders of magnitude. Finally, we demonstrate that our algorithm can solve an abstracted variant of a large game faster compared to the algorithms operating on the unabstracted perfect-recall variant.

Computing Maxmin Strategies in Extensive-form Zero-sum Games with Imperfect Recall

  • DOI: 10.5220/0006121200630074
  • Odkaz: https://doi.org/10.5220/0006121200630074
  • Pracoviště: Katedra počítačů, Centrum umělé inteligence
  • Anotace:
    Extensive-form games with imperfect recall are an important game-theoretic model that allows a compact representation of strategies in dynamic strategic interactions. Practical use of imperfect recall games is limited due to negative theoretical results: a Nash equilibrium does not have to exist, computing maxmin strategies is NP-hard, and they may require irrational numbers. We present the first algorithm for approximating maxmin strategies in two-player zero-sum imperfect recall games without absentmindedness. We modify the wellknown sequence-form linear program to model strategies in imperfect recall games resulting in a bilinear program and use a recent technique to approximate the bilinear terms. Our main algorithm is a branch-andbound search that provably reaches the desired approximation after an exponential number of steps in the size of the game. Experimental evaluation shows that the proposed algorithm can approximate maxmin strategies of randomly generated imperfect recall games of sizes beyond toy-problems within few minutes.

Heuristic Search Value Iteration for One-Sided Partially Observable Stochastic Games

  • Pracoviště: Katedra počítačů, Centrum umělé inteligence
  • Anotace:
    Security problems can be modeled as two-player partially observable stochastic games with one-sided partial observability and infinite horizon (one-sided POSGs). We seek for optimal strategies of player 1 that correspond to robust strategies against the worst-case opponent (player 2) that is assumed to have a perfect information about the game. We present a novel algorithm for approximately solving one-sided POSGs based on the heuristic search value iteration (HSVI) for POMDPs. Our results include (1) theoretical properties of one-sided POSGs and their value functions, (2) guarantees showing the convergence of our algorithm to optimal strategies, and (3) practical demonstration of applicability and scalability of our algorithm on three different domains: pursuit-evasion, patrolling, and search games.

ARETHUS - A Decision Support Platform for Reasoning About Security

  • Autoři: Vaněk, O., Kopřiva, Š., Hrstka, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the NATO Advanced Research Workshop on Meeting Security Challenges Through Data Analytics and Decision Support. Amsterdam: IOS Press BV, 2016. pp. 184-202. ISSN 1874-6268. ISBN 978-1-61499-715-3.
  • Rok: 2016
  • DOI: 10.3233/978-1-61499-716-0-184
  • Odkaz: https://doi.org/10.3233/978-1-61499-716-0-184
  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    Asymmetric threats in the current world are focused on various critical infrastructures. We choose a subset of the infrastructures and a set of surveillance policies, and we propose a number of security countermeasures that should be able to detect and potentially prevent a potential attack. Our goal is to provide a unified decision support platform ARETHUS to help decision-makers notice a threat and then choose from a computed array of potential preventive actions. The platform is built using a mixed-reality concept, and allows mixing of real-world and simulated data to provide not only a real-time work environment, but also a testbed to test out various scenarios. We plug in a number of algorithms computing various patrolling policies for heterogeneous agents, and we make the platform extensible for use by others. We demonstrate the usability of the platform and the performance of the algorithms on a set of pipeline protection scenarios.

Case Studies of Network Defense with Attack Graph Games

  • DOI: 10.1109/MIS.2016.74
  • Odkaz: https://doi.org/10.1109/MIS.2016.74
  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    The increaing complexity of securing modern computer networks makes decision support systems an important tool for administrators. A challenge many existing tools fail to address is that attackers react strategically to new security measures, adapting their behaviors in response. Game theory provides a methodology for making decisions that takes into account these reactions, rather than assuming static attackers. The authors present an overview of how game theory can be used to inform one type of security decision: how to optimally place honeypots in a network. They demonstrate this approach on a realistic case study and present initial validation results based on a study comparing their approach with human decision makers.

Detecting the Behavioral Relationships of Malware Connections

  • DOI: 10.1145/2970030.2970038
  • Odkaz: https://doi.org/10.1145/2970030.2970038
  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    A normal computer infected with malware is difficult to detect. There have been several approaches in the last years which analyze the behavior of malware and obtain good results. The malware traffic may be detected, but it is very common to miss-detect normal traffic as malicious and generate false positives. This is specially the case when the methods are tested in real and large networks. The detection errors are generated due to the malware changing and rapidly adapting its domains and patterns to mimic normal connections. To better detect malware infections and separate them from normal traffic we propose to detect the behavior of the group of connections generated by the malware. It is known that malware usually generates various related connections simultaneously and therefore it shows a group pattern. Based on previous experiments, this paper suggests that the behavior of a group of connections can be modelled as a directed cyclic graph with special properties, such as its internal patterns, relationships, frequencies and sequences of connections. By training the group models on known traffic it may be possible to better distinguish between a malware connection and a normal connection. © 2016 Copyright held by the owner/author(s).

Modeling Maritime Contraband Trafficking Activities with the Agent-Based Approach

  • Autoři: Vaněk, O., Kopřiva, Š., Ondráček, J., Hrstka, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the NATO Advanced Research Workshop on Meeting Security Challenges Through Data Analytics and Decision Support. Amsterdam: IOS Press BV, 2016. pp. 168-183. ISSN 1874-6268. ISBN 978-1-61499-715-3.
  • Rok: 2016
  • DOI: 10.3233/978-1-61499-716-0-168
  • Odkaz: https://doi.org/10.3233/978-1-61499-716-0-168
  • Pracoviště: Centrum umělé inteligence
  • Anotace:
    Illegal contraband trafficking is causing serious damage in many countries. We focus on a subset of illegal maritime activities, mainly on weapon and drug trafficking. Our aim is to help naval authorities evaluate their currently deployed countermeasures by modeling the behavior of traffickers as realistically as possible, and evaluating the impact of countermeasures in an agent-based simulation. We introduce BANDIT, a simulation platform designed for this purpose. We propose a novel model of traffickers based on a state-of-the-art game-theoretical model using the latest results in behavioral modeling. We apply this model to specific scenarios for drug smuggling in the Caribbean, and we demonstrate the capabilities of the platform.

Privacy-Concerned Multiagent Planning

  • DOI: 10.1007/s10115-015-0887-7
  • Odkaz: https://doi.org/10.1007/s10115-015-0887-7
  • Pracoviště: Katedra počítačů
  • Anotace:
    Coordinated sequential decision making of a team of cooperative agents can be described by principles of multiagent planning. Provided that the mechanics of the environment the agents act in is described as a deterministic transitions system, an appropriate planning model is MA-Strips. Multiagent planning modeled as MA-Strips prescribes exactly what information has to be kept private and which information can be communicated in order to coordinate toward shared or individual goals. We propose a multiagent planning approach which combines compilation for a classical state-of-the-art planner together with a compact representation of local plans in the form of finite-state machines. Proving soundness and completeness of the approach, the planner efficiency is further boosted up using distributed delete-relaxation heuristics and using an approximative local plan analysis. We experimentally evaluate applicability of our approach in full privacy setting where only public information can be communicated. We analyze properties of standard multiagent benchmarks from the perspective of classification of private and public information. We show that our approach can be used with different privacy settings and that it outperforms state-of-the-art planners designed directly for particular privacy classification.

Agent-based Approach to Illegal Maritime Behavior Modeling

  • DOI: 10.17402/026
  • Odkaz: https://doi.org/10.17402/026
  • Pracoviště: Katedra počítačů
  • Anotace:
    Maritime shipping is a set of complex activities with a large number of actors involved. We focus on a subset of illegal maritime activities, such as armed robberies, maritime piracy or contraband smuggling. To fight against them and minimize their negative impact naval authorities typically introduce a number of countermeasures, such as deployed patrols or surveillance agents. Due to very high costs of countermeasures it is often beneficial to evaluate their impact using a simulation, allowing what-if analysis and evaluation of a range of scenarios before actually deploying the countermeasures. We introduce BANDIT, an agent-based computational platform, which is designed to evaluate scenarios with an accent on the modeling of different types of illegal behavior and on the interaction between agents. The platform consists of an agent behavior modeling system and a multi-agent maritime simulator. The platform allows the definition of a number of scenarios through a simple configuration and it offers the means to run these scenarios in a single or a batch mode and evaluate the results as single or aggregate data sets respectively. We demonstrate the usefulness of the platform on the scenarios of the drug smuggling problem in the seas surrounding Central America. Senario outcomes (e.g., heatmaps of activities, set of trajectories etc.) are subsequently used to help with the design of effective countermeasures, i.e., allocating naval patrols and planning their patrol routes.

Bi-objective maritime route planning in pirate-infested waters

  • DOI: 10.17402/046
  • Odkaz: https://doi.org/10.17402/046
  • Pracoviště: Katedra počítačů
  • Anotace:
    Contemporary maritime shipping is subject to a large number of constraints given by tight shipping schedules and very low margins. Additionally, problematic areas with increased security needs dynamically changing in time, combined with seasonal oceanographic and meteorological conditions pose a challenging voyage planning problem. In this work we present a risk-aware voyage planner taking into account spatio-temporal environmental conditions. The planner is based on a graph-based search algorithm A*. We discretize the required area into a graph, we store various layers of information into the edges of the graph (such as risk and weather conditions) in a form of numeric weights and we define a bi-objective planning problem with a tradeoff between security and duration of the voyage. The nature of the algorithm guarantees a complete and optimal solution in a form of an optimized voyage with respect to the criterion function composed of the two weighted components, i.e, duration and security of the voyage. We demonstrate the approach on our area of interest: Indian Ocean. We use NATO piracy activity risk surface as the risk layer and we compute all transit voyages between relevant routing points in the area. Finally, thanks to the discretization of the problem, we are able to integrate corridors imposed by the shipping authorities and evaluate additional what-if scenarios with extended corridor systems. The resulting planner is exposed to the public using a web service with an easy interface requiring start time of the voyage and the origin and the destination point of voyage. Combined with an expressive visualization, this tool demonstrates the capabilities of the proposed solution.

Multiagent Plan Repair by Combined Prefix and Suffix Reuse

  • DOI: 10.3233/MGS-150228
  • Odkaz: https://doi.org/10.3233/MGS-150228
  • Pracoviště: Katedra počítačů
  • Anotace:
    Deterministic domain-independent multiagent planning is an approach to coordination of cooperative agents with joint goals. Provided that the agents act in an uncertain and dynamic environment, such plans can fail. The straightforward approach to recover from such situations is to compute a new plan from scratch, that is to replan. Even though, in a worst case, plan repair or plan re-use does not yield an advantage over replanning from scratch, there is a sound evidence from practical use that approaches trying to repair the failed original plan can outperform replanning in selected problems. One of the possible plan repairing techniques is based on preservation of fragments of the older plans. This work theoretically analyses complexity of plan repairing approaches based on preservation of fragments of the original plan and experimentally studies three practical aspects affecting its efficiency in various multiagent settings. We focus both on the computational, as well as the communication efficiency of plan repair in comparison to replanning from scratch and we report on the influence of the following properties on the efficiency of plan repair: (1)~the number of involved agents in the plan repairing process, (2)~inter-dependencies among the repaired actions, and finally (3)~particular modes of re-use of the older plans.

Solving Infrastructure Monitoring Problems with Multiple Heterogeneous Unmanned Aerial Vehicles

  • Autoři: Ondráček, J., Vaněk, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS. New York: ACM Press, 2015, pp. 1597-1605. ISSN 1548-8403. ISBN 978-1-4503-3771-7. Available from: http://www.scopus.com/record/display.uri?eid=2-s2.0-84944679231&origin=resultslist&sort=plf-f&src=s&st1=Solving+Infrastructure+Monitoring+Problems+with+Multiple+Heterogeneous+Unmanned+Aerial+Vehicles&st2=&sid=DF1B7967743F86F5FAF4AFD18332473D.I0QkgbIjGqqL
  • Rok: 2015
  • Pracoviště: Katedra počítačů
  • Anotace:
    A number of critical infrastructures, such as gas or oil pipelines operate in a sensitive environment and any damage done to the infrastructure significantly harms the surrounding fauna and flora and poisons water supplies. The infrastructure thus needs to be monitored and any damage or failure has to be detected and reported as quickly as possible. We focus on the enhancement of the monitoring systems- we propose a first holistic solution for a set of heterogeneous unmanned aerial vehicles (UAVs) which monitor the infrastructure under current technological restrictions such as speed, battery endurance and sensing radius. We solve the problem of (1) the allocation of charging/maintenance stations in the area, (2) the assignment of the UAVs to the stations and (3) the computation of their trajectories with respect to the environment sensitivity. We propose a formal graph-based model capturing problem constraints and requirements. We explore possible decompositions of the problem and we propose a number of algorithms allowing to choose between algorithm runtime and solution quality. The results show that our approach can be used to monitor real- world sized infrastructures of a length of tens of kilometers using up to five UAVs.

An Exact Double-Oracle Algorithm for Zero-Sum Extensive-Form Games with Imperfect Information

  • Pracoviště: Katedra počítačů
  • Anotace:
    Developing scalable solution algorithms is one of the central problems in computational game theory. We present an iterative algorithm for computing an exact Nash equilibrium for two-player zero-sum extensive-form games with imperfect information. Our approach combines two key elements: (1) the compact sequence-form representation of extensive-form games and (2) the algorithmic framework of double-oracle methods. The main idea of our algorithm is to restrict the game by allowing the players to play only selected sequences of available actions. After solving the restricted game, new sequences are added by finding best responses to the current solution using fast algorithms. We experimentally evaluate our algorithm on a set of games inspired by patrolling scenarios, board, and card games. The results show significant runtime improvements in games admitting an equilibrium with small support, and substantial improvement in memory use even on games with large support. The improvement in memory use is particularly important because it allows our algorithm to solve much larger game instances than existing linear programming methods. Our main contributions include (1) a generic sequence-form double-oracle algorithm for solving zero-sum extensive-form games; (2) fast methods for maintaining a valid restricted game model when adding new sequences; (3) a search algorithm and pruning methods for computing best-response sequences; (4) theoretical guarantees about the convergence of the algorithm to a Nash equilibrium; (5) experimental analysis of our algorithm on several games, including an approximate version of the algorithm.

Diverse Planning for UAV Trajectories

  • DOI: 10.1007/978-3-662-44440-5_17
  • Odkaz: https://doi.org/10.1007/978-3-662-44440-5_17
  • Pracoviště: Katedra počítačů
  • Anotace:
    Nowadays, unmanned aerial vehicles (UAVs) are more and more often used to solve various tasks in both the private and the public sector. Some of these tasks can often be performed completely autonomously while others are still dependent on remote pilots. They control an UAV using a command display where they can control it manually using joysticks or give it a simple task. The command displays allow to plan the UAV trajectory through waypoints while avoiding no- fly zones. Nevertheless, the operator can be aware of other preferences or soft restrictions for which it’s not feasible to be inserted into the system especially during time critical tasks. We propose to provide the opera- tor with several different alternative trajectories, so he can choose the best one for the current situation. In this contribution we propose sev- eral metrics to measure the diversity of the trajectories. Then we explore several algorithms for the alternative trajectories creation. Finally, we experimentally evaluate them in a benchmark 8-grid domain and we also present the evaluation by human operators.

Domain-independent multi-agent plan repair

  • DOI: 10.1016/j.jnca.2012.12.011
  • Odkaz: https://doi.org/10.1016/j.jnca.2012.12.011
  • Pracoviště: Katedra počítačů
  • Anotace:
    Achieving joint objectives in distributed domain-independent planning problems by teams of cooperative agents requires significant coordination and communication efforts. For systems facing a plan failure in a dynamic environment, arguably, attempts to repair the failed plan in general, and especially in the worst-case scenarios, do not straightforwardly bring any benefit in terms of time complexity. However, in multi-agent settings, the communication complexity might be of a much higher importance, possibly a high communication overhead might be even prohibitive in certain domains. We hypothesize that in decentralized systems, where frequent coordination is required to achieve joint objectives, attempts to repair failed multi-agent plans should lead to lower communication overhead than replanning from scratch. Here, we formally introduce the multi-agent plan repair problem. Building upon the formal treatment, we present the core hypothesis underlying our work and subsequently describe three algorithms for multi-agent plan repair reducing the problem to specialized instances of the multi-agent planning problem. Finally, we present an experimental validation, results of which confirm the core hypothesis of the paper. Our rigorous treatment of the problem and experimental results pave the way for both further analytical, as well algorithmic investigations of the problem.

Improving Group Transit Schemes to Minimize Negative Effects of Maritime Piracy

  • Autoři: Vaněk, O., Hrstka, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: IEEE Transactions on Intelligent Transportation Systems. 2014, 15(3), 1101-1112. ISSN 1524-9050.
  • Rok: 2014
  • DOI: 10.1109/TITS.2013.2294908
  • Odkaz: https://doi.org/10.1109/TITS.2013.2294908
  • Pracoviště: Katedra počítačů
  • Anotace:
    Contemporary maritime piracy around the Horn of Africa presents a serious threat to the global shipping industry. A number of countermeasures were deployed to minimize the probability of a successful ship hijack, one of them being the establishment of the International Recommended Transit Corridor (IRTC). Currently, all ships transiting the Gulf of Aden are recommended to follow the IRTC and take part in group transit schemes (GTSs)-prescribed fixed schedules stating a time of arrival to the beginning of the corridor and a speed at which to sail through the corridor. We provide a number of contributions that improve the GTS: we formalize the grouping problem, we design an efficient algorithm able to compute optimal fixed GTSs with respect to the distribution of ships' speeds, we provide a real-world data set with speeds of ships transiting the IRTC, and we compare the optimal fixed schedules with the currently deployed schedule and quantify possible savings. Additionally, we propose on-demand GTSs-customized schedules for a group of arriving ships-that take into account speeds, risk aversion, and actual positions of arriving ships. We formulate the problem of the optimal on-demand grouping as a biobjective mixed integer program, and we compute a set of Pareto optimal solutions. We evaluate the scalability of the approach, the structure of the solution, and quantify an improvement over the current GTS with respect to the number of ships grouped and the time saved.

Validation of an Air-Traffic Controller behavioral model for fast time simulation

  • DOI: 10.1109/ICNSurv.2014.6820020
  • Odkaz: https://doi.org/10.1109/ICNSurv.2014.6820020
  • Pracoviště: Katedra počítačů
  • Anotace:
    The US National Airspace System (NAS) is incredibly complex, and consists of many specific functions. Given predicted increases in air traffic, enhancement of the current system and development of the NextGEN system are critical to maintain safe and efficient operation. Each feature of the system needs to be carefully designed, developed, tested and validated. To this end, human-in-the-loop (HITL) simulations represent one of the most powerful and realistic testing tools. HITL simulations can provide valuable feedback on how new features influence the behavior of human operators. The drawbacks of HITL simulations include limited flexibility and scalability, and high cost. Computer simulations, which involve no direct human activity, can avoid some of these potential problems, and often represent an attractive alternative (or adjunct) to HITL simulation. A crucial question underlying the use of computer models is how well the model captures the human operator (in this case, the air traffic controller). This paper presents a validation of the AgentFly system, specifically a human en-route Air Traffic Controller (ATC) behavioral model. The ATC workload model is based on Multiple Resource Theory including visual scanning, radio emulation and different kinds of uncertainty. Validation of the AgentFly system was performed by comparing model output to HITL simulation data. The AgentFly system used simulated behavior of air traffic controllers and pilots to collect similar data. Both types of output data were processed and compared based on selected metrics.

Agent-based model of maritime traffic in piracy-affected waters

  • DOI: 10.1016/j.trc.2013.08.009
  • Odkaz: https://doi.org/10.1016/j.trc.2013.08.009
  • Pracoviště: Katedra počítačů
  • Anotace:
    Contemporary maritime piracy presents a significant threat to global shipping industry, with annual costs estimated at up to US$7bn. To counter the threat, policymakers, shipping operators and navy commanders need new data-driven decision-support tools that will allow them to plan and execute counter-piracy operations most effectively. So far, the provision of such tools has been limited. In cooperation with maritime domain stakeholders, we have therefore developed AgentC, a data-driven agent-based simulation model of maritime traffic that explicitly models pirate activity and piracy countermeasures. Modeling the behavior and interactions of thousands of individually simulated vessels, the model is capable of capturing the complex dynamics of the maritime transportation system threatened by maritime piracy and allows assessing the potential of a range of piracy countermeasures. We demonstrate the what-if analysis capabilities of the model on a real-world case study of designing a new transit corridor system in the Indian Ocean. The simulation results reveal that the positive past experience with the transit corridor in the narrow Gulf of Aden does not directly translate to the vast and open waters of the Indian Ocean and that additional factors have to be considered when designing corridor systems. The agent-based simulation development and calibration process used for building the presented model is general and can be used for developing simulation models of other maritime transportation phenomena.

Deployment of Multi-agent Algorithms for Tactical Operations on UAV Hardware

  • Pracoviště: Katedra počítačů
  • Anotace:
    Small Unmanned Aerial Vehicles (UAVs) are becoming increasingly popular for tasks such as surveillance or target tracking in various types of tactical missions. Traditionally, each UAV in a mission is controlled by one or more operators. In our previous work we have developed a collection of distributed algorithms that allow one operator to control a whole team of small UAVs. Here, we report on our successful effort to deploy the developed multi-agent control algorithms to a team of hardware UAVs. To reduce costs and risk, we first developed the multi-agent control algorithms using simulated approximation of the target environment. Then, we gradually refined the model of the target environment by adding higher-fidelity models of the assets and hardware-in-the loop assets. In the final step, the algorithms were deployed and field tested in a full hardware setting and in a mixed-reality setting, where hardware UAVs are accompanied by a a number of simulated UAVs.

Developing Multiagent Algorithms for Tactical Missions Using Simulation

  • DOI: 10.1109/MIS.2012.90
  • Odkaz: https://doi.org/10.1109/MIS.2012.90
  • Pracoviště: Katedra počítačů
  • Anotace:
    The development process and simulation architecture presented here help narrow the gap between how theoretical AI algorithms are traditionally designed and validated and how practical algorithms for controlling robotic assets in simulated tactical missions are developed.

Double-Oracle Algorithm for Computing an Exact Nash Equilibrium in Zero-Sum Extensive-Form Games

  • Pracoviště: Katedra počítačů
  • Anotace:
    We investigate an iterative algorithm for computing an exact Nash equilibrium in two-player zero-sum extensive-form games with imperfect information. The approach uses the sequence-form representation of extensive-form games and the double-oracle algorithmic framework. The main idea is to restrict the game by allowing the players to play only some of the sequences of available actions, then iteratively solve this restricted game, and exploit fast best-response algorithms to add additional sequences to the restricted game for the next iteration. In this paper we (1) extend the sequence-form double-oracle method to be applicable on non-deterministic extensive-form games, (2) present more efficient methods for maintaining valid restricted game and computing best-response sequences, and finally we (3) provide theoretical guarantees of the convergence of the algorithm to a Nash equilibrium. We experimentally evaluate our algorithm on two types of games: a search game on a graph and simplified variants of Poker. The results show significant running-time improvements compared to the previous variant of the double-oracle algorithm, and demonstrate the ability to find an exact solution of much larger games compared to solving full linear program for the complete game.

Dynamic group transit scheme for corridor transit

  • Autoři: Vaněk, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the 5th International Conference on Modeling, Simulation and Applied Optimization. Piscataway: IEEE, 2013. pp. 1-6. ISBN 978-1-4673-5814-9.
  • Rok: 2013
  • DOI: 10.1109/ICMSAO.2013.6552597
  • Odkaz: https://doi.org/10.1109/ICMSAO.2013.6552597
  • Pracoviště: Katedra počítačů
  • Anotace:
    Contemporary maritime piracy around the Horn of Africa presents a serious threat to the global shipping industry. A number of countermeasures were deployed to minimize the probability of a successful hijack, one of them being the establishment of the International Recommended Transit Corridor (IRTC). Currently, all ships transiting the Gulf of Aden are strongly recommended to follow the IRTC and take part in group transit schemes-prescribed schedules stating time of arrival to the beginning of the corridor and speed at which to sail through the corridor. These schedules are fixed in advance and do not take into account speeds and constraints of arriving ships. We propose dynamic grouping schemes, customized schedules for a group of arriving ships, which take into account speeds as well as positions of arriving ships. The problem of finding optimum grouping scheme for a group of arriving ships is formulated as a bi-objective mixed integer program, weighting the delay caused by the grouping scheme and the risk taken when sailing alone. We look for a set of Pareto optimal solutions and compare the dynamic grouping scheme with currently deployed fixed scheme. Results show an improvement over current grouping scheme with respect to the number of ships grouped as well as time saved.

How to Repair Multi-agent Plans: Experimental Approach

  • Pracoviště: Katedra počítačů
  • Anotace:
    Deterministic domain-independent multi-agent planning is an approach to coordination of cooperative agents with joint goals. Provided that the agents act in an imperfect environment, such plans can fail. The traightforward approach to recover from such situations is to compute a new plan from scratch, that is to replan. Even though, in a worst case, plan repair or plan re-use does not yield an advantage over replanning from scratch, there is a sound evidence from practical use that approaches trying to repair the failed original plan can outperform replanning in selected problems. One of the possible plan repairing techniques is based on preservation of the older plans. This work experimentally studies three aspects affecting efficiency of plan repairing approaches based on preservation of fragments of the original plan in a multi-agent setting. We focus both on the computational, as well as the communication efficiency of plan repair in comparison to replanning from scratch. In our study, we report on the influence of the following issues on the efficiency of plan repair: 1) the number of involved agents in the plan repairing process, 2) interdependencies among the repaired actions, and finally 3) particular modes of re-use of the older plans.

Multi-agent RRT*: Sampling-based Cooperative Pathfinding

  • Pracoviště: Katedra počítačů
  • Anotace:
    Cooperative pathfinding is a problem of finding a set of non-conflicting trajectories for a number of mobile agents. Its applications include planning for teams of mobile robots, such as autonomous aircrafts, cars, or underwater ve- hicles. The state-of-the-art algorithms for cooperative pathfinding for embod- ied robots typically rely on some heuristic forward-search pathfinding technique, where A* is often the algorithm of choice. Here, we propose MA-RRT*, a novel algorithm for multi-agent motion planning that builds upon a recently proposed asymptotically-optimal sampling-based algorithm called RRT*. In this paper, we focus on the case where the agents’ mobility model is a discrete graph. We eval- uate the performance of the proposed algorithm and its scalability with respect to the number of agents and the size of the environment. Our results show that the sampling-based approach offers better scalability than the classical forward- search approach in relatively sparse environments, which are typical in real-world applications such as multi-aircraft collision avoidance.

Multi-agent RRT*: sampling-based cooperative pathfinding

  • Pracoviště: Katedra počítačů
  • Anotace:
    Cooperative pathfinding is a problem of finding a set of non-conflicting trajectories for a number of mobile agents. Its applications include planning for teams of mobile robots, such as autonomous aircrafts, cars, or underwater vehicles. The state-of-the-art algorithms for cooperative pathfinding typically rely on some heuristic forward-search pathfinding technique, where A* is often the algorithm of choice. Here, we propose MA-RRT*, a novel algorithm for multi-agent path planning that builds upon a recently proposed asymptotically-optimal sampling-based algorithm for finding single-agent shortest path called RRT*. We experimentally evaluate the performance of the algorithm and show that the sampling-based approach offers better scalability than the classical forward-search approach in relatively large, but sparse environments, which are typical in real-world applications such as multi-aircraft collision avoidance.

Planning of diverse trajectories for UAV control displays

  • Pracoviště: Katedra počítačů
  • Anotace:
    Unmanned aerial vehicles (UAVs) are more and more often used to solve different tasks in both the private and the public sector. Some of these tasks, can be often performed completely autonomously, while the others are still dependent on the remote pilots. They control an UAV using a command display where they can control it manually using joysticks, or give it a simple task. The command display allow for the planning of the UAV trajectory through the waypoints while avoiding the no-fly zones. Nevertheless, the operator can be aware of other preferences, or soft restrictions, for which it's not feasible to be inserted into the system especially during the time critical tasks. We propose to provide the operator with several alternative trajectories which are different from the operator's point of view. So he can choose the best one for the current situation. In this contribution we evaluate previously presented techniques for diverse planning. We focus on an evaluation made by a group of human operators and show how it can be deployed in an UAV control display.

Scalable and Robust Multi-agent Planning with Approximated DCOP

  • Pracoviště: Katedra počítačů
  • Anotace:
    Distributed multi-agent planning presents several challenges as yet not addressed by existing techniques. First, the complexity of planning scales non-linearly as a function of the number of agents. Second, most multi-agent planning approaches assume perfect and reliable communications are available to coordinate actions across the distributed agents. Third, even given reliable communications, agents may not be able to converge on a reliable overall plan for the group without resorting to computationally expensive (and communication intensive) problem centralization. This paper develops a formalization of the multi-agent planning problem and a novel three-phase approach which generates plans, solves them using the approximate, robust Max-Sum DCOP algorithm and then uses plan repair to address these three points. We provide sketches of the proofs of these claims as well as empirical results, for a restricted version of the Crane-Robot domain, of better scalability than existing approaches, and robust performance with up to 90% message loss.

Simulated Multi-robot Tactical Missions in Urban Warfare

  • DOI: 10.1007/978-3-642-33323-1_7
  • Odkaz: https://doi.org/10.1007/978-3-642-33323-1_7
  • Pracoviště: Katedra počítačů
  • Anotace:
    Since late 90’s of the last century, rapid advances in technology, mechanical engineering, miniaturization, telecommunications and informatics enabled development and routine deployment of sophisticated robots in many real world domains. Besides many applications in assembly industry, e.g., in car, or electronics assembly lines, defense organizations, together with space exploration and mining industries belong to the most demanding and optimistic users of robotic technology [25]. Especially in the military domain we nowadays witness a routine deployment of robotic assets in the field.

Using Data-Driven Simulation for Analysis of Maritime Piracy

  • DOI: 10.3233/978-1-61499-201-1-109
  • Odkaz: https://doi.org/10.3233/978-1-61499-201-1-109
  • Pracoviště: Katedra počítačů
  • Anotace:
    Agent-based modelling has gained popularity as a useful technique for obtaining insights into the behaviour of complex adaptive systems in various fields, including economics, sociology and ecology. With its complex interactions between routes, schedules and engagement strategies, transit through piracy-affected waters is a problem very well suited for the application of this powerful modelling approach. Within the AgentC project, we have been developing a data-driven, agent-based model of global maritime traffic explicitly accounting for the effects of maritime piracy. The model employs finite state machines to represent the behaviour of merchant, pirate and naval vessels. It accurately replicates global shipping patterns and approximates real-world distribution of pirate attacks. By conducting and analysing results from thousands of simulation runs, the developed model and related tools allow gaining qualitative and quantitative insights into complex relationships governing piracy risks and costs. Further on, we utilize the simulation to conduct what-if analysis of possible piracy counter-measures and evaluate their effectiveness. Because of their strong application potential, the model and the tools are currently considered by the U.N. International Maritime Organization for potential use in assessing future operational counter-piracy measures, including new transit corridors and extended group transit schemes.

Using Double-Oracle Method and Serialized Alpha-Beta Search for Pruning in Simultaneous Move Games

  • Pracoviště: Katedra počítačů
  • Anotace:
    We focus on solving two-player zero-sum extensive-form games with perfect information and simultaneous moves. In these games, both players fully observe the current state of the game where they simultaneously make a move determining the next state of the game. We solve these games by a novel algorithm that relies on two components: (1) it iteratively solves the games that correspond to a single simultaneous move using a double-oracle method, and (2) it prunes the states of the game using bounds on the sub-game values obtained by the classical Alpha-Beta search on a serialized variant of the game. We experimentally evaluate our algorithm on the Goofspiel card game, a pursuit-evasion game, and randomly generated games. The results show that our novel algorithm typically provides significant running-time improvements and reduction in the number of evaluated nodes compared to the full search algorithm.

Agent-based Control for Multi-UAV Information Collection

  • Pracoviště: Katedra počítačů
  • Anotace:
    Multi-agent coordination and planning techniques play a fundamental role in designing control systems for autonomous multi-UAV-based information collection. The most important categories of information collection are exploration, surveillance, search and tracking. We introduce each category of information collection and then focus on a specific problem - multi-UAV-based surveillance in complex environments where sensor occlusions can occur due to high buildings and other obstacles in the target area. We formalize the problem and propose a solution as a decomposition of the problem in two subproblems: the problem of single-area surveillance and the problem of allocating UAVs to multiple areas. We present and compare several algorithms for the subproblems and prove their optimality. Finally, we empirically evaluate the performance of all algorithms on a realistic simulation of aerial surveillance, built using the AGENTFLYframework, and compare it to theoretical estimates.

AGENTFLY: Multi-Agent Simulation of Air-Traffic Management

  • Autoři: doc. Ing. David Šišlák, Ph.D., Volf, P., Pavlíček, D., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: ECAI 2012 - 20th European Conference on Artificial Intelligence. Amsterdam: IOS Press, 2012, pp. 1019-1020. ISSN 0922-6389. ISBN 978-1-61499-097-0. Available from: http://www.booksonline.iospress.nl/Content/View.aspx?piid=31572
  • Rok: 2012
  • Pracoviště: Katedra počítačů
  • Anotace:
    The current air-traffic management (ATM) system involves thousands of people, a majority of them being human controllers [5]. Controllers organize the flow of air-traffic to safely maintain airplane distance and plans for assigned airspace sectors. The capacity of ATM depends on many factors, such as availability of air traffic control (i.e., each controller can handle only limited number of airplanes), current or forecasted weather condition, availability of airspace and capacity of airport facilities. An issue occurs at peak hours when the current ATM system reaches its limits.

AgentFly: Scalable, High-Fidelity Framework for Simulation, Planning and Collision Avoidance of Multiple UAVs

  • Pracoviště: Katedra počítačů
  • Anotace:
    AgentFly is a software prototype providing intelligent algorithms for autonomous unmanned aerial vehicles. AgentFly is implemented as a scalable multi-agent system in JAVA running on the top of the Aglobe platform which provides flexible middle-ware supporting seamless interaction among heterogenous software, hardware and human actors. Thanks to JAVA, AgentFly can be easily hosted on UAVs or computers with different operating systems. The multi-agent approach provides straightforward mapping - each airplane is controlled by one agent. Agents integrate intelligent algorithms providing a coordination-based control for autonomous UAVs. In the presented work, only algorithms which are fully distributed among airplanes are used. Such algorithms provide a real autonomous control for UAVs which do not require any central unit (a ground station or master airplane) controlling a group of UAVs. The main benefit is that the group of UAVs can operate also in the situations where the permanent communication link with the central unit or ground operating station is missing. Some of the algorithms presented in this chapter suppose that UAVs are equipped with communication modems which allow them to dynamically establish bi-directional communication channels based on their mutual position. Thus, airplanes utilize the mobile ad-hoc wireless network created by their communication modems. These algorithms provide the robust control in critical situations: loose of communication, destroyed airplane.

AgentPolis: towards a platform for fully agent-based modeling of multi-modal transportation

  • Pracoviště: Katedra počítačů
  • Anotace:
    AgentPolis is a fully agent-based platform for modeling multi-modal transportation systems. It comprises a high-performance discrete-event simulation core, a cohesive set of high-level abstractions for building extensible agent-based models and a library of predefined components frequently used in transportation and mobility models. Together with a suite of supporting tools, textsc{AgentPolis} enables rapid prototyping and execution of data-driven simulations of a wide range of mobility and transportation phenomena. We illustrate the capabilities of the platform on a model of fare inspection in public transportation networks.

Agents vs. Pirates: Multi-Agent Simulation and Optimization to Fight Maritime Piracy

  • Autoři: doc. Ing. Michal Jakob, Ph.D., Vaněk, O., Hrstka, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems. County of Richland: IFAAMAS, 2012, pp. 37-44. ISBN 978-0-9817381-2-3. Available from: http://dl.acm.org/citation.cfm?id=2343581
  • Rok: 2012
  • Pracoviště: Katedra počítačů
  • Anotace:
    Contemporary maritime piracy presents a significant threat to the global shipping industry, with annual costs estimated at up to US$12bn. To address the threat, commanders and policymakers need new data-driven decision-support tools that will allow them to plan and execute counter-piracy activities most effectively. So far, however, the provision of such tools has been very limited. To fill this gap, we have employed the multi-agent approach and developed a novel suite of computational tools and techniques for operational management of counter-piracy operations. A comprehensive agent-based simulation enables the stakeholders to assess the efficiency of a range of piracy counter-measures, including recommended transit corridors, escorted convoys, group transit schemes, route randomization and navy patrol deployments. Decision-theoretic and game-theoretic optimization techniques further assist in discovering counter-measure configurations that yield the best trade-off between transportation security and cost. We demonstrate our approach on two case studies based on the problems and solutions currently explored by the maritime security community. Our work is the first integrated application of agent-based techniques to high-seas maritime security and opens a wide range of directions for follow-up research and development.

Anytime Algorithms for Multi-agent Visibility-based Pursuit-evasion Games

  • Pracoviště: Katedra počítačů
  • Anotace:
    We investigate algorithms for playing multi-agent visibility-based pursuit-evasion games. A team of pursuers attempts to maintain visibility contact with an evader who actively avoids tracking. We aim for applicability of the algorithms in real-world scenarios; hence, we impose hard constraints on the run-time of the algorithms and we evaluate them in a simulation model based on a real-world urban area. We compare Monte-Carlo tree search (MCTS) and iterative deepening minimax algorithms running on the information-set tree of the imperfect-information game. The experimental results demonstrate that both methods create comparable good strategies for the pursuer, while the later performs better in creating the evader's strategy.

Asynchronous decentralized algorithm for space-time cooperative pathfinding

  • Pracoviště: Katedra počítačů
  • Anotace:
    Cooperative pathfinding is a multi-agent path planning problem where a group of vehicles searches for a corresponding set of non-conflicting space-time trajectories. Many of the practi- cal methods for centralized solving of cooperative pathfinding prob- lems are based on the prioritized planning strategy. However, in some domains (e.g., multi-robot teams of unmanned aerial vehicles, au- tonomous underwater vehicles, or unmanned ground vehicles) a de- centralized approach may be more desirable than a centralized one due to communication limitations imposed by the domain and/or pri- vacy concerns. In this paper we present an asynchronous decentralized variant of prioritized planning ADPP and its interruptible version IADPP. The algorithm exploits the inherent parallelism of distributed systems and allows for a speed up of the computation process. Unlike the synchro- nized planning approaches, the algorithm allows an agent to react to updates about other agents' paths immediately and invoke its local spatio-temporal path planner to find the best trajectory, as response to the other agents' choices. We provide a proof of correctness of the algorithms and experimentally evaluate them on synthetic domains.

Autonomous UCAV Coordination in Dynamic Search and Destroy Missions

  • Pracoviště: Katedra počítačů
  • Anotace:
    Military operations of the last decades are no longer conflicts of only two participants. Coalitions of countries are participating on one or both sides of the conflict. These conflicts are composed of a number of missions of different nature. We focus on the search and destroy missions which form an irreplaceable part of most of the conflicts since the Vietnam War. With the introduction of Unmanned Combat Air Vehicles (UCAVs) the importance of these missions increases even more since it allows to further decrease the number of causalities among the allies. In this article we discuss the use of UCAVs in search and destroy missions and compare two approaches: a multi-agent negotiation approach, and Process Integrated Mechanism (PIM). Both approaches allow a high degree of autonomy of the UCAVs, promising to decrease the operator load and the base–UCAV communication. We propose several different quality metrics and use them to evaluate and compare both approaches. We also propose an interesting strategy that uses both approaches to create a coalition of autonomous UCAVs, taking advantage of the strengths of a multi-agent approach and PIM.

Decentralized Multi-agent Plan Repair in Dynamic Environments (Extended Abstract)

  • Pracoviště: Katedra počítačů
  • Anotace:
    Achieving joint objectives by teams of cooperative planning agents requires significant coordination and communication efforts. For a single-agent system facing a plan failure in a dynamic environment, arguably, attempts to repair the failed plan in general do not straightforwardly bring any benefit in terms of time complexity. However, in multi-agent settings the communication complexity might be of a much higher importance, possibly a high communication overhead might be even prohibitive in certain domains. We hypothesize that in decentralized systems, where coordination is enforced to achieve joint objectives, attempts to repair failed multi-agent plans should lead to lower communication overhead than replanning from scratch.

Extending Security Games to Defenders with Constrained Mobility

  • Pracoviště: Katedra počítačů
  • Anotace:
    A number of real-world security scenarios can be cast as a problem of transiting an area guarded by a mobile patroller, where the transiting agent aims to choose its route so as to minimize the probability of encountering the patrolling agent, and vice versa. We model this problem as a two-player zero-sum game on a graph, termed the transit game. In contrast to the existing models of area transit, where one of the players is stationary, we assume both players are mobile. We also explicitly model the limited endurance of the patroller and the notion of a base to which the patroller has to repeatedly return. Noting the prohibitive size of the strategy spaces of both players, we develop single- and double-oracle based algorithms including a novel acceleration scheme, to obtain optimum route selection strategies for both players. We evaluate the developed approach on a range of transit game instances inspired by real-world security problems in the urban and naval security domains.

Game Theoretic Model of Strategic Honeypot Selection in Computer Networks

  • DOI: 10.1007/978-3-642-34266-0_12
  • Odkaz: https://doi.org/10.1007/978-3-642-34266-0_12
  • Pracoviště: Katedra počítačů
  • Anotace:
    A honeypot is a decoy computer system used in network security to waste the time and resources of attackers and to analyze their behaviors. While there has been significant research on how to design honeypot systems, less is known about how to use honeypots strategically in network defense. Based on formal deception games, we develop two game-theoretic models that provide insight into how valuable should honeypots look like to maximize the probability that a rational attacker will attack a honeypot. The first model captures a static situation and the second allows attackers to imperfectly probe some of the systems on the network to determine which ones are likely to be real systems (and not honeypots) before launching an attack. We formally analyze the properties of the optimal strategies in the games and provide linear programs for their computation. Finally, we present the optimal solutions for a set of instances of the games and evaluate their quality in comparison to several baselines.

Game-theoretic Approach to Adversarial Plan Recognition

  • DOI: 10.3233/978-1-61499-098-7-546
  • Odkaz: https://doi.org/10.3233/978-1-61499-098-7-546
  • Pracoviště: Katedra počítačů
  • Anotace:
    We argue that the problem of adversarial plan recognition, where the observed agent actively tries to avoid detection, should be modeled in the game theoretic framework. We define the problem as an imperfect-information extensive-form game between the observer and the observed agent. We propose a novel algorithm that approximates the optimal solution in the game using Monte-Carlo sampling. The experimental evaluation is performed on a syn- thetic domain inspired by a network security problem. The proposed method produces significantly better results than several simple baselines on a practically large domain.

Game-theoretic Resource Allocation for Malicious Packet Detection in Computer Networks

  • Pracoviště: Katedra počítačů
  • Anotace:
    We study the problem of optimal resource allocation for packet selection and inspection to detect potential threats in large computer networks with multiple valuable computers of differing importance. An attacker tries to harm these targets by sending malicious packets from multiple entry points of the network; the defender thus needs to optimally allocate his resources to maximize the probability of malicious packet detection under network latency constraints. We formulate the problem as a graph-based security game with multiple resources of heterogeneous capabilities and propose a mathematical program for finding optimal solutions. Due to the very limited scalability caused by the large attacker's strategy space and non-linearity of the program, we investigate solutions with approximated utility function and propose Grande, a novel polynomial approximate al- gorithm utilizing submodularity of the problem able to find solutions with a bounded error on problem of a realistic size.

Iterative Algorithm for Solving Two-player Zero-sum Extensive-form Games with Imperfect Information

  • Pracoviště: Katedra počítačů
  • Anotace:
    We develop and evaluate a new exact algorithm for finding Nash equilibria of two-player zero-sum extensive-form games with imperfect information. Our approach is based on the sequence-form representation of the game, and uses an algorithmic framework of double-oracle methods that have been used successfully in other classes of games. The algorithm uses an iterative decomposition, solving restricted games and exploiting fast best-response algorithms to add additional sequences to the game over time. We demonstrate our algorithm on a class of adversarial graph search games motivated by real world border patrolling scenarios. The results indicate that our framework is a promising way to scale up solutions for extensive-form games, reducing both memory and computation time requirements.

Mixed-Reality Testbeds for Incremental Development of HART Applications

Multi-agent Simulation Approach to Development of Applications for Decentralized Tactical Missions

  • Pracoviště: Katedra počítačů
  • Anotace:
    The development of control algorithms for tactical missions is being impeded by the significant gap between the way the artificial intelligence (A.I.) algorithms have been designed and validated and the way the robotic applications for (high-fidelity simulations) of tactical missions are being developed. On the one hand, we have low-level robotic simulators (or even robotic field testing). On the other hand, we have synthetic - usually mathematically defined - environments used for the design and formal testing of A.I. algorithms, e.g. randomly generated problem instances, synthetic graph structures, logical structures, regular grids, and similar. In this work, we are proposing a development process and a related software toolkit helping to narrow this gap. We use the simulation-aided development approach and tailor it towards the domain of tactical missions. The process is demonstrated on a specific application scenario, employing a general software toolkit Alite to glue together and adapt a number of A.I. algorithms, originally designed as highly abstract.

Multi-Agent Simulation of En-Route Human Air-Traffic Controller

  • Autoři: doc. Ing. David Šišlák, Ph.D., Volf, P., prof. Dr. Michal Pěchouček, MSc., Cannon, C.T., Nguyen, D.N., Regli, W.C.
  • Publikace: Proceedings of the 24th Innovative applications of artificial intelligence conference. Menlo Park, California: AAAI Press, 2012, pp. 2323-2328. ISBN 978-1-57735-568-7. Available from: http://www.aaai.org/ocs/index.php/IAAI/IAAI-12/paper/view/4873
  • Rok: 2012
  • Pracoviště: Katedra počítačů
  • Anotace:
    The Next-Generation Transportation program coordinates the evolution and transformation of the current air-traffic management (ATM) system for the National Airspace System (NAS). Currently the NAS has a limited capacity and cannot handle the increasing future air traffic demands. However, before newly proposed ATM concepts are deployed they must be rigorously evaluated under realistic conditions. This paper presents AGENTFLY, an emerging NAS-wide highfidelity multi-agent ATM simulator with precise emulation of the human controller operation workload model and human-system interaction. The simulator is validated using a flight scenario developed by the U.S. Federal Aviation Administration that is based on real data. We present preliminary results focusing on the accuracy of the simulated controllers within AGENTFLY.

Nas-wide en-route air-traffic controller modeling

  • DOI: 10.1109/ICNSurv.2012.6218417
  • Odkaz: https://doi.org/10.1109/ICNSurv.2012.6218417
  • Pracoviště: Katedra počítačů
  • Anotace:
    Increasing air-traffic demand implies that new air-traffic management (ATM) concepts lowering controller loads, maintaining safety and increasing efficiency need to be designed and implemented. Many of such ideas are prepared within NextGEN. Before they are deployed to real daily usage in National Airspace System (NAS), they must be rigorously evaluated under realistic conditions. The paper presents AGENTFLY, a NAS-wide high-fidelity distributed multi-agent simulator with precise emulation of the human controller operation workload model and human-system interaction. The current version of AGENTFLY provides precise modeling of the human radar controller (R-side) operating in en-route sector.

Sense and Avoid Concepts: Vehicle-Based SAA Systems (Vehicle-to-Vehicle)

  • Pracoviště: Katedra počítačů
  • Anotace:
    The various scenarios of unmanned aerial vehicles (UAVs) deployment require the ability to navigate UAVs in unknown terrain. UAV, while fulfilling the mission objectives, has to avoid static obstacles as well as moving obstacles like other UAVs, airplanes, balloons or areas with bad weather forecast or bad weather conditions. Furthermore, if UAV enters the commercial controlled airspace, it needs to be able to sense and avoid the potential conflicts considering the air-traffic control regulations. The concepts for development of automated systems providing the sense and avoid capability (also referred to as collision detection and resolution systems, CDR) came mainly from two domains. The first one is the air-traffic management domain, where automated tools like Traffic Collision Avoidance System (TCAS) and Precission Runway Monitor (PRM) are used to increase safety and fluency of the air-traffic. The second one is the artificial intelligence research and particularly robotics, where scientists investigated the trajectory planning and obstacle avoidance algorithms for aerial, ground and maritime systems.

Strategy Representation Analysis for Patrolling Games

  • Pracoviště: Katedra počítačů
  • Anotace:
    This paper considers the problem of patrolling multiple targets in a Euclidean environment by a single patrolling unit. We use game-theoretic approach and model the problem as a two-player zero-sum game in the extensive form. Based on the existing work in the domain of patrolling we propose a novel mathematical non-linear program for finding strategies in a discretized problem, in which we introduce a general concept of internal states of the patroller. We experimentally evaluate game value for the patroller for various graphs and strategy representations. The results suggest that adding internal states for the patroller yields better results in comparison to adding choice nodes in the used discretization.

Tactical Operations of Multi-Robot Teams in Urban Warfare (Demonstration)

  • Pracoviště: Katedra počítačů
  • Anotace:
    With scaling of multi-robot teams deployed in military operations, there is a need to boost autonomy of individual, as well as team behaviors. We developed a feature-rich simulation testbed for experimental evaluation of multi-agent coordination mechanisms applicable in tactical military operations in urban warfare. In particular, we investigated and implemented four approaches including multi-agent mission planning and plan repair, reactive planning for teamwork, patrolling of mobile targets, and tracking of smart targets. Besides the live-system demonstrator, we aim to showcase a scenario engaging a human in a pursuit-evasion game against the algorithms we implemented.

Towards Parallel Real-Time Trajectory Planning

  • DOI: 10.1007/978-3-642-28786-2_11
  • Odkaz: https://doi.org/10.1007/978-3-642-28786-2_11
  • Pracoviště: Katedra počítačů
  • Anotace:
    This paper exploits the computing power of widely available multi-core machines to accelerate the trajectory planning by parallelisation of the search algorithm. In particular we investigate the approach that schedules the workload on the cores using the hashing function based on the geographical partitioning of the search space. We use this approach to parallelize the AA* algorithm. In our solution, each partition of the geographical space is represented as an agent. The concept is evaluated on the simulation of real-time trajectory planning of aircraft respecting the environment and real aircraft performance models. We show that the approach decreases the planning time significantly on common multi-core machines preserving the quality of the trajectory provided by AA* algorithm.

Towards Simulation-Aided Design of Multi-Agent Systems

  • DOI: 10.1007/978-3-642-28939-2_1
  • Odkaz: https://doi.org/10.1007/978-3-642-28939-2_1
  • Pracoviště: Katedra počítačů
  • Anotace:
    With the growing complexity of multi-agent applications and environments in which they are deployed, there is a need for development techniques that would allow for early testing and validation of application design and implementation. This is particularly true in cases where the developed multi-agent application is to be closely integrated with an existing, real-world system of multi-agent nature. Drawing upon our previous experiences with development of complex multi-agent applications, we propose simulation-aided design of multi-agent systems (SADMAS), a methodology tightly integrating simulations of the target system into the MAS application development process. In its heart lies the use of mixed-mode simulation, a simulation where parts of the deployed application operate in the target environment and parts remain simulated. We argue, that employing SADMAS process contributes to reduction of risks involved in development of complex MAS applications, as well as it helps to accelerate the process. Besides describing the capstones of the SADMAS approach and consequences of its application, we also illustrate it’s use on a case-study of a next-generation decentralised air traffic management system.

Abstract Architecture for Task oriented Multi agent Problem Solving

  • DOI: 10.1109/TSMCC.2010.2073465
  • Odkaz: https://doi.org/10.1109/TSMCC.2010.2073465
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Problem solving and planning in decentralized environments is a key technical challenge in numerous industrial applications, ranging from manufacturing, logistics, virtual enterprizes to multirobotics systems. We present an abstract architecture of a multiagent solver and respective algorithm providing decomposition, task allocation, and task delegation. Various features of the abstract architecture, such as computational complexity or admissibility of the underlying optimization heuristics, are analyzed in the paper. Four instances of the abstract architecture implementations are given to demonstrate the applicability of the abstract solver in a wide variety of real-problem domains.

Agent-Based Cooperative Decentralized Airplane-Collision Avoidance

  • DOI: 10.1109/TITS.2010.2057246
  • Odkaz: https://doi.org/10.1109/TITS.2010.2057246
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The efficiency of the current centralized air-traffic management is limited. A next-generation air transportation system should allow airplanes (manned and unmanned) to change their flight paths during the flight without approval from a centralized en route control. Such a scheme requires decentralized peer-to-peer conflict detection and collision-avoidance processes. In this paper, two cooperative (negotiation-based) conflictresolution algorithms are presented: iterative peer-to-peer and multiparty algorithms. They are based on high-level flight-plan variations using evasion maneuvers. The algorithms work with a different level of coordination autonomy, respect realistic assumptions of imprecise flight execution (integrating required navigation performance), and work in real time, where the planning and plan-execution phases interleave. Both algorithms provide a resolution in a 4-D domain (3-D space and time).

AgentC: Agent-based System for Securing Maritime Transit (Demonstration)

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Recent rise in maritime piracy prompts the search for novel techniques for addressing the problem. We therefore developed AgentC, a prototype system that demonstrates how agent-based traffic management techniques can be used to improve the security of transit through piracy-affected areas. Combining agent-based modeling and simulation of maritime traffic and novel route planning and vessel scheduling techniques, the system shows the promising potential of agent-based methods for increasing maritime security.

Agentfly: NAS-wide simulation framework integrating algorithms for automated collision avoidance

  • Autoři: doc. Ing. David Šišlák, Ph.D., Volf, P., Kopřiva, Š., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Integrated Communications Navigation and Surveillance Conference. Piscataway: IEEE, 2011, pp. 1-11. ISSN 2155-4943. ISBN 978-1-4577-0592-2. Available from: http://ieeexplore.ieee.org/search/srchabstract.jsp?arnumber=5935278
  • Rok: 2011
  • DOI: 10.1109/ICNSURV.2011.5935278
  • Odkaz: https://doi.org/10.1109/ICNSURV.2011.5935278
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    AgentFly is a software prototype providing a distributed architecture for large-scale NAS-wide simulation implemented as a multi-agent system. AgentFly is implemented on top of the Aglobe platform which is both an implementation framework and a runtime engine for custom agents. It was selected over possible alternatives (e.g. JADE) for its outstanding performance and scalability supporting seamless interaction among heterogeneous software, hardware and human actors. AgentFly system has been developed for over five years. It was initially built f or simulation-based validation and comparison of various approaches for autonomous collision avoidance algorithms adopting the free-flight concept. Later, AgentFly has been extended with high-level control algorithms providing tactical control - i.e. coordination of several autonomous unmanned aerial vehicles (UAV).

Agentni simulaci proti somalskym piratum

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Výzkumníci z Katedry kybernetiky Fakulty elektrotechnické na ČVUT studují použitelnost metod umělé inteligence a agentních technologií při zajišťování bezpečnosti v námořní doméně. Předmětem výzkumu sponzorovaného americkým Úřadem pro námořní výzkum (ONR) je vytvoření podrobného multiagentního modelu chování pirátů v prostředí námořní dopravy a návrh algoritmů pro optimálně znáhodněné plánování bezpečného transitu Adenským zálivem.

Automated Conflict Resolution Utilizing Probability Collectives Optimizer

  • DOI: 10.1109/TSMCC.2010.2089448
  • Odkaz: https://doi.org/10.1109/TSMCC.2010.2089448
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Rising manned air traffic and deployment of unmanned aerial vehicles in complex operations requires integration of innovative and autonomous conflict detection and resolution methods. In this paper, the task of conflict detection and resolution is defined as an optimization problem searching for a heading control for cooperating airplanes using communication. For the optimization task, an objective function integrates both collision penalties and efficiency criteria considering airplanes' objectives (waypoints). The probability collectives optimizer is used as a solver for the specified optimization task. This paper provides two different implementation approaches to the presented optimization-based collision avoidance: 1) a parallel computation using multiagent deployment among participating airplanes and 2) semicentralized computation using the process-integratedmechanism architecture.

Computing Time-Dependent Policies for Patrolling Games with Mobile Targets

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We study how a mobile defender should patrol an area to protect multiple valuable targets from being attacked by an attacker. In contrast to existing approaches we allow the targets to move through the area according to a priori known deterministic movement schedules. We represent the patrol area by a graph of arbitrary topology and do not put any restrictions on the movement schedules. We assume the attacker can observe the defender and has full knowledge of the strategy the defender employs. We construct a game-theoretic formulation and seek defender's optimal randomized strategy in a Stackelberg equilibrium of the game. We formulate the computation of the strategy as a mathematical program whose solution corresponds to an optimal time-dependent Markov policy for the defender.

Content-Based Privacy Management on the Social Web

  • DOI: 10.1109/WI-IAT.2011.208
  • Odkaz: https://doi.org/10.1109/WI-IAT.2011.208
  • Pracoviště: Katedra počítačů
  • Anotace:
    Protection of privacy is a major concern for users of social web applications, including social networks. Although most online social networks now offer fine-grained controls of information sharing, these are rarely used, both because their use imposes additional burden on the user and because they are too complex for an average user to handle. To mitigate the problem, we propose an intelligent privacy manager that automates the assignment of sharing permissions, taking into account the content of the published information and user's high-level sharing policies. At the core of our contribution is a novel privacy policy language which explicitly accounts for social web concepts and which balances the expressive power with representation complexity. The manager employs named entity recognition algorithms to annotate sensitive parts of published information and an answer set programming system to evaluate user's privacy policies and determine the list of safe recipients. We implemented a prototype of the manager on the Face book platform. On a small test scenario, the manager reached the F-measure value of 0.831 in correctly recommending safe recipients.

Double Oracle Algorithm for Zero-Sum Security Games on Graph

  • Autoři: Jain, M., Korzhyk, D., Vaněk, O., Conitzer, V., prof. Dr. Michal Pěchouček, MSc., Tambe, M.
  • Publikace: AAMAS 2011. County of Richland: IFAAMAS, 2011, pp. 327-334. ISBN 978-0-9826571-8-8.
  • Rok: 2011
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In response to the Mumbai attacks of 2008, the Mumbai police have started to schedule a limited number of inspection checkpoints on the road network throughout the city. Algorithms for similar security-related scheduling problems have been proposed in recent literature, but security scheduling in networked domains when targets have varying importance remains an open problem at large. In this paper, we cast the network security problem as an attacker-defender zero-sum game. The strategy spaces for both players are exponentially large, so this requires the development of novel, scal- able techniques. We first show that existing algorithms for approximate solutions can be arbitrarily bad in general settings.

Game Theoretical Adaptation Model for Intrusion Detection System

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Grill, M., Stiborek, J., Bartoš, K.
  • Publikace: AAMAS 2011. County of Richland: IFAAMAS, 2011, pp. 1123-1124. ISBN 978-0-9826571-8-8. Available from: http://www.ifaamas.org/Proceedings/aamas2011/papers/R29.pdf
  • Rok: 2011
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a self-adaptation mechanism for Network Intrusion Detection System which uses a game-theoretical mechanism to increase system robustness against targeted attacks on IDS adaptation. We model the adaptation process as a strategy selection in sequence of single stage, two player games. The key innovation of our approach is a secure runtime game definition and numerical solution and real-time use of game solutions for dynamic system reconfiguration. Our approach is suited for realistic environments where we typically lack any ground truth information regarding traffic legitimacy/maliciousness and where the significant portion of system inputs may be shaped by the attacker in order to render the system ineffective. Therefore, we rely on the concept of challenge insertion: we inject a small sample of simulated attacks into the unknown traffic and use the system response to these attacks to define the game structure and utility functions.

ICT and eHealth Projects

  • Autoři: Lhotská, L., Štěpánková, O., prof. Dr. Michal Pěchouček, MSc., prof. Ing. Boris Šimák, CSc., Chod, J.
  • Publikace: Telecom World (ITU WT), 2011 Technical Symposium at ITU. Piscataway: IEEE, 2011, pp. 57-62. ISBN 978-1-4577-1148-0. Available from: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6100931
  • Rok: 2011
  • Pracoviště: Katedra telekomunikační techniky, Katedra počítačů
  • Anotace:
    Information and communication technologies have already become inseparable part of healthcare sector activities. In the paper we present existing solutions of eHealth and ambient assisted living systems developed by researchers of the Faculty of Electrical Engineering of the Czech Technical University in Prague and their industrial partners. We also touch the issue of interoperability that is crucial for correct interconnection of medical and other devices and information systems. We propose a high level functional architecture of a system that can satisfy the requirements of interoperability.

Intelligent Content-based Privacy Assistant for Facebook

  • Pracoviště: Katedra počítačů
  • Anotace:
    Although most online social networks now offer fine-grained controls of information sharing, these are rarely used, both because their use imposes additional burden on the user and because there are too many control settings for an average user to handle. To mitigate this problem, we have developed an Intelligent Privacy Assistant for Facebook that partially automates the assignment of sharing permissions, taking into account the content of the information published and user's high-level sharing policies. The Assistant uses a novel social web privacy language, employs named entity recognition algorithms to annotate sensitive parts of published information and an answer set programming system to evaluate user's privacy policies and determine the list of safe recipients. On a test scenario, the Assistant reached 73.8% and 95.2% performance in correctly determining safe and unsafe recipients, respectively.

Iterative Game-theoretic Route Selection for Hostile Area Transit and Patrolling

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    A number of real-world security scenarios can be cast as a problem of transiting an area patrolled by a mobile adversary, where the transiting agent aims to choose its route so as to minimize the probability of encountering the patrolling agent, and vice versa. We model this problem as a two player zero-sum game on a graph, termed the transit game. In contrast to the existing models of area transit, where one of the players is stationary, we assume both players are mobile. We also explicitly model the limited endurance of the patroller and the notion of a base to which the patroller has to repeatedly return. Noting the prohibitive size of the strategy spaces of both players, we employ iterative oracle-based algorithms including a newly proposed accelerated scheme, to obtain optimum route selection strategies for both players. We evaluate the developed approach on a range of transit game instances inspired by real-world security problems in the urban and naval security domains.

Large-Scale High-Fidelity Agent-Based Simulation in Air Traffic Domain

  • DOI: 10.1080/01969722.2011.610270
  • Odkaz: https://doi.org/10.1080/01969722.2011.610270
  • Pracoviště: Katedra počítačů
  • Anotace:
    We present the concept of dynamic partitioning of scalable, high-fidelity multi-agent simulation complemented with intelligent load-balancing processes. The simulation framework is designed to simulate entities to high details that require extended computation resources. To be able to simulate a huge amount of entities, distributed simulation is introduced using spatial partitioning and dynamic load balancing. A novel and important feature is the combination of the synchronous and asynchronous parts in the simulation. We use the domain of the air traffic simulation to verify the simulation framework. We present a method to perform spatial and temporal planning within 3D space and multilayer architecture using several collision avoidance algorithms to illustrate the high computational demands of each airplane. The platform has been used to support simulation of an entire civilian air traffic touching the national airspace of United States.

Parallel Real-time Trajectory Planning in U.S. NAS

  • Pracoviště: Katedra počítačů
  • Anotace:
    This paper exploits the computing power of widely available multi-core machines to accelerate the trajectory planning by parallelisation of the search algorithm. In particular we investigate the approach that schedules the workload on the cores using the hashing function based on the geographical partitioning of the search space. We use this approach to parallelize the AA* algorithm. The concept is evaluated on the simulation of real-time trajectory planning of aircraft respecting the environment and real aircraft performance models. We show that this approach decreases the planning time significantly on common multi-core machines preserving the quality of the trajectory provided by AA* algorithm.

Plan representation and execution in multi actor scenarios by means of social commitments

  • DOI: 10.3233/WIA-2011-0210
  • Odkaz: https://doi.org/10.3233/WIA-2011-0210
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present an approach to plan representation in multi-actor scenarios that is suitable for flexible replanning and plan revision purposes in dynamic non-deterministic multi-actor environments. The key idea of the presented approach is in representation of the distributed hierarchical plan by social commitments, as a theoretically studied formalism representing mutual relations among intentions of collaborating agents. The article presents a formal model of a recursive form of commitments and discusses how it can be deployed to a selected hierarchical planning scenario. The decommitment rules definition and their influence on the plan execution robustness and stability is also presented. The approach was verified and evaluated in a simulated environment. The experimental validation confirms the performance, stability, and robustness of the system in complex scenarios.

Surveillance of Unmanned Aerial Vehicles Using Probability Collectives

  • DOI: 10.1007/978-3-642-23181-0_23
  • Odkaz: https://doi.org/10.1007/978-3-642-23181-0_23
  • Pracoviště: Katedra počítačů
  • Anotace:
    A rising deployment of unmanned aerial vehicles in complex environment operations requires advanced coordination and planning methods. We address the problem of multi-UAV-based area surveillance and collision avoidance. The surveillance problem contains non-linear components and non-linear constraints which makes the optimization problem a hard one. We propose discretization of the problem based on the definition of the points of interest and time steps to reduce its complexity. The objective function integrates both the area surveillance and collision avoidance sub-problems. The optimization task is solved using a probability collection solver that allows to distribute computation of the optimization. We have implemented the probability collective solver as a multi-agent simulation. The results show the approach can be used for this problem.

Towards Cooperation in Adversarial Search with Confidentiality

  • DOI: 10.1007/978-3-642-23181-0_24
  • Odkaz: https://doi.org/10.1007/978-3-642-23181-0_24
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We investigate the problem of cooperation of self-interested agents with respect to the confidentiality of their plans and without a presence of any third-party mediator. We base our approach on non-zero-sum n-player games in the extensive form focusing on two main goals: (1) the analysis of the maximal improvement of the utility value that an agent can gain by negotiation, and (2) the dependence of this improvement on the basic characteristics of the game -- the number of agents, size of the branching factor, and correlation of the utility functions. We provide theoretical definitions together with experimental results evaluated on games abstracting real-world scenarios.

Using Agents to Improve International Maritime Transport Security

  • DOI: 10.1109/MIS.2011.23
  • Odkaz: https://doi.org/10.1109/MIS.2011.23
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The recent surge in maritime piracy presents a serious threat to the international maritime transport system. Over the past few years, insurance rates have increased more than tenfold for vessels transiting known pirate waters, and the overall costs of piracy in the Pacific and Indian Oceans alone were estimated at up to US$16 billion in 2008 and continue to rise. To combat this problem, researchers have explored various measures for getting piracy back under control and for mitigating the risks it entails. Inspired by the recent successful applications of the multiagent approach to other traffic and transportation domains, we have developed a testbed for prototyping and evaluating agent-based techniques for understanding, detecting, anticipating, and eventually suppressing piracy and possibly other categories of maritime crime. Building on that testbed, we have investigated a range of specific coordination and planning methods for tackling the problem

Using Multi-Agent Simulation to Improve the Security of Maritime Transit

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Despite their use for modeling traffic in ports and regional waters, multi-agent simulations have not yet been applied to model mar- itime traffic on a global scale. We therefore propose a fully agent-based, data-driven model of global maritime traffic, focusing primarily on mod- eling transit through piracy-affected waters. The model employs finite state machines to represent the behavior of several classes of vessels and can accurately replicate global shipping patterns and approximate real- world distribution of pirate attacks. We apply the model to the problem of optimizing the Gulf of Aden group transit. The results demonstrate the usefulness of agent-based modeling for evaluating and improving op- erational counter-piracy policies and measures.

Agent Subset Adversarial Search for Complex Non-cooperative Domains

  • DOI: 10.1109/ITW.2010.5593351
  • Odkaz: https://doi.org/10.1109/ITW.2010.5593351
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We investigate reduction of the complexity of a multi-agent adversarial search in the domain of n-player games. We describe a method that decomposes the game into a set of smaller overlapping sub-games, solves each sub-game separately, and then combines the results into a global solution. This way, the exponential dependence of the adversarial search complexity on the number of agents can be reduced to polynomial. Still, the proposed method performs well in the domains with sparse agents' interactions. The method can be used with a generic adversarial search algorithm. For the experimental evaluation, we implement it on top of an existing adversarial search algorithm designed for complex domains and we evaluate its performance on a game, which is a model of a humanitarian relief operation in conflict environment. The results show that the method often finds the same solutions as the complete search, but the search efficiency is significantly improved.

AgentC: Agent-based Testbed for Adversarial Modeling and Reasoning in the Maritime Domain

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present an agent-based system for modeling, analyzing and reasoning in the maritime domain with the emphasis on detecting, anticipating and preventing illegitimate activities, such as contemporary maritime piracy. At the core of the system is a data-driven agent-based simulation which combines a rich array of sources of real-world piracy-related data with simulated operation of thousands of vessels of different types in order to create a rich model of maritime activity. The simulation is integrated with a range of advanced adver- sarial reasoning methods for analyzing illegitimate activities and for planning active counter-measures. In combination with experiment support tools and a powerful presentation frontend based on Google Earth, the system provides a complete testbed for the development and evaluation of counter-piracy methods based on the multi-agent approach.

Agents Towards Vehicle Routing Problems

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    A multi-agent VRP solver is presented in this paper. It utilizes the contract-net protocol based allocation and several improvement strategies. It provides the solution with the quality of 81% compared to the optimal solution on 115 benchmark instances in polynomial time. The self-organizing capability of the system successfully minimizes the number of vehicles used. The presented solver architecture supports great runtime parallelization with incremental increase of solution quality. The presented solver demonstrates applicability to the VRP problem and easy adaptation to problem variants.

Cooperative Agent Navigation in Partially Unknown Urban Environments

  • DOI: 10.1145/1967112.1967118
  • Odkaz: https://doi.org/10.1145/1967112.1967118
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Navigation of unmanned ground vehicles in an urban area is a fundamental problem which has to be solved prior to real-world deployment of the autonomous ground assets. Since the topology data of the environment are usually known a priori, they can be exploited in high-level planning of the routes. On the other hand, the low-level robot control requires precise path to follow and thus trajectory planning has to be adopted as well. Finally, the particular details of the environment can differ from the known topology and thus the vehicles need an area exploration method. The integrated multi-agent system for cooperative navigation in partially unknown urban environment is introduced and validated using vehicle physics based simulation. The goal is to support the navigation of a convoy by a set of unmanned vehicles in an urban environment to avoid convoy stops or u-turns and minimize the total traveled distance of all vehicles.

Deception in Networks of Mobile Sensing Agents

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In this study we consider deception by an adversary, which is relevant in many (military) applications. The adversary is expected to use deception to prevent the sensor team from performing its tasks. We employ a game theoretic model to analyze the expected strategy of the adversary and find the best response. We represent a Mobile Sensor Team problem using the Distributed Constraint Optimization Problem (DCOP) framework. We propose an optimal method for the selection of a position of a single agent facing a deceptive adversary. This method serves as a heuristic for agents to select their position in a full scale problem with multiple agents in a large area. Our empirical study demonstrates the success of our model as compared with existing models in the presence of deceptions.

Distributed Scheduling Using Constraint Optimization and Multiagent Path Planning

  • Autoři: Cannon, Ch., Lass, R., Sultanik, E., Regli, W., doc. Ing. David Šišlák, Ph.D., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of AAMAS 2010 The 12th International Workshop on Distributed Constraint Reasoning. Philadelphia: Drexel university, 2010, pp. 22-34. ISBN 978-0-9826571-1-9. Available from: https://www.cs.drexel.edu/files/eas28/dcr2010papers/dcr2010_8.pdf
  • Rok: 2010
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The goal of the distributed scheduling problem is to minimize the global cost of assigning n decentralized workers to m tasks at time points. This problem is further complicated in continuous environments because the entire state space cannot be searched. This paper presents a decentralized approach of dividing the distributed scheduling in continuous environments problem into two subproblems: distributed set covering and distributed multiagent path planning. First, we represent the rpblem of assigning workers (i.e., covers) to tasks (i.e., sets) as a Distributed Constraint Optimization Problem (DCOP). Then, the DCOP solver passes its solution to the distributed multiagent path planner who creates a conflict-free path for each worker to its assigned tasks. By first representing the problem as a DCOP, it restricts the plan space to only a set of feasible plans. We apply this approach to the scenario of distributed scheduling for unmanned aerial vehicle surveillance.

Employing Agents to Improve the Security of International Maritime Transport

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We explore how agent-based techniques can be employed to reduce the threat of contemporary maritime piracy to international transport. At the center of our approach is a data-driven agent-based simulation platform incorporating a range of real-world data sources in order to provide a solid computational model of maritime activity. The platform is integrated with extension modules providing advanced analysis, reasoning and planning capabilities. Two such modules are presented. The first module applies statistical machine learning techniques to extract models of vessel movement from trajectory data; the models are subsequently used for categorizing vessels and detecting suspicious activity. The second module employs game theory-based strategic reasoning to plan risk-minimizing routes for vessels transiting known pirate waters.

Expanding Decision Support Systems Outside Company Gates

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This chapter presents set of different decision support systems to demonstrate different ways, how the decision support process can be extended outside a single company

Goal-Based Game Tree Search for Complex Domains

  • DOI: 10.1007/978-3-642-11819-7_8
  • Odkaz: https://doi.org/10.1007/978-3-642-11819-7_8
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a novel approach to reducing adversarial search space by employing background knowledge represented in the form of higher-level goals that players tend to pursue in the game. The algorithm is derived from a simultaneous-move modification of the max n algorithm by limiting the search to those branches of the game tree that are consistent with pursuing player's goals. The algorithm has been tested on a real-world-based scenario modelled as a large-scale asymmetric game. The experimental results obtained indicate the ability of the goal-based heuristic to reduce the search space to a manageable level even in complex domains while maintaining the high quality of resulting strategies.

Iterative Accelerated A* Path Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper provides a description of an iterative version of the Accelerated A* algorithm for path planning and its application in the air traffic domain for airplanes with defined motion dynamics operationg in the Earth-centered, Earth-fixed coordinate system (GPS) on a sperical model of the Earth constrained by the landscape and special use airspaces (SUA). The motion dynamics of the airplanes is modeled using the Base of Aircraft Data (BADA) airplane performance models. The presented algorithm provides an extension of the A* algorithm that significantly reduces the serch space and makes planning of the flight trajectories computationally tractable.

Large Scale Agent Based Simulation of Air traffic

  • Autoři: doc. Ing. David Šišlák, Ph.D., Volf, P., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the Twentieth European Meeting on Cybernetics and Systems Research. Vienna: Austrian Society for Cybernetics Studies, 2010, pp. 527-532. ISBN 978-3-85206-178-8. Available from: http://www.springerlink.com/content/8kx6507332735361/
  • Rok: 2010
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We describe a multi-agent platform \textsc{AgentFly} used for large-scale high-detail simulation of air traffic. The platform introduces spatial and temporal planning within 3D space, multi-layer architecture using several collision avoidance algorithms. To be able to simulate a huge amount of airplanes, distributed simulation is introduced using spatial partitioning and dynamic load-balancing. The platform has been used to support simulation of an entire civilian air traffic touching National Air-Space of United States. Thorough evaluation of the system has been performed, confirming that it can scale up to a very high number of complex agents operating simultaneously (thousands of aircraft) with full detailed models.

Occlusion-aware Multi-UAV Surveillance

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present an agent-based coordination and planning method for autonomous aerial surveillance of multiple urban areas using a group of fixed-wing unmanned aerial vehicles (UAVs). The goal of the surveillance is to observe a set of ground points of interest within the target areas as often as possible. The method differs from the existing work by explicit consideration of sensor occlusions that can occur due to high buildings and/or other obstacles in the target area. The solution employs a decomposition of the problem in two sub- problems: the problem of single-area surveillance and the problem of allocating UAVs to multiple areas. The overall method is evaluated empirically on a realistic simulation of aerial surveillance built using the AgentFly framework.

Occlusion-aware Multi-UAV Surveillance of Multiple Urban Areas

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present an agent-based coordination and planning method for aerial surveillance of multiple urban areas using a group of fixed-wing unmanned aerial vehicles (UAVs). The method differs from the existing work by explicit consideration of sensor occlusions that can occur due to high buildings and other obstacles in the target area. The solution employs a decomposition of the problem in two subproblems: the problem of single-area surveillance and the problem of allocating UAVs to multiple areas. Three occlusion-aware methods for single-area surveillance are presented and compared. An algorithm for UAV allocation is presented and its optimality proved. The performance of all algorithms is evaluated empirically on a realistic simulation of aerial surveillance, built using the AgentFly framework, and is compared to theoretical estimates.

Probabilistic Modeling of Mobile Agents' Trajectories

  • DOI: 10.1007/978-3-642-15420-1_6
  • Odkaz: https://doi.org/10.1007/978-3-642-15420-1_6
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a method for learning characteristic motion patterns of mobile agents. The method works on two levels. On the first level, it uses the expectation-maximization algorithm to build a Gaussian mixture model of the spatial density of agents' movement. On the second level, agents' trajectories as expressed as sequences of the components of the mixture model; the sequences are subsequently used to train hidden Markov models. The trained hidden Markov models are then employed to determine agent type, predict further agent movement or detect anomalous agents. The method has been evaluated in the maritime domain using ship trajectory data generated by the AgentC maritime traffic simulation.

Research Challenges in Simulation Aided Design of Complex Multi-agent Systems

  • Pracoviště: Katedra počítačů
  • Anotace:
    In today's world, we are increasingly surrounded by and reliant on complex sys- tems and infrastructures. Often, the se systems behave far from the optimum or even highly undesirable. Roads in our cities are congested, plane trips fre- quently delayed, computer networks rout inely overrun by worms and elektricity grids fail in split-second cascade react ions. Our systems have become massively interwoven and interdependent making both highly positive and negative chain reactions possible in critical systems. The systems that surround us, that provide us with communication, energy resources and support our safety and komfort are increasingly decentralized, interno nnected and autonom ous, with more and more decisions originating at the level of individual subsystems rather than be- ing imposed top-down. These systems are characterized by large numbers of geographically dispersed active entities with a complex network of mutual in- teractions and feedbacks, together giving rise to dynamic, non-linear emergent behavior which is very difficult to understand and even more difficult to control

Transiting Areas Patrolled by a Mobile Adversary

  • DOI: 10.1109/ITW.2010.5593377
  • Odkaz: https://doi.org/10.1109/ITW.2010.5593377
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We study the problem of a mobile agent trying to cross an area patrolled by a mobile adversary. The transiting agent aims to choose its route so as to minimize the probability of hostile encounter; the patroller agent, controlling one or more patrol units, aims at the opposite. We model the problem as a two-player zero-sum game (termed transit game) and search for an optimum route selection strategy as a mixed Nash equilibrium of the game. In contrast to existing game-theoretic models of this kind, we explicitly consider the limited endurance of patrols and the notion of bases to which the patrols need to repeatedly return. Noting the prohibitive size of the transit game, we employ two techniques for reducing the complexity of finding Nash equilibria - a compact network-flow-based representation of transit routes and iterative single- and doubleoracle algorithms for incremental game matrix construction

Accelerated A* Path Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper addresses the area of path planning for nonholonomic vehicles operating in a large-scale dynamic continuous three-dimensional space where the vehicle has to avoid given obstacles and restricted areas.

Accelerated A* Trajectory Planning: Grid based Path Planning Comparison

  • Autoři: doc. Ing. David Šišlák, Ph.D., Volf, P., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the 19th International Conference on Automated Planning & Scheduling/ 4th Workshop on Planning and Plan Execution for Real-World Systems. Menlo Park, California: AAAI Press, 2009, pp. 74-81. ISBN 978-1-57735-407-9.
  • Rok: 2009
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The contribution of the paper is a high performance pathplanning algorithm designed to be used within a multi-agent planning framework solving a UAV collision avoidance problem. Due to the lack of benchmark examples and available algorithms for 3D+time planning, the algorithm performance has been compared in the classical domain of path planning in grids with blocked and unblocked cells. The Accelerated A* algorithm has been compared against the Theta* path planner, Rapid-Exploring Random Trees-based planners and the original A* searching in graphs providing the shortest any-angle paths. Experiments have shown that Accelerated A* finds the shortest paths in all scenarios including many randomized configurations. Experiments document that Accelerated A* is slower than Theta* and RRT-based planers in many cases, but it is faster than the original A*.

Adaptive Multi-Agent System for Network Traffic Monitoring

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Grill, M., Stiborek, J., Bartoš, K., Čeleda, P.
  • Publikace: IEEE Intelligent Systems. 2009, 24(3), 16-25. ISSN 1541-1672.
  • Rok: 2009
  • DOI: 10.1109/MIS.2009.42
  • Odkaz: https://doi.org/10.1109/MIS.2009.42
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present an application of agent-based data mining for a near-real time detection of attacks against the computer networks and connected hosts. The presented system processes the statistics of network traffic provided by high-speed network monitoring cards and uses a set of known anomaly detection techniques to identify the anomalous behavior. The individual anomaly detection methods have relatively high error rates that make them unfit for most practical deployments. Based on the agent-based trust modeling technique, our system fuses the data provided by snímaly detection methods and progressively builds a better classification, with an acceptable error rate. The system uses agent-based self-adaptation techniques to dynamically align its structure with the changes in network traffic structure and attacks.

Adversarial Search with Procedural Knowledge Heuristic

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We introduce an adversarial planning algorithm based on game tree search, which is applicable in large-scale multiplayer domains. In order to tackle the scalability issues of game tree search, the algorithm utilizes procedural knowledge capturing how individual players tend to achieve their goals in the domain; the information is used to limit the search only to the part of the game tree that is consistent with pursuing players' goals. We impose no specific requirements on the format of the procedural knowledge; any programming language or agent specification paradigm can be employed. We evaluate the algorithm both theoretically and empirically, confirming that the proposed approach can lead to a substantial search reduction with only a minor negative impact on the quality of produced solutions.

Agent Based Approach to Free Flight Planning, Control, and Simulation

  • DOI: 10.1109/MIS.2009.1
  • Odkaz: https://doi.org/10.1109/MIS.2009.1
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Intelligent agents technology provides techniques and algorithms for distributed coordination and distributed decision making. The authors developed AgentFly, a multiagent prototype for air traffic control of free flight based operations of multiple aerial assets, based on intelligent agents. AgentFly provides mechanisms for distributed planning, negotiation based collision avoidance, and multiagent flight simulation. The US Air Force supports this project, but the Federal Aviation Administration is also studying AgentFly for planning mixed traffic of manned and unmanned air traffic.

Autonomous UAV Surveillance in Complex Urban Environments

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We address the problem of multi-UAV surveillance in complex urban environments with occlusions. The problem consists of coordinating the flight of UAVs with on-board cameras so that the coverage and recency of the information about a designated area is maximized. In contrast to the existing work, sensing constraints due to occlusions and UAV flight constraints are modeled realistically and taken into account. We propose a novel occlusion-aware surveillance algorithm based on a decomposition of the surveillance problem into a variant of the three-dimensional art gallery problem and the multi-traveling salesmen problem for Dubins vehicles. The algorithm is thoroughly evaluated on the high-fidelity AGENTFLY UAV simulation testbed which accurately models all constraints and effects involved. The results confirm the importance of occlusion-aware flight path planning, in particular in the case of narrow street areas and low UAV flight altitudes.

Autonomous UAV Surveillance of Complex Urban Environments

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We address the problem of multi-UAV surveillance in complex urban environments with occlusions. The problem consists of coordinating the flight of UAVs with on-board cameras so that the coverage and recency of the information about a designated area is maximized. In contrast to the existing work, sensing constraints due to occlusions and UAV flight constraints are modeled realistically and taken into account. We propose a novel occlusion-aware surveillance algorithm based on a decomposition of the surveillance problem into a variant of the three-dimensional art gallery problem and the multi-traveling salesmen problem for Dubins vehicles. The algorithm is thoroughly evaluated on the high-fidelity AGENTFLY UAV simulation testbed which accurately models all constraints and effects involved. The results confirm the importance of occlusion-aware flight path planning, in particular in the case of narrow street areas and low UAV flight altitudes.

Collaborative Approach to Network Behavior Analysis Based on Hardware-Accelerated FlowMon Probes

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Grill, M., Bartoš, K., Krmíček, V., Čeleda, P.
  • Publikace: International Journal of Electronic Security and Digital Forensics. 2009, 2(1), 35-48. ISSN 1751-911X.
  • Rok: 2009
  • DOI: 10.1504/IJESDF.2009.023874
  • Odkaz: https://doi.org/10.1504/IJESDF.2009.023874
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Network behavior analysis techniques are designed to detect intrusions and other undesirable behavior in computer networks by analyzing the tra_c statistics. We present an e_cient framework for integration of anomaly detection algorithms working on the identical input data. This framework is based on high-speed network tra_c acquisition subsystem and on trust modeling, a well-established set of techniques from the multi-agent system _eld. Trust-based integration of algorithms results in classi_cation with lower error rate, especially in terms of false positives. The presented system is suitable for both online and o_ine processing, and introduces a relatively low computational overhead compared to deployment of isolated anomaly detection algorithms.

Contract Observation in Web Services Environments

  • DOI: 10.1007/978-3-642-10739-9_1
  • Odkaz: https://doi.org/10.1007/978-3-642-10739-9_1
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Electronic contracting, based on explicit representation of different parties' commitments, is a promising way to specifying and regulating behaviour in distributed business applications. A key part of contract-based system is a process through which the actual behaviour of individual parties is checked for conformance with contracts set to govern such behaviour. Such checking requires that relevant information on the behaviour of the parties, both with respect to the application processes they execute and to managing their contractual relationships, is captured. The process of collecting all such information, termed contract observation, is the subject of this paper. First, we describe general properties and requirements of such an observation process; afterwards, we discuss specifics of realising contract observation in web services environments.

Decommitting in multi-agent execution in non-deterministic environment: experimental approach

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The process of planning in complex, multi-actor environment depends strongly on the ability of the individual actors to perform intelligent decommitment upon specific changes in the environment. Reasoning about decommitment alternatives during the planning process contributes to flexibility and robustness of the resulting plan. In this article we formally introduce and discuss three specific decommitment rules: (i) relaxation, (ii) delegation and (iii) full decommitment. We argue that appropriate selection, setting and preference ordering of the decommitment rules contributes to robustness (measured as a number of failures) of the overall plans. The presented claims are supported by empirical experiments.

Distributed planning and coordination in non-deterministic environments

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a demonstration of a multi-agent prototype for distributed planning and coordination in dynamic non-deterministic multi-actor mixed-initiative environments. The system provides flexible planning, replanning, and task allocation. The key technologies utilized in the system are (i) I-X hierarchical planner with (ii) agent-based architecture and (iii) commitment-based plan representation. The implementation of the system was verified and evaluated in simulated environment. The experimental validation confirms the performance, stability, and robustness of the system in complex scenarios. In this demonstration we present the compilation of the most representative scenarios.

Distributed Platform for Large-Scale Agent-Based Simulations

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We describe a distributed architecture for situated largescale agent-based simulations with predominately local interactions. The approach, implemented in AglobeX Simulation platform, is based on a spatially partitioned simulated virtual environment and allocating a dedicated processing core to the environment simulation within each partition. In combination with dynamic load-balancing, such partitioning enables virtually unlimited scalability of the simulation platform. The approach has been used to extend the AgentFly air-traffic testbed to support simulation of a complete civilian air-traffic touching National Air-Space of United States. Thorough evaluation of the system has been performed, confirming that it can scale up to a very high number of complex agents operating simultaneously (thousands of aircraft) and determining the impact of different configurations of the simulation architecture on its overall performance.

Dynamic Information Source Selection for Intrusion Detection Systems

  • Autoři: Rehák, M., Staab, E., prof. Dr. Michal Pěchouček, MSc., Stiborek, J., Grill, M., Bartoš, K.
  • Publikace: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems. New York: ACM Press, 2009. p. 1009-1016. ISBN 978-0-9817381-7-8.
  • Rok: 2009
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Our work presents a mechanism designed for the selection of the optimal information provider in a multi-agent, heterogeneous and unsupervised monitoring system. The self-adaptation mechanism is based on the insertion of a small set of prepared challenges that are processed together with the real events observed by the system. The evaluation of the system response to these challenges is used to select the optimal information source. Our algorithm uses the concept of trust to identify the best source and to optimize the number of challenges inserted into the system. The mechanism is designed for intrusion/fraud detection systems, which are frequently deployed as part of online transaction processing (banking, telecommunications or process monitoring systems). Our approach features unsupervised adjustment of its configuration and dynamic adaptation to the changing environment, which are both vital for these domains.

Flight Trajectory Path Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper describes an application of the A* algorithm for flight path planning for airplanes with defined motion dynamics operating in a continuous three-dimensional space constrained by existing physical obstacles. The presented A* algorithm modification provides significant acceleration (reduction of the state space) of the path planning process. The described algorithm is able to find a path through small gaps between obstacles using a pre-defined searching precision. The paper documents a set of path planning benchmarks where the solution quality and internal algorithm properties are compared against the A* algorithm for flight trajectory path planning.

Goal-Based Adversarial Search - Searching Game Trees in Complex Domains using Goal-based Heuristic

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a novel approach to reducing adversarial search space by using background knowledge represented in the form of higher-level goals that players tend to pursue in the game. The algorithm is derived from a simultaneous-move modification of the maxn algorithm by only searching the branches of the game tree that are consistent with pursuing player's goals. The algorithm has been tested on a real-world-based scenario modelled as a large-scale asymmetric game. The experimental results obtained indicate the ability of the goal-based heuristic to reduce the search space to a manageable level even in complex domains while maintaining the high quality of resulting strategies.

I-Globe: Distributed planning and coordination of mixed-initiative activities

  • Pracoviště: Katedra počítačů
  • Anotace:
    We present an approach to distributed planning and coordination architecture for dynamic non-deterministic multi-actor mixed-initiative environment. The system provides flexible planning, replanning, and task allocation. The key idea of the presented approach is in integration of (i) I-X hierarchical planner with (ii) agent-based architecture and (iii) commitment-based plan representation. The implementation of the system was verified and evaluated on simulated environment. The experimental validation confirms the performance, stability, and robustness of the system in complex scenarios.

Integration of Probability Collectives for Collision Avoidance in AGENTFLY

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Rising deployment of Unmanned Aerial Assets in komplex operations requires innovative automatic coordination algorithms, especially for decentralized collision avoidance. The paper investigates a stochastic Probability Collectives (PC) optimizer for the collision avoidance problem defined as an optimization task where efficiency criteria, collision penalties and airplanes' missions are integrated in an objektive function. The paper provides two different implementation approaches of the proposed method - complex multiagent deployment distributes the PC optimization process among airplanes and the Process Integrated Mechanism approach replaces communication with optimizer migration. Both implementations have been developed and tested on an airspace multi-agent framework AGENTFLY.

Multi-Agent Planning with Decommitment

  • Pracoviště: Katedra počítačů
  • Anotace:
    One of the problems that must be solved during coalition operations is the planning problem: finding a course of actions for the operation. Knowledge-based planning is a technique that can be used to address this problem. However, traditional planning has focussed on the finding of a plan that achieves a given goal or accomplishes a given task. During a coalition operation such a plan may need to be agreed between the different parties involved in the coalition. In this paper we shall describe an approach that can be used for finding an agreed plan. This plan will include a set of decommitment rules allowing participants to specify conditions under which they are allowed to deviate from the agreed course of action. The proposed algorithm can be used as the basis for an automated planner, but it should also be usable in a mixed-initiative setting.

Optimization based Collision Avoidance for Cooperating Airplanes

  • Autoři: doc. Ing. David Šišlák, Ph.D., Volf, P., prof. Dr. Michal Pěchouček, MSc., Suri, N., Nicholson, D., Woodhouse, D.
  • Publikace: 2009 IEEE/WIC/ACM INTERNATIONAL JOINT CONFERENCES ON WEB INTELLIGENCE (WI) AND INTELLIGENT AGENT TECHNOLOGIES (IAT), VOL 2. Los Alamitos: IEEE Computer Society, 2009, pp. 375-378. ISBN 978-1-4244-5331-3.
  • Rok: 2009
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Application of autonomous intelligent systems into airspace domain is very important nowadays. The paper presents decentralized collision avoidance algorithm utilizing a solution of the defined optimization problem where efficiency criteria, collision penalties and airplanes' missions are integrated in an objective function. Two different implementation approaches used for stochastic Probability Collectives optimizer are presented and evaluated - a complex distributed multi-agent deployment among participating airplanes and the Process Integrated Mechanism inspired architecture. Both approaches have been validated and evaluated on the multi-agent framework AGENTFLY providing precise simulation for airspace operations.

Relaxation Of Social Commitments In Multi Agent Dynamic Environment

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The role of social commitments in distributed, multi-agent planning and plan execution will be discussed in this article. We argue agents' capability to reason about the actions in the form of social commitments directly improving robustness of the plans in dynamic, multi-actor environment. We focused on relaxation decommitment strategy, targeted specifically to the time interval in which the agent agrees to accomplish the commitment. We will discuss how changes of this interval affect the plan execution and how the potential changes of this interval can be represented in the commitment itself. The value of the use of social commitments in planning in dynamic, multi-actor environment has been documented on a series of empirical experiments.

Runtime Monitoring and Dynamic Reconfiguration for Intrusion Detection Systems

  • Autoři: Rehák, M., Staab, E., Fusenig, V., prof. Dr. Michal Pěchouček, MSc., Grill, M., Stiborek, J., Bartoš, K., Engel, T.
  • Publikace: Recent Advances in Intrusion Detection. Heidelberg: Springer, 2009, pp. 61-80. Lecture Notes in Computer Science. ISSN 0302-9743. ISBN 978-3-642-04341-3.
  • Rok: 2009
  • DOI: 10.1007/978-3-642-04342-0_4
  • Odkaz: https://doi.org/10.1007/978-3-642-04342-0_4
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Our work proposes a generic architecture for runtime monitoring and optimization of IDS based on the challenge insertion. The challenges, known instances of malicious or legitimate behavior, are inserted into the network traffic represented by NetFlow records, processed with the current traffic and the system's response to the challenges is used to determine its effectiveness and to fine-tune its parameters. The insertion of challenges is based on the threat models expressed as attack trees with attached risk/loss values. The use of threat model allows the system to measure the expected undetected loss and to improve its performance with respect to the relevant threats, as we have verified in the experiments performed on live network traffic.

Threat-model-driven runtime adaptation and evaluation of intrusion detection system

  • Autoři: Rehák, M., Staab, E., Fusenig, V., Stiborek, J., Grill, M., Bartoš, K., prof. Dr. Michal Pěchouček, MSc., Engel, T.
  • Publikace: International Conference on Autonomic Computing. New York: ACM Press, 2009, pp. 65-66. ISBN 978-1-60558-564-2.
  • Rok: 2009
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a mechanism for autonomous self-adaptation of a network-based intrusion detection system (IDS). The system is composed of a set of cooperating agents, each of which is based on an existing network behavior analysis method. The self adaptation mechanism is based on the insertion of a small number of challenges, i.e. known instances of past legitimate or malicious behavior. The response of individual system components to these challenges is used to measure and eventually optimize the system performance in terms of accuracy. In this work we show how to choose the challenges in a way such that the IDS attaches more importance to the detection of attacks that cause much damage.

Towards Cooperative Predictive Data Mining in Competitive Environments.

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We study the problem of predictive data mining in a competitive multi-agent setting, in which each agent is assumed to have some partial knowledge required for correctly classifying a set of unlabelled examples. The agents are self-interested and therefore need to reason about the trade-offs between increasing their classification accuracy by collaborating with other agents and disclosing their private classification knowledge to other agents through such collaboration. We analyze the problem and propose a set of components which can enable cooperation in this otherwise competitive task. These components include measures for quantifying private knowledge disclosure, data-mining models suitable for multi-agent predictive data mining, and a set of strategies by which agents can improve their classification accuracy through collaboration. The overall framework and its individual components are validated on a synthetic experimental domain.

A Game based Approach to Comparing Different Coordination Mechanisms

  • Autoři: Ford, K.M., Suri, N., Košnar, K., Jisl, P., Ing. Petr Benda, prof. Dr. Michal Pěchouček, MSc., Přeučil, L.
  • Publikace: Distributed Human-Machine Systems. Praha: CTU Publishing House, 2008, pp. 20-25. ISBN 978-80-01-04027-0.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Achieving coordinated behavior among multiple physical or logical entities is a challenging problem. Research in coordination has traditionally focused on either centralized or distributed approaches, but both approaches have inherent problems. The Process Integrated Mechanism (PIM) is a novel approach to coordination that relies on strong mobility to rapidly move a single process (the Coordinating Process or CP) among all the nodes that are part of the PIM. The continuous migration of a single process that performs the coordination combines the best of centralized and distributed approaches - simplicity of programming and reliability without a single point of failure. This paper proposes a method for the comparison of a traditional distributed approach based on Multi Agent Systems (MAS) and the new PIM approach. A simplified version of the Capture-the-Flag game is used for evaluation. One side is controlled by the MAS whereas the other side is controlled by the PIM.

AGENTFLY: A Multi-Agent Airspace Test-bed

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The contribution presents a multi-agent technology in the domain of the air-traffic control of several autonomous seriál vehicles (manned as well as unmanned). The system has been validated mainly by the collision avoidance (CA) tasks. Several cooperative and non-cooperative CA methods have been integrated in the system to validate and compare thein properties in the scalable experiments. The AGENTFLY system is suitable also for the developing and testing of algorithms for the collective flight control. The operation of the underlying multi-agent system has been integrated with freely available geographical and tactical data sources. The system provides real time 2D/3D visualization and also the web-access component.

AGENTFLY: Towards Multi-Agent Technology in Free Flight Air Traffic Control

  • Autoři: doc. Ing. David Šišlák, Ph.D., prof. Dr. Michal Pěchouček, MSc., Volf, P., Pavlíček, D., Samek, J., Mařík, V., Losiewicz, P.
  • Publikace: Defense Industry Applications of Autonomous Agents and Multi-Agent Systems. Heidelberg: Birkhäuser Verlag AG, 2008. p. 73-96. Whitestein Series in Software Agent Technologies and Autonomic Computing. ISBN 978-3-7643-8570-5.
  • Rok: 2008
  • DOI: 10.1007/978-3-7643-8571-2_5
  • Odkaz: https://doi.org/10.1007/978-3-7643-8571-2_5
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Ever rising deployment of Unmanned Aerial Assets (UAAs) in complex military and rescue operations require novel and innovative methods for intelligent planning and collision avoidance among a high number of heterogeneous, semi-trusted flying assets in well specified and constrained areas [1]. We have studied the free flight concept as an alternative to the classical, centralized traffic control. In free flight the unmanned aerial assets are provided with flight trajectory that has been elaborated without consideration of other flying objects that may occupy the same air space. The collision threads are detected by each of the aircraft individually and the collisions are avoided by an asset-to-asset negotiation. Multi-agent technology is very well suited as a technological platform for supporting the free-flight concept among the heterogeneous UAAs. In this chapter we present AGENTFLY, multi-agent system for free-flight simulation and flexible collision avoidance.

CAMNEP: An intrusion detection system for high speed networks

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Bartoš, K., Grill, M., Celeda, P., Krmicek, V.
  • Publikace: Progress in Informatics. 2008, 4(5), 65-74. ISSN 1349-8614.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The presented research aims to detect malicious traffic in high speed networks by means of correlated anomaly detection methods. In order to acquire the real-time traffic statistics in NetFlow format, we deploy transparent inline probes based on FPGA elements. They provide traffic statistics to the agent-based detection layer, where each agent uses a specific anomaly detection method to detect anomalies and describe the flows in its extended trust model. The agents share the anomaly assessments of individual network flows that are used as an input for the agent's trust models. The trustfulness values of individual flows from all agents are combined to estimate their maliciousness. The estimate of trust is subsequently used to filter out the most significant events that are reported to network operators for further analysis.

Case studies for contract-based systems

  • Pracoviště: Katedra kybernetiky, Katedra počítačů
  • Anotace:
    Of the ways in which agent behaviour can be regulated in a multi-agent system, electronic contracting - based on explicit representation of different parties' responsibilities, and the agreement of all parties to them - has significant potential for modern industrial applications. Based on this assumption, the CONTRACT project aims to develop and apply electronic contracting and contract-based monitoring and verification techniques in real world applications. This paper presents results from the initial phase of the project, which focused on requirements solicitation and analysis. Specifically, we survey four use cases from diverse industrial applications, examine how they can benefit from an agent-based electronic contracting infrastructure and outline the technical requirements that would be placed on such an infrastructure. We present the designed CONTRACT architecture and describe how it may fulfil these requirements.

Collaborative Approach to Network Behavior Analysis

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Grill, M., Bartoš, K., Čeleda, P., Krmíček, V.
  • Publikace: Global E-Security. Heidelberg: Springer, 2008, pp. 153-160. ISSN 1865-0929. ISBN 978-3-540-69402-1.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Network Behavior Analysis techniques are designed to detect intrusions and other undesirable behavior in computer networks by analyzing the traffic statistics. We present an efficient framework for integration of anomaly detection algorithms working on the identical input data. This framework is based on high-speed network traffic acquisition subsystem and on trust modeling, a well-established set of techniques from the multi-agent system field. Trust-based integration of algorithms results in classification with lower error rate, especially in terms of false positives. The presented framework is suitable for both online and offline processing, and introduces a relatively low computational overhead compared to deployment of isolated anomaly detection algorithms.

Collaborative Learning with Logic-Based Models

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Adaptability is a fundamental property of any intelligent system. In this paper, we present how adaptability in multi-agent systems can be implemented by means of collaborative logic-based learning. The proposed method is based on two building blocks: (1) a set of operations centred around inductive logic programming for generalizing agents' observations into sets of rules, and (2) a set of communication strategies for sharing acquired knowledge among agents in order to improve the collaborative learning process. Using these modular building blocks, several learning algorithms can be constructed with different trade-offs between the quality of learning, computation and communication requirements, and the disclosure of the agent's private information. The method has been implemented as a modular software component that can be integrated into the control loop of an intelligent agent.

Decentralized Algorithms for Collision Avoidance in Airspace

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper proposes decentralized deconfliction algorithms deployed on multiple autonomous aerial vehicles in freeflight operations. The paper provides two separate algorithms for collision avoidance - one based on the iterative peer-to-peer negotiation solving a singular collision and second based on multi-party negotiation about a cluster of collisions. The presented decentralized algorithms allow the vehicles operating in the same area to utilize the given airspace more efficiently. The algorithms have been developed and tested on a multi-agent prototype and the properties of both algorithms are discussed on a set of large scale experiments.

ExtraPlanT as a Multi-Agent System for Extra-Enterprise Collaboration

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The ExtraPlanT system addresses the concept of the extra-enterprise production planning in order to manage efficient resource allocation not only within the enterprise, but also at the company external environments (e.g. suppliers, co-operators involved in the supply chain or virtual organization environments). ExtraPlanT demonstrates the ability of multi-agent systems to improve business processes on the extra-enterprise level and to bring the virtual organization ideas to the real industrial environment.

Filter Allocation Using Iterative ECNP

  • Autoři: Tožička, J., Urban, Š., Prokopová, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Cooperative Information Agents XII. Heidelberg: Springer, 2008, pp. 221-233. ISSN 0302-9743. ISBN 978-3-540-85833-1.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Network devices can filter traffic in order to protect end user computers against network worms and other threats. Since these devices have very limited memories and cannot deploy filters against every known worm, the traffic can be forwarded to other device during so called filter delegation. In this contribution we present two negotiation based algorithms looking for a good filter delegation solution. We formally describe this filter allocation problem in a network dealing with distribution of filters among agents so that several constraints are fulfilled and we extend this problem to fit a real world task. We show that both the basic problem and its extension are NP complete. Both algorithms solving this problem are experimentally evaluated on a realistic network simulation.

Improving Anomaly Detection Error Rate by Collective Trust Modeling

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Bartoš, K., Grill, M., Čeleda, P., Krmíček, V.
  • Publikace: Recent Advances in Intrusion Detection 2008 11th International Symposium. Heidelberg: Springer, 2008, pp. 398-399. ISSN 0302-9743. ISBN 978-3-540-87402-7.
  • Rok: 2008
  • DOI: 10.1007/978-3-540-87403-4_25
  • Odkaz: https://doi.org/10.1007/978-3-540-87403-4_25
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Current Network Behavior Analysis (NBA) techniques are based on anomaly detection principles and therefore subject to high error rates. We propose a mechanism that deploys trust modeling, a technique for cooperator modeling from the multi-agent research, to improve the quality of NBA results. Our system is designed as a set of agents, each of them based on an existing anomaly detection algorithm coupled with a trust model based on the same traffic representation. These agents minimize the error rate by unsupervised, multi-layer integration of traffic classification. The system has been evaluated on real traffic in Czech academic networks.

Incrementally Refined Acquaintance Model for Consortia Composition

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents a specific contracting algorithm that contributes to the process of distributed planning and resource allocation in competitive, semi-trusted environments. The presented contraction algorithm is based on incrementally refined acquaintance models (IRAM) of the actor that provide the right set of approximate knowledge needed for appropriate task decomposition and delegation. This paper reports on empirical evaluation of the IRAM algorithm deployment in consortia formation domain.

Incrementaly Refined Acquaintance Model (IRAM) for Request based Virtual Organization Formation

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents a specific contracting algorithm that contributes to the process of distributed planning and resource allocation in competitive, semi-trusted environments. The presented contraction algorithm is based on incrementally refined acquaintance models (IRAM) of the actor that provide the right set of approximate knowledge needed for appropriate task decomposition and delegation. This paper reports on empirical evaluation of the IRAM algorithm deployment in Request-based Virtual Organizations formation domain.

Industrial Deployment of Multi-agent Technologies: Review and Selected Case Studies

  • DOI: 10.1007/s10458-008-9050-0
  • Odkaz: https://doi.org/10.1007/s10458-008-9050-0
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper reports on industrial deployment of multi-agent systems and agent technology. It provides an overview of several application domains and an in-depth presentation of four specific case studies. The presented applications and deployment domains have been analyzed. The analysis indicates that despite strong industrial involvement in this field, the full potential of the agent technology has not been fully utilized yet and that not all of the developed agent concepts and agent techniques have been completely exploited in industrial practice. In the paper, the key obstacles for wider deployments are listed and potential future challenges are discussed.

MALEF: Framework for distributed machine learning and data mining

  • Autoři: Tožička, J., Rovatsos, M., prof. Dr. Michal Pěchouček, MSc., Urban, Š.
  • Publikace: International Journal of Intelligent Information and Database Systems. 2008, 2(1), 6-24. ISSN 1751-5858.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Growing importance of distributed data mining techniques has recently attracted attention of researchers in multiagent domain. In this paper we present a novel framework MultiAgent Learning Framework (MALEF) designed for both the agent-based distributed machine learning as well as data mining. Proposed framework is based on: the exchange of meta-level descriptions of individual learning process; online reasoning about learning success and learning progress. This paper illustrates how MALEF framework can be used in practical system in which different learners use different datasets, hypotheses and learning algorithms. We describe our experimental results obtained using this system and review related work on the subject.

Návrh koncepce výuky informatiky na FEL

Planning and Re-planning in Multi-actors Scenarios by means of Social Commitments

  • DOI: 10.1109/IMCSIT.2008.4747215
  • Odkaz: https://doi.org/10.1109/IMCSIT.2008.4747215
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present an approach to plan representation in multi-actors scenarios that is suitable for flexible replanning and plan revision purposes. The key idea of the presented approach is in integration of (i) the results of an arbitrary HTN (hierarchical task network) -oriented planner with (ii) the concept of commitments, as a theoretically studied formalism representing mutual relations among intentions of collaborating agents. The paper presents formal model of recursive form of commitments and discusses how it can be deployed to a selected scenario.

ProPlanT as a Multi-Agent Technology for Decision-Making Support

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper presents the concept of ProPlanT multi-agent system which has been designed for planning the manufacturing process in project driven production domain.

Social Knowledge in Multi-Agent Systems

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Encyclopedia of Networked and Virtual Organizations - vol. III Pu-Z. Hershey: Information science Reference, 2008. p. 1456-1465. ISBN 978-1-59904-885-7.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper presents the concept of social knowledge in multi-agent systems as a computational model of agents mutual awareness and explains their role in the domain of virtual organizations.

Trust Based Classifier Combination for Network Anomaly Detection

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Grill, M., Bartoš, K.
  • Publikace: Cooperative Information Agents XII. Heidelberg: Springer, 2008, pp. 116-130. ISSN 0302-9743. ISBN 978-3-540-85833-1.
  • Rok: 2008
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a method that improves the results of network intrusion detection by integrating several anomaly detection algorithms through trust and reputation models. Our algorithm is based on existing network behavior analysis approaches that are embodied into several detection agents. We divide the processing into three distinct phases: anomaly detection, trust model update and collective trusting decision. Each of these phases contributes to the reduction of classification error rate, by the aggregation of anomaly values provided by individual algorithms, individual update of each agent's trust model based on distinct traffic representation features (derived from its anomaly detection model), and re-aggregation of the trustfulness data provided by individual agents. The result is a trustfulness score for each network flow, which can be used to guide the manual inspection, thus significantly reducing the amount of traffic to analyze.

Utility-based Model for Classifying Adversarial Behaviour in Multi-Agent Systems

  • DOI: 10.1109/IMCSIT.2008.4747216
  • Odkaz: https://doi.org/10.1109/IMCSIT.2008.4747216
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Interactions and social relationships among agents are an important aspect of multi-agent systems. In this paper, we explore how such relationships and their relation to agent's objectives influence agent's decision-making. Building on the framework of stochastic games, we propose a classification scheme, based on a formally defined concept of interaction stance, for categorizing agent's behaviour as self-interested, altruistic, competitive, cooperative, or adversarial with respect to other agents in the system. We show how the scheme can be employed in defining behavioural norms, capturing social aspects of agent's behaviour and/or in representing social configurations of multiagent systems.

A Framework for Agent-Based Distributed Machine Learning and Data Mining

  • Autoři: Tožička, J., Rovatsos, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the Sixth International Conference on Autonomous Agents and Multiagent Systems. County of Richland: IFAAMAS, 2007, pp. 666-673. ISBN 978-81-904262-7-5.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper proposes a framework for agent-based distributed machine learning and data mining based on (i) the exchange of meta-level descriptions of individual learning processes among agents and (ii) online reasoning about learning success and learning progress by learning agents. We present an abstract architecture that enables agents to exchange models of their local learning processes and introduces a number of different methods for integrating these processes. This allows us to apply existing agent interaction mechanisms to distributed machine learning tasks, thus leveraging the powerful coordination methods available in agent-based computing, and enables agents to engage in meta-reasoning about their own learning decisions. We apply this architecture to a real-world distributed clustering application to illustrate how the conceptual framework can be used in practical systems in which different learners may be using different datasets, hypotheses and learning algorithms.

Agent Based Approach to Mass Oriented Production Planning: Case Study

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Rehák, M., Charvát, P., Vlček, T., Kolář, M.
  • Publikace: IEEE Transactions on Systems, Man, and Cybernetics: Part C. 2007, 37(3), 386-395. ISSN 1094-6977.
  • Rok: 2007
  • DOI: 10.1109/TSMCC.2006.889537
  • Odkaz: https://doi.org/10.1109/TSMCC.2006.889537
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper discusses the potential of multiagent planning techniques in the production-planning domain, with special focus on mass-oriented production. The research presented in the paper has been centered around ExPlanTech-a specific implementation of a production-planning multiagent system. Suitability of ExPlanTech for mass-oriented and project-driven manufacturing is also discussed in the paper. Applicability of multiagent concepts is demonstrated on a multiagent planning architecture and production-planning case study at a Skoda Auto Engine Plant.

Agent Based Network Intrusion Detection System

  • Autoři: Krmicek, V., Celeda, P., Rehák, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: 2007 IEEE/WIC/ACM International Conference on Intelligent Agent Technology - Proceedings. Los Alamitos: IEEE Computer Society, 2007, pp. 528-531. ISBN 978-0-7695-3027-7.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper presents security platform based on agents as an efficient and robust solution for high-performance intrusion detection system designed for deployment on highspeed network links. The proposed detection algorithm is based on extension of trust modeling techniques with representation of uncertain identities, context representation and implicit assumption that significant traffic anomalies are a result of potentially malicious action. The heterogeneous anomaly detection methods are used by cooperating agents and then correlated using a reputation mechanism. To satisfy the performance requirements, wire-speed data acquisition layer is based on hardware-accelerated Net-Flow probes that provide overview of current network traffic.

Agent Based Network Protection Against Malicious Code

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Tožička, J., Prokopová, M., Medvigy, D., Novotný, J.
  • Publikace: Multi-Agent Systems and Applications V. Heidelberg: Springer, 2007, pp. 22-31. ISSN 0302-9743. ISBN 978-3-540-75253-0.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents an agent-based approach to Network Intrusion Prevention on corporate networks, emphasizing the protection from fast-spreading mobile malicious code outbreaks (e.g. worms) and related threats. Agents are not only used as a system-integration platform, but we use modern agent approaches to trust modeling and distributed task allocation to efficiently detect and also counter the attack by automatically created and deployed filters. The ability of the system to react autonomously, without direct human supervision, is crucial in countering the fast-spreading worms, that employ efficient scanning strategies to immediately spread farther once they infect a single host in the network.

Agent Methods for Network Intrusion Detection and Response

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Medvigy, D., Prokopová, M., Tožička, J., Foltýn, L.
  • Publikace: Holonic and Multi-Agent Systems for Manufacturing - HoloMAS 2007. Munich: Springer, 2007, pp. 149-160. ISSN 0302-9743. ISBN 978-3-540-74478-8.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    While the need to build the Intrusion Detection Systems (IDS) based on on a distributed and cooperative (P2P) paradigm is being generally acknowledged, the field has been disconnected from the recent advances in the multi-agent research, most notably the field of trust modeling. Our contribution reviews recent implementations of IDS systems and presents them from an agent research perspective. We also identify the opportunities where the agent approaches can be successfully used. Agent techniques can make the IDS more adaptive, scalable and reliable while increasing their autonomy and reducing the maintenance requirements. Besides trust modeling, we propose that the distributed decision-making and planning techniques can be used to shorten the detection-response loop, making the system more robust while facing worm attacks.

Agent-Based Multi-Layer Collision Avoidance to Unmanned Aerial Vehicles

  • DOI: 10.1109/KIMAS.2007.369837
  • Odkaz: https://doi.org/10.1109/KIMAS.2007.369837
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This contribution presents a distributed, multi-layer collision avoidance architecture supporting efficient utilization of air space shared by several autonomous aerial vehicles. Presented multi-layer architecture is based on deliberative deployment of several collision avoidance methods by the aircraft at the same time. Both cooperative and non-cooperative collision avoidance methods are presented in the paper. The robustness of the architecture is justified by means of experimental validation of multi-agent simulation.

An Intelligent Telephony Interface of Multiagent Decision Support Systems

  • Autoři: Becvar, P., Smid, L., Psutka, J., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: IEEE Transactions on Systems, Man, and Cybernetics: Part C. 2007, 37(6), 553-560. ISSN 1094-6977.
  • Rok: 2007
  • DOI: 10.1109/TSMCC.2007.897335
  • Odkaz: https://doi.org/10.1109/TSMCC.2007.897335
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    ExtraPlanT is a multiagent production planning system designed for small and medium sized enterprises with project oriented production. In order to make the results of the system available even to users who are located away from the enterprise, it has been equipped with the possibility of remote access a Web and telephony interface. The multiagent design of the ExtraPlanT makes the integration of these interfaces robust and simple. The telephony interface uses VoiceXML technology so that it can be built without extensive knowledge of speech processing. The interface also uses innovative techniques to overcome the common disadvantages of speech as a medium for machine output.

Autonomous Protection Mechanism for Joint Networks in Coalition Operations

  • Autoři: Rehák, M., Tožička, J., prof. Dr. Michal Pěchouček, MSc., Prokopová, M., Foltýn, L.
  • Publikace: Proceedings of 2007 International Conference on Integration of Knowledge Intensive Multi Agent Systems. Piscataway: IEEE, 2007, pp. 384-389. ISBN 1-4244-0945-4.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Any successful coalition cooperation requires efficient communication network connecting the coalition members. Protection of this joint network requires special techniques as it is highly dynamic, heterogenous and a joint network management team can not always be established. To address the requirements for joint network protection, we propose a design of a highly autonomous, adaptive and decentralized agent-based mechanism for network intrusion detection and self-protection. Detection process is based on correlation of anomalies in network traffic with simple alarms raised by host-based intrusion detection components, in order to achieve a low false positive rate. The self-protection mechanism features distributed, policy driven deployment of automatically generated filters. Our approach doesn't require any direct operator oversight, but all components are subject to policies established by their owners to prevent undesirable behavior or system misuse.

Collaborative Attack Detection in High Speed Networks

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Čeleda, P., Krmíček, V., Minařík, P., Medvigy, D.
  • Publikace: Multi-Agent Systems and Applications V. Heidelberg: Springer, 2007, pp. 73-82. ISSN 0302-9743. ISBN 978-3-540-75253-0.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a multi-agent system designed to detect malicious traffic in high-speed networks. In order to match the performance requirements related to the traffic volume, the network traffic data is acquired by hardware accelerated probes in NetFlow format and preprocessed before processing by the detection agent. The proposed detection algorithm is based on extension of trust modeling techniques with representation of uncertain identities, context representation and implicit assumption that significant traffic anomalies are a result of potentially malicious action. In order to model the traffic, each of the cooperating agents uses an existing anomaly detection method, that are then correlated using a reputation mechanism. The output of the detection layer is presented to operator by a dedicated analyst interface agent, which retrieves additional information to facilitate incident analysis.

Collaborative Learning with Logic-Based Models

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Adaptivity is a fundamental property of any intelligent system. In this paper, we present how adaptivity in multi-agent systems can be implemented by means of collaborative logic-based learning. The proposed method uses inductive logic programming to generalize agents' observations into sets of rules and inter-agent communication of acquired knowledge to improve team adaptation process. Based on Horn logic, the method is interoperable with semantic web languages and techniques. It has been implemented as a modular software component that can be readily integrated into the control loop of an intelligent agent or an autonomic component. We have evaluated the method on a realistic logistic scenario, in which teams of trading agents learn the properties of the environment in order to optimize their operation.

Competitive Contract Net Protocol

  • DOI: 10.1007/978-3-540-69507-3_57
  • Odkaz: https://doi.org/10.1007/978-3-540-69507-3_57
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The proposed Competitive Contract Net Protocol has been designed to facilitate a flexible cooperation in competitive multi-agent environments and to support automated or semi-automated negotiations in competitive domains. The protocol is based on FIPA standards. The protocol covers not only the phase of contracting the commitments, but also allows for a decommitment negotiation and contract termination. Thus, it consists of three phases: (i) a contracting phase, where conditions of agreement are concluded, (ii) an optional decommitment phase, where contract may be breached, and (iii) a contract termination phase, where the compliance with the concluded contract conditions is evaluated

Convergence of Peer to Peer Collision Avoidance among Unmanned Aerial Vehicles

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In this article we study the theoretical aspects of the collision avoidance among the collectives of unmanned aerial vehicles (UAVs) engaged in the free flight operation. The free flight based operations do not provide collision-free trajectories as a flight specification to the UAVs. Collision avoidance of the trajectories is implemented by means of peer-to-peer negotiations among the individual UAVs. In this paper we study the role of interaction in the collision avoidance process. We prove theoretically convergence of the specific negotiating protocol that has been deployed in a practical implementation of the software prototype of the distributed collision avoidance system.

Detecting Intrusions in Agent System by Means of Exception Handling

  • Autoři: Platon, E., Rehák, M., Sabouret, N., prof. Dr. Michal Pěchouček, MSc., Honiden, S.
  • Publikace: Holonic and Multi-Agent Systems for Manufacturing - HoloMAS 2007. Munich: Springer, 2007, pp. 161-172. ISSN 0302-9743. ISBN 978-3-540-74478-8.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a formal approach to conception of a dedicated security infrastructure based on the exception handling in the protected agents. Security-related exceptions are identified and handled by a dedicated reflective layer of the protected agent, or delegated to specialized intrusion management agents in the system if the local reflective layer fails to address the problem. Incidents are handled either directly, if a known remedy exists or indirectly, when an appropriate solution must be identified before response execution. The cooperation between the intrusion management agents and aggregation of their observations can make the system more resilient to misclassification than a solution based purely on signature matching.

High Performance Agent System for Intrusion Detection in Backbone Networks

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Čeleda, P., Krmíček, V., Moninec, J., Dymáček, T., Medvigy, D.
  • Publikace: Cooperative Information Agents XI. Düsseldorf: Springer VDI Verlag, 2007, pp. 134-148. ISSN 0302-9743. ISBN 978-3-540-75118-2.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    High Performance Agent System for Intrusion Detection in Backbone Networks

Incrementally Refined Acquaintance Model for Distributed Planning and Resource Allocation in Semi-Trusted Environments

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Rehák, M., Mařík, V.
  • Publikace: 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops (WI-IAT Workshops 2007). Piscataway: IEEE, 2007, pp. 391-394. ISBN 978-0-7695-3028-4.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents a specific contracting algorithm that contributes to the process of distributed planning and resource allocation in competitive, semi-trusted environments. The presented contraction algorithm is based on incrementally refined acquaintance models (IRAM) of the agents that provide the right set of approximate knowledge needed for appropriate task decomposition.

Multi party Collision Avoidance among Unmanned Aerial Vehicles

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper addresses the problem of distributed cooperative collision avoidance that supports efficient utilization of air space shared by several autonomous unmanned aerial vehicles. The novel multi-party collision avoidance (MPCA) algorithm is described. It is compared to the iterative peer-to-peer collision avoidance (IPPCA) algorithm that iteratively optimizes social welfare. The paper provides a set of experiments and a comparison of different collision avoidance mechanisms in a multi-agent model of air traffic.

Multi-Agent Reflection in Autonomic Systems

  • Autoři: Tožička, J., prof. Dr. Michal Pěchouček, MSc., Rehák, M., Prokopová, M.
  • Publikace: Holonic and Multi-Agent Systems for Manufacturing - HoloMAS 2007. Munich: Springer, 2007, pp. 27-36. ISSN 0302-9743. ISBN 978-3-540-74478-8.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Increasing complexity and scales of computing systems bring growing demands on their designers and administrators. These issues have been explored from different viewpoints. While the multi-agent system researchers focus on the coordination and theoretic properties of distributed system, the researchers from the field of autonomic computing focus on the deployment of self-adapting systems in real domains. This contribution tries to bring together both domains and presents the multi-agent reflection from the autonomic computing point of view. We show that proposed architecture of reflective agent covers all the characteristics of an autonomic computing system and furthermore, we describe some properties of reflective agents that can further extend the autonomic computing system, especially its self-optimizing abilities.

Multi-agent-Based Diagnostics of Automotive Electronic Systems

  • Autoři: Pavlíček, D., prof. Dr. Michal Pěchouček, MSc., Mařík, V., Flek, O.
  • Publikace: Holonic and Multi-Agent Systems for Manufacturing - HoloMAS 2007. Munich: Springer, 2007, pp. 371-382. ISSN 0302-9743. ISBN 978-3-540-74478-8.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The diagnostic system discussed in this paper provides an agent-based approach to advanced on-board diagnostics of operation and communication failures occurring in an electronic automotive system. The paper presents both the proof-of-concept on-board diagnostics system and the simulation layer used for its development and testing. The following topics are covered: simulation of the hardware units, simulation of user-invoked hardware failures, distributed detection and diagnostics of the failures, and visualization.

Multi-robot Exploration Using Multi-agent Approach

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper deals with a problem of exploring an unknown environment by a team of mobile robots. Widely used approach in the robotic community is frontier based exploration. We combine this technique with a multi-agent architecture A-globe, which allows solving the exploration problem with limited communication accessibility and with changing number of participating robots. Frontier based approach heavily depends on path planning algorithm. A novel method combining A* search with harmonic potential fields is also presented. Finally, the Iterative Closest Point localization algorithm has been improved in several ways, in order to increase its speed and robustness. The whole exploration framework has been implemented and tested in both simulated and real environments.

Network Intrusion Detection by Means of Community of Trusting Agents

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Bartoš, K., Grill, M., Celeda, P.
  • Publikace: 2007 IEEE/WIC/ACM International Conference on Intelligent Agent Technology - Proceedings. Los Alamitos: IEEE Computer Society, 2007, pp. 498-504. ISBN 978-0-7695-3027-7.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We apply advanced agent trust modeling techniques to identify malicious traffic in computer networks. Our work integrates four state-of-the-art techniques from anomaly detection, and combines them by means of extended trust model. Deployment of trust model ensures interoperability between methods, allows cross-correlation of results during various stages of the detection and ensures efficient evaluation of current traffic in the context of historical observations. The goal of the system, which is designed for online monitoring of high-speed network, is to provide efficient tool for targeted runtime surveillance of malicious traffic by network operators.

Od osamocených robotů ke kolaborativní robotice

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Od osamocených robotů ke kolaborativní robotice

Planning and Choosing: Augmenting HTN Based Agents with Mental Attitudes

  • Autoři: Wickler, G., Potter, S., Tate, A., prof. Dr. Michal Pěchouček, MSc., Semsch, E.
  • Publikace: Intelligent Agent Technology. Los Alamitos: IEEE Computer Society, 2007, pp. 222-228. ISBN 978-0-7695-3027-7.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Planning and Choosing: Augmenting HTN Based Agents with Mental Attitudes

Practical Lessons of Artificial Intelligence and Multi-Agent Systems

  • Autoři: Tožička, J., Urban, Š., prof. Dr. Michal Pěchouček, MSc., Čepek, J.
  • Publikace: Proceedings of the 18th EAEEIE Annual Conference. Praha: České vysoké učení technické v Praze, 2007, ISBN 978-80-01-03745-4.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Artificial intelligence belongs to the youngest research areas of computer science, very dynamic field of information science. The research in multi-agent systems, a booming field of artificial intelligence, advances very quickly. Therefore it is very difficult to keep pace with this progress in the education and educate students that will be able to reuse their knowledge in practice. In this contribution we show why and how we plan to involve the research in the domain of e-home and created an open system that can be used by students to practice the creation of multi-agent system, or integrate other methods of artificial intelligence.

Trust Modeling with Context Representation and Generalized Identities

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Cooperative Information Agents XI. Düsseldorf: Springer VDI Verlag, 2007, pp. 298-312. ISSN 0302-9743. ISBN 978-3-540-75118-2.
  • Rok: 2007
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a trust model extension that attempts to relax the assumptions that are currently taken by the majority of existing trust models: (i) proven identity of agents, (ii) repetitive interactions and (iii) similar trusting situations. The proposed approach formalizes the situation (context) and/or trusted agent identity in a multi-dimensional Identity-Context feature space, and attaches the trustworthiness evaluations to individual elements from this metric space, rather than to fixed identity tags (e.g. AIDs, addresses). Trustworthiness of the individual elements of the I-C space can be evaluated using any trust model that supports weighted aggregations and updates, allowing the integration of the mechanism with most existing work.

A Distributed Stand-in Based Algorithm for Opportunistic Resource Allocation

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Mobile ad-hoc networks (MANET) are expected to form the basis of future mission critical applications such as combat and rescue operations. In this context, communication and computational tasks required by overlying applications will rely on the combined capabilities and resources provided by the underlying network nodes. This paper introduces an integrated FlexFeed/A-globe technology and distributed algorithm for opportunistic resource allocation in resource- and policy-constrained mobile ad-hoc networks. The algorithm is based on agent negotiation for the bidding, contract and reservation of resources, relying primarily on the concept of remote presence. In the proposed algorithm, stand-in Agents technology is used to create a virtual, distributed coordination component for opportunistic resource allocation in mobile ad-hoc networks.

A Mobile Agent-Based Middleware for Opportunistic Resource Allocation and Communications

  • Autoři: Carvalho, M., prof. Dr. Michal Pěchouček, MSc., Suri, N.
  • Publikace: Defence Applications of Multi-Agent Systems: International Workshop, DAMAS 2005, Utrecht, The Netherlands, July 25, 2005, Revised and Invited Papers. Heidelberg: Springer, 2006, pp. 121-134. ISSN 0302-9743. ISBN 3-540-32832-7.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Dependable communication capabilities are amongst the most important technical requirements for mission success in military combat operations. This paper introduces a mobile agent-based middleware that supports both point-to-point messaging and hierarchical data-streaming. Two infrastructure technologies (Mockets and FlexFeed) are introduced as service providers for messaging and publish-subscriber models for data streaming. Opportunistic resource allocation and monitoring are handled by distributed coordination algorithms, implemented here through two complementary technologies: Stand-In Agents and Acquaintance models.

Agents in Industry: The Best from the AAMAS 2005 Industry Track

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Thompson, S.G., Baxter, J.W., Horn, G.S., Kok, K., Warmer, C., Kamphuis, R., Mařík, V., Vrba, P., Hall, K.H., Maturana, F.P., Dorer, K., Calisti, M.
  • Publikace: IEEE Intelligent Systems. 2006, 21(2), 86-95. ISSN 1541-1672.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Multiagent systems and agent technologies provide industrial developers with a novel implementation paradigm and a wide range of ready-to-use technologies, development platforms, and techniques and algorithms. The Industry Track of the Fourth International Conference on Autonomous Agents and Multiagent Systems covered a wide range of industrial applications of agent technologies. The articles in this department intend to give some indication of agent technology's readiness for commercial deployment, based primarily on the presentations and discussions at the Industry Track, and briefly describe agent deployment in unmanned'aerial'vehicle control, logistics, manufacturing, and electricity distribution.

Autonomous Agents for Air Traffic Deconfliction

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This contribution presents a deployment exercise of multi-agent technology in the domain of deconflicted air-traffic control among several autonomous aerial vehicles. Negotiation based deconfliction algorithm have been developed and integrated in the agent-based model of the individual flight. Operation of the underlying multi-agent system has been integrated with freely available, geographical and tactical data sources in order to demonstrate openness of the technology. An additional, web client visualization and access component has been developed in order to facilitate a multi-user, platform independent use of the system.

Crossing the agent technology chasm: Lessons, experiences and challenges in commercial applications of agents

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Belecheanu, R.A., Munroe, S., Miller, T., Mc Burney, P., Luck, M.
  • Publikace: The Knowledge Engineering Review. 2006, 21(4), 345-392. ISSN 0269-8889.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Agent software technologies are currently still in an early stage of market development, where, arguably, the majority of users adopting the technology are visionaries who have recognized the long term potential of agent systems. Some current adopters also see short term net commercial benefits from the technology, and more potential users will need to perceive such benefits if agent technologies are to become widely used. One way to assist potential adopters to assess the costs and benefits of agent technologies is through the sharing of actual deployment histories of these technologies. Working in collaboration with several companies and organizations in Europe and North America, we have studied deployed applications of agent technologies, and we present these case studies in detail in this paper.

Deployment of A globe Multi Agent Platform

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    A-globe is a freeware, simulation-oriented multi-agent platform featuring agent migration, communication inaccessibility simulation and high scalability with moderate hardware requirements. The paper presents several deployment of A-globe platform.

Distributed Planning Algorithm for Coalition Logistics in Semi trusted Environment

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Volf, P.
  • Publikace: 2006 International IEEE Workshop on Distributed Intelligent Systems (DIS 2006). Piscataway: IEEE, 2006. p. 265-272. ISBN 0-7695-2589-X.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a collective approach to coalition logistics planning that presents the features crucial for application in an adversarial environment: planning and communication efficiency, well-defined levels of information to be shared, tight integration of trustfulness with the planning and stability with respect to unprecise trustfulness values. To achieve this goal, we combine multi-agent negotiation with efficient fuzzy and flexible linear programming techniques from operation research field. Alternating rounds of global optimization and restricted negotiation split the task into subtasks, create teams, assign them to the tasks and provide a task-resource mapping. Resulting plan execution can be easily verified and verification results can be used to update the trust and social models and potentially to perform re-planning immediately.

Iterative Query Based Approach to Efficient Task Decomposition and Resource Allocation

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Lerch, O., Bíba, J.
  • Publikace: Cooperative Information Agent X. Heidelberg: Springer, 2006, pp. 259-271. ISSN 0302-9743. ISBN 3-540-38569-X.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Iterative Query Based Approach to Efficient Task Decomposition and Resource Allocation

Market Inspired Approach to Collaborative Learning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper describes a decentralized peer-to-peer multi-agent learning method based on inductive logic programming and knowledge trading. The method uses first-order logic for model representation. This enables flexible sharing of learned knowledge at different levels of abstraction as well as seamless integration of models created by other agents. A market-inspired mechanism involving knowledge trading is used for inter-agent coordination. This allows for decentralized coordination of learning activity without the need for a central control element. In addition, agents can participate in collaborative learning while pursuing their individual goals and maintaining full control over the disclosure of their private information. Several different types of agents differing in the level and form of knowledge exchange are considered. The mechanism is evaluated using a set of performance criteria on several scenarios in a realistic logistic domain extended with adversary behavior.

Multidimensional Context Representations for Situational Trust

  • Autoři: Rehák, M., Gregor, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: 2006 International IEEE Workshop on Distributed Intelligent Systems (DIS 2006). Piscataway: IEEE, 2006, pp. 315-320. ISBN 0-7695-2589-X.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We propose a generic model for situation representation in agent trust models. As we argue that general trust models are inappropriate in complex environments and their use for advanced decision-making is limited due to the lack of detail, we introduce a generic framework for context representation in trust model. Presented method is independent of the trustfulness representation formalism in the underlying trust model. It doesn't prescribe any particular form for the set of reference contexts that holds the trustworthiness information in the context space: we define and evaluate the baseline approach with regular grid and discuss future extension towards more adaptive approaches using octant trees and fuzzy clustering techniques.

Multilevel Approach to Agent Based Task Allocation in Transportation

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Volf, P.
  • Publikace: Cooperative Information Agent X. Heidelberg: Springer, 2006. p. 273-287. ISSN 0302-9743. ISBN 3-540-38569-X.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Multilevel Approach to Agent Based Task Allocation in Transportation

Negotiation Based Approach to Unmanned Aerial Vehicles

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a framework for agent based aircraft deconfliction mechanism to enable efficient airspace use by various UAVs during coalition operations. In our approach, each vehicle is autonomous, but cooperative: it actively shares its flight plan with near aircrafts so that potential collisions can be detected and resolved using norm-based system. Non-cooperative and utility-based deconfliction approaches are also discussed as they offer a possibility to achieve more efficient and robust mechanism in the future. System is validated on multi-agent simulation that uses the public online-accessible data from various information sources.

Reflective-Cognitive Architecture: From Abstract Concept to Self-Adapting Agent

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Multi-agent systems penetrate into interesting domains of computing with limited resources, programme code reusability and automated code generation. This paper presents general framework of Reflective-Cognitive agent architecture which enables the agent to alter its own code in runtime according to the changes in the environment. We also present results of architecture implementation showing the plausibility of created prototype.

Representing Context for Multiagent Trust Modeling

  • Autoři: Rehák, M., Gregor, M., prof. Dr. Michal Pěchouček, MSc., Bradshaw, J.M.
  • Publikace: IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT 2006 Main Conference Proceedings) (IAT'06). USA: IEEE Computer Society, 2006. p. 737-746.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a universal mechanism that can be combined with existing trust models to extend their capabilities towards efficient modelling of the situational (context-dependent) trust. The mechanism describes the similarity between the situations using their distance in a metric space and defines a set of reference contexts in this space to which it associates the trustfulness data. The data associated with each reference context is updated and queried with the weight that decreases with distance between the current situation and the reference context. In the presented mechanism, we use Leader-Follower clustering to place the reference contexts to be representative of the data. In an empirical test, we show that context-aware models easily outperform the general trust when the situation has an impact on partner trustfulness and that their performance and efficiency is comparable with general trust models when the trustfulness is independent of the situation.

Role of acquaintance models in agent's private and semi-private knowledge disclosure

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The organizational architecture of the multi-agent systems and the structure of social knowledge that the members of the community administer are critical factors for assuring such patterns of information exchange that keep agents private knowledge confidential. In this paper we will introduce the concept of agents' private and semi-private knowledge and we will explain the difference between the alliance - a semi-permanent organizational structure and a coalition - a goal-oriented, non-permanent organizational structure. We will provide the reader with an analysis on how does the agents' social knowledge, stored in the tri-base acquaintance model, contributes to permanent confidentiality of agents' private knowledge, preferences, decision making models, resources, etc.

Towards Formal Model of Adversarial Action in Multi Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Tožička, J., Rehák, M.
  • Publikace: Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems. New York: ACM, 2006, ISBN 1-59593-303-4.
  • Rok: 2006
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Detecting and preventing the adversarial action of an agent with respect to the community of agents can be a serious issue in the design of open multi-agent systems. This task is severely domain dependent and it is hard to find a general solution. This contribution presents a utility based model of adversarial action and analyses few properties of adversarial behavior in multi-agent systems.Potential use and important drawbacks of this model are discussed in the paper.

A-globe: Agent Development Platform with Inaccessibility and Mobility Support

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    At present several Java-based multi-agent platforms from different developers are available, but none of them fully supports agent mobility and communication inaccessibility simulation. They are thus unsuitable for experiments with large scale real-world simulation. In this chapter we describe architecture of A-globe, fast, scalable and lightweight agent development platform with environmental simulation and mobility support. Beside the functions common to most agent platforms it provides a position-based messaging service, so it can be used for experiments with extensive environment simulation and communication inaccessibility. Simple benchmarks that compare the A-globe performance against other available agent platforms are also included.

A-globe: Multi-agent Platform with Advanced Simulation and Visualization Support

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    A-Globe is a simulation oriented multi-agent platform featuring agent migration, communication inaccessibility simulation and high scalability with moderate hardware requirements. Using dedicated simulation messaging together with 2D and 3D visualization support, large agent systems can be engineered, tested and visualized on a single machine. A-globe agents are fully fledged JAVA agents, each with its own independent thread, that can autonomously migrate between platforms running on different hosts. Thanks to the separation of simulation and agent code, deployment of agents to embedded devices is straightforward. Platform is not natively FIPA-compliant, as the interoperability was sacrificed to support the scalability and efficiency.

Adversarial Behavior in Multi-Agent Systems

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Tožička, J.
  • Publikace: Multi-Agent Systems and Applications IV. Berlin: Springer, 2005, pp. 470-479. ISSN 0302-9743. ISBN 3-540-29046-X.
  • Rok: 2005
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Adversariality of the agents with respect to the multi-agent system can be a serious issue in the design of open multi-agent systems. Until now, many incoherent definitions of such behavior were used, preventing the consolidation of the knowledge about the domain. By basing ourselves on the valid and accepted results from economics, law and conflict theory, we propose a consistent definition of adversariality in the multi-agent systems and discuss the characteristics of the behavior that falls into this definition.

An Abstract Architecture for Computational Reflection in Multi-Agent Systems

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We propose a general framework for computational reflection in multi-agent systems and address some technical issues related to its implementation. Potentials of computational models of cognition and reflection in a multi-agent system are detailed, and using such models, an abstract architecture of a reflective agent is designed. We also propose important characteristics of reflective multi-agent systems build upon the presented architecture.

Expectations and Deployment of Agent Technology in Manufacturing and Defence: Case Studies

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Rehák, M., Mařík, V.
  • Publikace: The Fourth International Joint Conference on Autonomous Agents and Multi Agent Systems - Special Track for Industrial Applications. New York: ACM, 2005, pp. 100-106. ISBN 1-59593-093-0.
  • Rok: 2005
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Agent technology provides the manufacturing and defence with novel technological concept. This concept has been deployed in a number of different application throughout last few years. This contribution provides the readers with several case studies of agent deployment both in manufacturing and defence. Based on our experience the generalization of agents' applicability in these industry sectors is provided. We also discuss matching of the industry demands and expectations with agent technology promisees and real performance.

ExPlanTech and ExtraPlant: multi-agent technology for production planning, simulation and extra-enterprise collaboration

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents a unified multi-agent technology for decision-making support in production planning and scheduling, manufacturing simulation and collaboration among enterprises. We distinguish intra-enterprise and extra-enterprise levels of production planning problem. Two technologies covering both levels have been developed, ExPlanTech for intra-enterprise level and ExtraPlanT for extra-enterprise level. Developed technology implementing prototypes can be used separately, be connected to other systems or together to maximize utility. The technology has been tested on industrial cases.

ExPlanTech: Multiagent Support for Manufacturing Decision Making

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This article presents and discusses the potential of agent technologies in the manufacturing domain. It reports on the authors' experiences in deploying an open, Foundation for Intelligent Physical Agents-compliant agent-based solution in several industrial applications-namely, planning, simulation, and supply chain management. It primarily discuses and presents multiagent technologies' integration aspects. Besides the state-of-the-art review, the article provides a basic introduction to agent-based systems and lists requirements an application needs to be well suited to an agent-based solution. The articles' key contribution is its presentation of the ExPlanTech multiagent framework and technological architecture. The authors demonstrate the framework's general applicability through several use cases and in pivotal applications.

Fuzzy Number Approach to Trust in Coalition Environment

  • Autoři: Rehák, M., prof. Dr. Michal Pěchouček, MSc., Ing. Petr Benda, Foltýn, L.
  • Publikace: The Fourth International Joint Conference on Autonomous Agents and Multi Agent Systems. New York: ACM, 2005, pp. 1247-1248. ISBN 1-59593-094-9.
  • Rok: 2005
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    General trust management model that we present is adapted for ad-hoc coalition environment, rather than for classic client-supplier relationship. The trust representation used in the model extends the current work by using the fuzzy number approach, readily representing the trust uncertainty without sacrificing the simplicity. The model contains the trust representation part, decision-making part and a learning part. In our representation, we define the trusted agents as a type-2 fuzzy set. In a decision-making part, we use the methods from the fuzzy rule computation and fuzzy control to take trusting decision. For trust learning, we use a strictly iterative approach. We verify our model in a multi-agent simulation where the agents in the community learn to identify and refuse the defectors. Our simulation contains the environment-caused involuntary failure used as a background noise that makes the trust-learning difficult.

Meta-reasoning Methods for Agent`s Intention Modelling

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Tožička, J., Mařík, V.
  • Publikace: Autonomous Intelligent Systems: Agents and data Mining. Berlin: Springer, 2005, pp. 134-148. ISSN 0302-9743. ISBN 3-540-26164-8.
  • Rok: 2005
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Intention modelling in self-interested and adversarial communities of agents is a challenging issue. This contribution discusses the role of modelling and meta-reasoning in intention modelling. The formal model of deductive and inductive meta-reasoning is presented and supported by experimental implementations. This research has been motivated by the problem of intention detection in semi-collaborative multi-agent system for OOTW (Operation Other Than War).

Modelling of Agents' Behavior with Semi-Collaborative Meta-Agents

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    An autonomous agent may largely benefit from its ability to reconstruct another agent's reasoning principles from records of past events and general knowledge about the world. In our approach, the meta-agent maintains a first-order logic theory, called the community model, yielding predictions about other agents' decisions. In this contribution we introduce a query-based collective reasoning process where the semi-collaborative meta-agents use active learning technique to improve their models. We provide empirical results that demonstrate the viability of the concept and show the benefits of collective meta-reasoning.

Optimizing Agents Operation in Partially Inaccessible and Disruptive Environment

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The algorithm we present in this paper aims to optimally distribute and connect the community of loosely coupled middle agents ensuring communication accessibility in a dynamic, inaccessible environment. Complete decentralization, autonomous adaptation to local and global changes in the environment and domain independence are main features of the presented algorithm. The main motivation of this approach is to significantly decrease the number of messages required for communication relaying in inaccessible system operation. We use social dominance models and virtual payments to obtain such behavior.

Solving Inaccessibility in Multi-Agent Systems By Mobile Middle-Agents

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper analyzes the problem of communication inaccessibility in the multi-agent systems. Apart from listing the main reasons for existence of communication inaccessibility, it suggest a complete inaccessibility model and metrics. Various inaccessibility solutions are presented, together with their applicability in the environments with different degrees of inaccessibility, as verified by experiments. Major contribution of this paper is in suggesting a novel solution to solving inaccessibility based on community of autonomous, migrating middle-agents. A distributed algorithm for dynamic allocation of the middle-agents in a network of partially inaccessible agents is proposed. The suggested solution is supported by a set of experiments comparing the distributed and centralized algorithm for middle-agents allocation.

System Innovation Award at CIA2004, Erfurt

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The A-Globe platform is primarily aimed at large scale, real world simulations with fully fledged agents. To support this goal, it includes a special infrastructure for envirnmental simulation.

Trust Model for Open Ubiquitous Agent Systems

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Trust management model that we present is adapted for ubiquitous devices cooperation, rather than for classic client-supplier relationship. We use fuzzy numbers to represent trust, to capture both the trust value and its uncertainty. The model contains the trust representation part, decision-making part and a learning part. In our representation, we define the trusted agents as a type-2 fuzzy set. In a decision-making part, we use the methods from the fuzzy rule computation and fuzzy control domain to take trusting decision. For trust learning, we use a strictly iterative approach, well adapted to constrained environments. We verify our model in a multi-agent simulation where the agents in the community learn to identify defecting members and progressively refuse to cooperate with them. Our simulation contains significant background noise to validate model robustness.

Using Stand-In Agents in Partially Accessible Multi-Agent Environment

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This contribution defines a metrics and proposes a solution for the problem of agents inaccessibility in multi-agent systems. We define the stand-in pattern for knowledge maintenance and remote presence in distributed agent systems with communication inaccessibility. Our implementation has been designed and tested in the A-globe agent platform. We also present a set of measurements quantifying agents' inaccessibility in our domain and comparing the usefulness of different solution in the environments with different inaccessibility

A-Globe: Agent Platform with Inaccessibility and Mobility Support

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In this paper we describe architecture of newly developed agent platform A-Globe. It is fast and lightweight platform with agent mobility support. Beside the functions common to most of agent platforms it provides the Geographical Information System service to user, so it can be used for experiments with environment simulation and communication inaccessibility. A-Globe performance benchmarks compared against other agent platforms are also stated in this paper.

Agent System Application in High-Volume Production Management

  • Autoři: Rehák, M., Charvát, P., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Emerging Solutions for Future Manufacturing Systems. New York: Springer, 2004, pp. 193-200. ISBN 0-387-22828-4.
  • Rok: 2004
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Based on actual industrial project on which the Gerstner laboratory has collaborated, we present a multiple-level scheduling approach as a mean to efficiently apply agent-based planning systems in high-volume production environment. Brief description of efficient and reconfigurable high-level scheduler based on linear programming, as well as design elements of low-level agent-based planning are included

Agent Technology

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Collaborative Networked Organizations / A research agenda for emerging business models. Norwell, MA: Kluwer Academic Publishers, 2004. p. 193-214. ISBN 1-4020-7823-4.
  • Rok: 2004
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    A brief overview of current stat-of-the-art of the agent technology is provided. Principle concepts and architectures of agent-based solutions are presented. Basic information on available platforms, standards and ontology structures is summarized. Appropriate techniques that can be immediately used in the area of virtual enterprises are stressed. FIPA standardization efforts are highlighted.

AgentLink Report: Industry Action

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    While there is still intensive basic research being carried out in the field of multi-agent systems, agent technology has reached a degree of maturity such that it can substantially improve industrial applications. The application of agent technology in business and commerce is one of the main targets of AgentLink III.

Alarm Root Cause Detection System

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Production process control becomes complicated as the complexity of the controlled process grows. To simplify the operator's role many computer based control systems with integrated visualization clients have been developed. In many practical circumstances malfunction of one or more process components results in other related components entering the alarm states. Several alarms appear on the operator's display in a short time making it difficult for the operator to diagnose the root cause quickly. Within this paper we describe a solution of this problem based on a multi-agent system that processes all incoming alarms, identifies the root cause alarms vs. alarms arising in consequence of the roots and presents the diagnostic results to the operator visually.

Decision support framework ExtraPlanT with remote access and telephony interface

  • Autoři: Becvar, P., prof. Dr. Michal Pěchouček, MSc., Šmídl, L.
  • Publikace: 2004 2ND IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS - COLLABORATIVE AUTOMATION - ONE KEY FOR INTELLIGENT INDUSTRIAL ENVIRONMENTS. Piscataway: IEEE Industrial Electronics Society, 2004. p. 95-100.
  • Rok: 2004
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    ExtraPlanT system is a multi-agent production planning system designed for small factories, which needs to react quickly on market changes. To deal with this requirement, ExtraPlanT system has been equipped with an extra-enterprise access feature that allows managers to access and use the system whenever and wherever they need. One possibility of the extra-enterprise access is the telephony interface using computer based speech recognition and synthesis.

ExPLanTech: Multi-Agent Framework for Production Planning, Simulation and Supply Chain Management

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We present a unified multi-agent technology for decision making support in production planning and scheduling, manufacturing simulation in and supply chain management. The technology has been tested on several industrial cases and is used in a daily production processes of one important automobile industry supplier in the Czech Republic.

Making a Perfect`Gin and Tonic`: Mass-Customisation Using Holons

  • Autoři: Fletcher, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Emerging Solutions for Future Manufacturing Systems. New York: Springer, 2004, pp. 23-32. ISBN 0-387-22828-4.
  • Rok: 2004
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents a model of mass-customisation in manufacturing based on designing and deploying intelligent software agents. We illustrate how this mass-customisation would work in a novel scenario - making a perfect `Gin and Tonic`. We also discuss some of the benefits this balanced approach can offer businesses in terms of pragmatic holonic software engineering within complex environments and a formal of holon operations to academia.

Multi-agentní řízení, simulace a plánování výroby

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Popis systému pro multi-agentní řízení, simulace a plánvání výroby

Návrh telefonního rozhraní multiagentního systému pro plánování výroby ExtraPlanT

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Systém ExtraPlanT je multiagentní systém pro plánování výroby v prostředí s omezenými zdroji. Systém je určen pro malé a střední podniky, kterým umožňuje udržet přehled o existujících zakázkách, jejich nárocích na zdroje a o volných kapacitách. Aby systém odpovídal požadavkům moderního řízení podniku, byl vybaven několika možnostmi vzdáleného přístupu. Jednou z těchto možností je telefonní hlasové rozhraní založené na technologii VoiceXML, využívající počítačové syntézy a rozpoznávání řeči. Tento článek se věnuje jednak celkovému popisu systému a jednak prostředkům použitým k překonání obecných nevýhod hlasových rozhraní - sekvenčnosti a průběžnosti předávání informací. Prvním z prostředků je dvojúrovňový model komunikace, který v určitých situacích provádí předzpracování dat a uživateli předává jen důležité závěry. Druhým prostředkem je zkrácení a zjednodušení dialogu dynamickým výběrem rozsahu a znění promluv systému.

Reasoning about Agent's Private Knowledge

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    An important property of an autonomous agent is its ability to reason about other agents' private knowledge. Knowledge about the community and private knowledge of its members can be obtained by monitoring events appearing in the community. We propose three approaches how an agent can use the observed events to build such a model: one is based on theorem proving, the other on machine learning techniques, namely ILP and version space. The proposed framework allows to choose the type of model revision/update on eager-lazy strategy scale. These techniques were implemented and compared in two case studies concerning coalition formation.

Simulating Agents´ Mobility and Inaccessibility with A-Globe Multi-agent System

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Simulating Agents´ Mobility and Inaccessibility with A-Globe Multi-agent System

Social Knowledge in Multi-Agent Systems

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Conference Proceedings 2004 IEEE International Conference on Systems, Man & Cybernetics. Piscataway: IEEE, 2004, pp. 1950-1957. ISSN 1062-922X. ISBN 0-7803-8566-7.
  • Rok: 2004
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents the concept of social knowledge in multi-agent systems. Basic classification of the various types of social knowledge is provided and di_erent mechanisms for social knowledge maintenance are presented. An inseparable part of this contribution is an analysis of the di_erent classes of industrial applications with respect to di_erent role of social knowledge in either of these.

Software agents for process monitoring and notification

  • Autoři: Bunch, L., Breedy, M., Bradshaw, J.M., Carvalho, M., Suri, N., Uszok, A., Hansen, J., prof. Dr. Michal Pěchouček, MSc., Mařík, V.
  • Publikace: Proceedings of the 2004 ACM Symposium on Applied Computing (SAC). New York: ACM, 2004, pp. 94-100. ISBN 1-58113-812-1.
  • Rok: 2004
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Safety and efficiency are primary concerns in chemical processing facilities, though the complexity of many such systems often makes it difficult for operators to detect abnormal conditions before they compromise throughput or become hazardous. In this paper, we report initial results from the application of multi-agent systems to monitor complex chemical processes and flexibly and appropriately notify key plant personnel about off-nominal conditions.

Solutions for Cooperation with Limited Communication

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    We define a set of metrics for communication inaccessibility measurements, together with a comparison of existing solutions for inaccessibility in a MAS. We compare the solutions such as relaying, middle agents, stand-in agents and analyze the performance of these solutions for various values of inaccessibility properties. The measurements are obtained on a test domain implemented using the A-Globe agent platform with inaccessibility support.

Solving Communication Inaccessibility in Coalition Operations

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Inability to communicate the exact information in the right time has become one of the key bottlenecks in real-time control of military operations as well as in planning large scale coalition operations. In this paper we study situations in which communication and coordination inaccessibility can occur and discuss three different solutions of various level of sophistication -- relay agents, acquaintance models and stand-in agents. These methods were deployed in the aglobe multi-agent system. Deployment in two different scenarios is discussed here.

Abstract Architecture for Meta-reasoning in Multi-agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Štěpánková, O., Mařík, V., Bárta, J.
  • Publikace: Multi-Agent Systems and Applications III. Berlin: Springer, 2003. p. 85-99. ISSN 0302-9743. ISBN 3-540-40450-3.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Agent's meta-reasoning is a computational process that implements agent's capability to reason on a higher level about another agents or a community of agents. There is a potential for meta-reasoning in multi-agent systems. Meta-reasoning can be used for reconstructing agents' private knowledge, their mental states and for prediction of their future courses of action. Mega-agents should have the capability to reason about incomplete or imprecise information. Unlike the ordinary agents, the meta-agent may contemplate about the community of agents as a whole and is expected to contribute to agent's operation efficiency improvement. This contribution suggests a theoretical specification of an abstract reasoning and knowledge representation architecture for the meta-reasoning agents and discusses/categorizes the related computational processes.

Agent Based Production Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    There are many advantages why the agent-based approach to planning shall be adopted. Agent based planning offers very often high degree of reconfigurability and flexibility as the same planning algorithms for particular agents can be used in many different settings of the agent community. Agent-based planning also offers tractability and capability to explain how the decision has been made (on the singleagent level). It is very convenient to use this approach in domains with natural distribution of physical elements (e.g. logistics, flight control, . . . ) Using advanced techniques of distributed artificial intelligence planning efficiency can be substantially improved.

Agent Exchange - Virtual Trading Environment

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Agent Exchange is a virtual trading environment serving as a test bed for experiments with market simulations, trading strategies and auctioning techniques. Agent Exchange is the distributed environment implementing up-to-date knowledge from multi-agent systems and secure communication.

Agent Technology for Virtual Organizations

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Processes and Foudations for Virtual Organizations. Boston: Kluwer Academic Publishers, 2003, pp. 243-252. ISBN 1-4020-7638-X.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper summarizes the latest achievements in the area of intelligent agent-based solutions for manufacturing. The main idea of this paper is that many solutions developed in the multi-agent area can be successfully reused for the virtual enterprises purposes. Critical analysis of both the MAS advantages and gaps from the VO point of view is presented.

Decision planning knowledge representation framework: A case-study

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper discusses experiences and perspectives of utilisation of declarative knowledge structures as a convenient knowledge base medium in configuration expert systems. Although many successful systems have been developed, these are often difficult to maintain and to generalize in rapidly changing domains. In this paper we address the problem of building intelligent knowledge based systems with emphasis on their maintainability. Firstly, several industrial applications of proof planning, a theorem proving technique, will be described and their advantages and flaws will be discussed. This discussion is followed by the theoretical foundation of decision planning knowledge representation framework that, based on proof planning, facilitates separate administration of inference problem solving knowledge and the domain theory axioms. Machine learning methods for maintaining the inference knowledge to be up-to-date with permanently changing domain theory are commented and evaluated.

ExPlanTech/ExtraPLANT: Production Planning and Supply-Chain Management Multi-Agent Solution

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    An intelligent support and automation of production planning in both small and medium enterprises as much as big manufacturers is a key for achieving fast due-dates, high degree of manufacturing flexibility, minimization of stock resources, balanced load of the manufacturing machinery, etc. in this contribution we present a jade-based multi-agent solution for intra-enterprise production planning and for extra-enterprise activities such as supply chain management.

FIPA Standards and Holonic Manufacturing

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Vrba, P., Hrdonka, V.
  • Publikace: Agent-Based Manufacturing. Berlin: Springer, 2003. p. 89-119. ISBN 3-540-44069-0.
  • Rok: 2003

Foundations of Agent Based Systems: Brief Introduction to Alliance and Coalition Formation

  • Autoři: prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Intelligent and Adaptive Systems in Medicine. Praha: ČVUT v Praze, FEL, 2003, pp. 132-147. ISSN 1213-3000.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The multi-agent systems consist of a set of non-centralised, mutually co-operating elements { agents which act autonomously. They exchange information and knowledge in order to achieve desired instance of collaboration. Multi-agent decision making is not only processing information from various sources of diverse nature. Multi-agent systems allow its agents to act proactively: any agent is able to try to persuade the rest of the community members to adopt the agent's local goal as their joint motivation and implement it. Either hierarchical, heterarchical or partially structured communities of agents perform joint decision making by means of communication, collaboration, negotiation, and responsibility delegation that are based on agents' individual rationality and social intelligence

Inaccessibility in Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Dobíšek, M., Lažanský, J., Mařík, V.
  • Publikace: Intelligent Agent Technology. Los Alamitos: IEEE Computer Society Press, 2003. pp. 182-188. ISBN 0-7695-1931-8.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In standard situations, agents in a multi-agent community need to communicate each other to accomplish cooperation and coordination of joint activities. Normally it is expected that each agent can contact any other using a reliable communication infrastructure. Often one has to think about situations when a communication subsystem becomes disintegrated and some agents become isolated from the rest of the community. The paper provides basic analysis of such inaccessibility situations, and reviews possible technologies to remedy the resulting difficulties. The concepts of a so-called doubler agent and stand-in agent for maintaining agents accessibility is introduced. A brief discussion on suitability of the acquaintance models for maintaining accessibility on a symbolic level is also touched.

Industrial Applications of Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Znalosti 2003 - sborník příspěvků 2. ročníku konference. Ostrava: VŠB-TUO, 2003, pp. 2-5. ISBN 80-248-0229-5.
  • Rok: 2003

MAS for Production Planning: CTU Experience

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper reviews the main reasons leading to utilization of distributed systems for project-oriented production planning and it introduces a family of multi-agent systems/technologies developed in the Gerstner Laboratory to achieve this goal. The entire solution consists of three generations of MAS systems: ProPlanT, ExPlanTech and ExtraPlanT. ProPlanT is presented as a general agent based planning system shell which became a basis for a MAS system to be used for production planning in Modelarna Liaz, sro. The system running in LIAZ is described in some more details.

Meta-Reasoning for Agents' Private Knowledge Detection

  • Autoři: Tožička, J., Bárta, J., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Cooperative Information Agents VII. Berlin: Springer, 2003, pp. 316-323. ISSN 0302-9743. ISBN 3-540-40798-7.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Agent's meta-reasoning is a computational process that implements agent's capability to reason on a higher level about another agent or a community of agents. There is a potential for meta-reasoning in multi-agent systems. Meta-reasoning can be used for reconstructing agents' private knowledge, their mental states and for prediction of their future courses of action. Meta-agents should have the capability to reason about incomplete or imprecise information. Unlike the ordinary agents, the meta-agent may contemplate about the community of agents as a whole. This contribution presents application of the meta-reasoning process for the agent's private knowledge detection within the multi-agent system for planning of humanitarian relief operations.

Od holonů k virtuálním organizacím

  • Autoři: Mařík, V., Vrba, P., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Umělá inteligence (4). Praha: Academia, 2003. p. 407-450. ISBN 80-200-1044-0.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Zabývá se aplikací myšlenek multiagentních systémů a oblasti průmyslové výroby, a to na všech úrovních. Jsou zde popisovány holony jako agenti přímo fyzicky spojení s výrobním zařízením, operujícím v reálném čase. Speciální plánovací a rozhodovací agenti zabezpečují optimální využívání výrobních kapacit na úrovni dílny a podniku. Rozšíření multiagentních myšlenek směrem k mezipodnikové kooperaci vede k vizi virtuálních sítí dílen a podniků, vzájemně provázaných elektronickou komunikací. Hlavním problémem zavádění multiagentních řešení s e jeví vzájemná interoperabilita, jejíž řešení je podporováno nově vznikajícími strandardy FIPA, opírajícími se o zkušenosti z oblasti distribuované umělé inteligence. Podstatnou částí kapitoly jsou dvě případové studie, realizované za spoluúčasti autorů.

Role of Subscription-based Contraction in Agent-based Production Planning

  • Autoři: prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of the First European Workshop on Multi-Agent Systems. Southampton: University of Southampton, 2003, pp. 57-70.
  • Rok: 2003
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This contribution is supposed to provide a set of arguments justifying the role of agent-based computing in the area of real-life planning and scheduling. This is a discussion position paper that contains description of the key ideas. It does feature neither formal proofs of the the suggested algorithms nor experimental results. The paper introduces the novel contraction mechanism and discusses its properties.

A Knowledge-Based Approach to Coalition Formation

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The task of planning humanitarian relief operations within a high number of hardly collaborating and vaguely linked non-governmental organizations is a challenging problem. We suggest an alternative knowledge based approach to the coalition formation problem for humanitarian and peace-keeping missions. We combined classical negotiation mechanisms with the acquaintance models and social knowledge techniques in order to reduce the communication traffic and to keep the privacy of knowledge. Experimental results are discussed in the paper.

Application of Agent Technologies in Extended Enterprise Production Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    By reusing and extending the classical multi-agent production planning infrastructure the extra-enterprise technology helps to organise external business relations of an enterprise and optimize their supply chains. It is obvious that small and medium enterprises that operate in project-driven manufacturing need to share their available resources in the most optimal way. Apart from technological infrastructure that need to interoperable across the extended enterprise, this paper emphasis the role of a shared ontologies and semantic meaning of the inter-agent communication.

CPlanT:Coalition Planning Multi-Agent System for Humanitarian Relief Operations

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Bárta, J., Mařík, V.
  • Publikace: Multi-Agent Systems and Applications II. Berlin: Springer, 2002, pp. 363-375. ISBN 3-540-43377-5.
  • Rok: 2002

Distributed Branch and Bound Algorithm in Coalition Planning

  • Autoři: Bárta, J., Štěpánková, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Multi-Agent Systems and Applications II. Berlin: Springer, 2002, pp. 159-168. ISBN 3-540-43377-5.
  • Rok: 2002
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    with exponential complexity e.g. coalition planning is presented. Thisch

ExPlanTech: applying multi-agent systems in production planning

  • DOI: 10.1080/00207540210140086
  • Odkaz: https://doi.org/10.1080/00207540210140086
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This paper presents work carried out within the 'ExPlanTech' project (IST-1999-20171) funded in part by the European Commission's Information Technologies Programme. The mission of the ExPlanTech technology transfer project is to introduce, customize and exploit the multi-agent production planning technology (ProPlanT multi-agent system research prototype) in two specific industrial enterprises. An agent driven service negotiations and decision process based on usage-centred knowledge about task requirements substitutes the traditional production planning activity. We introduce methodology for integration of the project-driven production planning based on agent-based engineering within the existing enterprise resource planning system.

ExPlanTech: Exploitation of Agent-Based Technology in Production Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The mission of the ExPlanTech technology transfer project is to introduce, customize and exploit the multi-agent production planning technology in two distinct industrial cases. The traditional production planning activity is substituted by agent driven service negotiations, intelligent decomposition and distributed decision-making. This paper describes a FIPA-compliant implementation of the ExPlanTech technology at the LIAZ Pattern Shop manufacturing company. We describe the structure of the agent community, types of agents, implementation of the planning strategy and its incorporation within the real production environment.

Extra-Enterprise Production Planning in ExPlanTech System

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The work presented in this paper reports on extending the intra-enterprise multi-agent production planning to the extra-enterprise level. By reusing and extending the classical multi-agent production planning infrastructure the extra-enterprise technology helps to organise external business relations of an enterprise and optimize their supply chains. It is obvious that small and medium enterprises that operate in project-driven manufacturing, need to share their available resources in the most optimal way.

From Intra-Enterprise Towards Extra-Enterprise Production Planning

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    In the domain of production planning multi-agent systems there is a strong demand for extending the solution beyond the borders of a single enterprise in order to meet future business requirements: (i) to manage the extra-enterprise production planning effectively, (ii) to create and reconfigure flexible dynamic configuration of virtual enterprises (e.g. among collaborating business partners). The concept of extra-enterprise agents helps to facilitate secure remote access and manage the production planning processes from outside the factory, inspect the current and the future load of particular production units, modify already running customer-projects, or include/invoke a new customer-project into the system remotely

Holons & Agents: Recent Developments and Mutual Impacts

  • Autoři: Mařík, V., Fletcher, M., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Multi-Agent Systems and Applications II. Berlin: Springer, 2002, pp. 233-267. ISBN 3-540-43377-5.
  • Rok: 2002

Knowledge Systems for Coalition Operations

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    Rewiew of the state-of-the-art of the Knowledge Systems for Coalition Operations

Multi-Agent System for Planning in Project-Oriented Production: Case Study

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The mission of the ExPlanTech technology transfer project is to introduce, customize and exploit the multi-agent production planning technology in two distinct industrial cases. The traditional production planning activity is substituted by agent driven service negotiations, intelligent decomposition and distributed decision-making. This paper describes a FIPA-compliant implementation of the ExPlanTech technology at the LIAZ Pattern Shop manufacturing company. We describe the structure of the agent community, types of agents, implementation of the planning strategy and its incorporation within the real production environment.

Organization of social knowledge in multi-agent systems

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Integrated Computer-Aided Engineering. 2002, 1(9), 195-206. ISSN 1069-2509.
  • Rok: 2002

Reduction of Task Complexity in Coalition Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Bárta, J.
  • Publikace: Cybernetics and Systems 2002, volume II. Vienna: Austrian Society for Cybernetics Studies, 2002, pp. 695-700. ISBN 3-85206-160-1.
  • Rok: 2002

Acquaintance Models in Coalition Planning for Humanitarian Relief Operation

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Bárta, J.
  • Publikace: Intelligent Agent Technology. Singapore: World Scientific, 2001, pp. 434-443. ISBN 981-02-4706-0.
  • Rok: 2001

Adoption of an Agent-Based Production Planning Technology in the Manufacturing Industry

  • Autoři: Říha, A., prof. Dr. Michal Pěchouček, MSc., Krautwurmová, H., Charvát, P., Koumpis, A.
  • Publikace: Database and Expert Systems Applications. Los Alamitos: IEEE Computer Society Press, 2001, pp. 640-646. ISBN 0-7695-1230-5.
  • Rok: 2001

Application of the Multi-Agent Approach in Production Planning and Modelling

  • Autoři: Lažanský, J., Štěpánková, O., Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Engineering Applications of Artificial Intelligence. 2001, 14(14), 369-376. ISSN 0952-1976.
  • Rok: 2001

Coalition Planning in Multi-Agent Systems

  • Autoři: Bárta, J., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Proceedings of Workshop 2001. Praha: České vysoké učení technické v Praze, 2001, pp. 250-251. ISBN 80-01-02335-4.
  • Rok: 2001

Communication Safety in Multi-Agent Systems

  • Autoři: Říha, A., prof. Dr. Michal Pěchouček, MSc., Bárta, J.
  • Publikace: Proceedings of Workshop 2001. Praha: České vysoké učení technické v Praze, 2001, pp. 248-249. ISBN 80-01-02335-4.
  • Rok: 2001

Communitaction Safety in Multi-Agent Systems

  • Autoři: Říha, A., prof. Dr. Michal Pěchouček, MSc., Bárta, J.
  • Publikace: Poster 2001. Praha: České vysoké učení technické v Praze, Fakulta elektrotechnická, 2001, pp. 36.
  • Rok: 2001

CPlanT: An Acquaintance Model Based Coalition Formation Multi-Agent System

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Bárta, J.
  • Publikace: From Theory to Practice in Multi-Agent Systems. Berlin: Springer, 2001, pp. 234-241. ISBN 3-540-43370-8.
  • Rok: 2001
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    This article will describe the CPlanT multi-agent system that has been designed in order to suggest and test alternative approaches to coalition formation. The system has been implemented for planning the Operations Other Than War (OOTW) coalition, which is the domain with a strong emphasis put on maintaining privacy of communicated information among collaborating actors - agents and important level of autonomy of their decision making. The paper presents a concept of an acquaintance model as computational models of agents' mutual awareness. In the acquaintance model the agents administer and maintain different types social knowledge that are exploited in the coalition formation process.

CPlantT: An Acquaintance Model Based Coalition Formation Multi-Agent System

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Bárta, J.
  • Publikace: Proceedings of the Second International Workshop of Central and Eastern Europe on Multi-Agent Systems. Krakow: Uniwersytet Jagiellonski, 2001, pp. 209-216. ISBN 83-915953-0-7.
  • Rok: 2001

Distributed Branch and Bound Algorithm in Coalition Planning

  • Autoři: Bárta, J., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Multi-Agent Systems and Applications & Adaptability and Embodiment Using Multi-Agent Systems. Praha: České vysoké učení technické v Praze, 2001, pp. 56-63. ISBN 80-01-02387-7.
  • Rok: 2001

Editorial of "Industrial Applications of Holonic and Multi-Agent Systems"

ExPlanTech: Applying Multi-agent Systems in Production Planning

  • Autoři: Říha, A., prof. Dr. Michal Pěchouček, MSc., Mařík, V., Pražma, V.
  • Publikace: 16th International Conference on Production Research (ICPR-16). Praha: Český svaz vědeckotechnických společností, 2001, pp. 99. ISBN 80-02-01438-3.
  • Rok: 2001

Exploitation of ProPlanT Technology: ExPlanTech

  • Autoři: Říha, A., prof. Dr. Michal Pěchouček, MSc., Charvát, P.
  • Publikace: Multi-Agent Systems and Applications & Adaptability and Embodiment Using Multi-Agent Systems. Praha: České vysoké učení technické v Praze, 2001, pp. 192-199. ISBN 80-01-02387-7.
  • Rok: 2001

Holons @ Agents: Recent Development and Mutual Impacts

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Database and Expert Systems Applications. Los Alamitos: IEEE Computer Society Press, 2001, pp. 605-610. ISBN 0-7695-1230-5.
  • Rok: 2001

Multi-Agent Approach to Coalition Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Bárta, J.
  • Publikace: Advances in Database and Expert Systems - Volume VII. Windsor, Ontario: The International Institute for Advanced Studies in Systems Research and Cybern., 2001. p. 22-28. ISBN 1-894613-14-7.
  • Rok: 2001

Multi-Agent System as a Model of Market

  • Autoři: Hodík, J., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Poster 2001. Praha: České vysoké učení technické v Praze, Fakulta elektrotechnická, 2001, pp. 12.
  • Rok: 2001
  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The paper presents a multi-agent model of market negotiation. The negotiation about price is modeled.

Multiagentní systémy:Principy komunikace a základní formální architektury

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Umělá inteligence (3). Praha: Academia, 2001. p. 189-236. ISBN 80-200-0502-1.
  • Rok: 2001

Organization of Social Knowledge in Multi-agent Systems

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: W9: Holons: Autonomous and Cooperative Agents For Industry. New York: ACM Press, 2001, pp. 39-45.
  • Rok: 2001

Relexivity and Meta-reasoning in Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Norrie, D., Mařík, V.
  • Publikace: W12: Autonomy-Oriented Computation (AOC). New York: ACM Press, 2001, pp. 31-40.
  • Rok: 2001

Replanning in Multi-Agent Systems

  • Pracoviště: Katedra kybernetiky
  • Anotace:
    The article presents the basic replanning approach for multi-agents planning systems.

Social Knowledge in Multi-agent Systems

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Multi-Agent Systems and Applications. Berlin: Springer, 2001, pp. 211-246. ISBN 3-540-42312-5.
  • Rok: 2001

Towards Reducing Communication Traffic in Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Štěpánková, O.
  • Publikace: Journal of Applied Systems Studies. 2001, 2(1), 152-174. ISSN 1466-7738.
  • Rok: 2001

Znalosti a multiagentní systémy

  • Autoři: Mařík, V., Štěpánková, O., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Sborník Znalosti 2001. Praha: Vysoká škola ekonomická, 2001, pp. 19-36. ISBN 80-245-0190-2.
  • Rok: 2001

Acquaintance Model in Re-Planning and Reconfiguration

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Advances in Networked Enterprises. Boston: Kluwer Academic Publishers, 2000, pp. 175-186. ISBN 0-7923-7958-6.
  • Rok: 2000

Administrating Knowledge via Acquaintance Models

Coalition Formation in Manufacturing Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Štěpánková, O.
  • Publikace: Database and Expert Systems Applications. Los Alamitos: IEEE Computer Society Press, 2000, pp. 241-246. ISBN 0-7695-0680-1.
  • Rok: 2000

FIPA Standards and Holonic Manufacturing

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Vrba, P., Hrdonka, V.
  • Publikace: Abnormal Loading on Structures. London: E&FN SPON, 2000. p. 89-119. ISBN 0-419-25960-0.
  • Rok: 2000

HOLOMAS'00: Industrial Applications of Holonic and Multi-Agent Systems

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Database and Expert Systems Applications. Los Alamitos: IEEE Computer Society Press, 2000, pp. 213. ISBN 0-7695-0680-1.
  • Rok: 2000

Multi-Agent Systems and Coalition Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Advances in Artificial Intelligence and Engineering Cybernetics. Windsor: IIAS, 2000. p. 1-7. ISBN 1-894613-00-7.
  • Rok: 2000

Proplant: Applications of the Multi-Agent Paradigm in Production Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O.
  • Publikace: Proceedings of Conference on Intelligent Information Procerssing. Beijing: Publishing House of Electronics Industry, 2000, pp. 598-605. ISBN 7-5053-6109-0.
  • Rok: 2000

ProPlanT: Multi-Agent System for Production Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O., Lažanský, J.
  • Publikace: Applied Artificial Intelligence. 2000, 14(7), 727-760. ISSN 0883-9514.
  • Rok: 2000

ProPlanT: Multi-Agent Systems for Enterprise Modeling

  • Autoři: Pepiot, G., Gardon, R., Pouly, M., prof. Dr. Michal Pěchouček, MSc., Mařík, V.
  • Publikace: Agent-Based Simulation, Planning and Control. New Brunswick: Rutgers University, Dept. of Computer Science, 2000, pp. 1-11. ISBN 3-9522075-1-9.
  • Rok: 2000

Role of Acquaintance Models in Agent-Based Production Planning System

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Štěpánková, O.
  • Publikace: Cooperative Information Agents IV. Berlin: Springer, 2000, pp. 179-190. ISBN 3-540-67703-8.
  • Rok: 2000

Sharing Responsibility in Workflow Management in Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Štěpánková, O., Macůrek, F., Tichý, P.
  • Publikace: Cybernetics and Systems 2000. Vienna: Austrian Society for Cybernetics Studies, 2000, pp. 657-662. ISBN 3-85206-151-2.
  • Rok: 2000

Workflow Dynamics in Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Štěpánková, O., Lažanský, J.
  • Publikace: International ICSC Congress Intelligent Systems & Applications. Wetaskiwin: ICSC Academic Press, 2000, pp. 321-327. ISBN 3-906454-24-X.
  • Rok: 2000

Experience from Development of Multi-Agent Systems

  • Autoři: Mařík, V., Štěpánková, O., Lažanský, J., prof. Dr. Michal Pěchouček, MSc., Hazdra, T.
  • Publikace: Advances in Artificial Intelligence and Engineering Cybernetics. Windsor: IIAS, 1999, pp. 16-21. ISBN 0-821836-61-9.
  • Rok: 1999

Financial Data Challenge

Inductive Logic Programming as a Tool for Knowledge Extraction

Knowledge Acquisition Using ILP

  • Autoři: Štěpánková, O., Mikšovský, P., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings of Student Sessions. Chania: National Center for Scientific Research DEMOKRITOS, 1999, pp. 11-14.
  • Rok: 1999

Maintenance of Discovery Knowledge

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Štěpánková, O., Mikšovský, P.
  • Publikace: Priciples of Data Mining and Knowledge Discovery. Berlin: Springer, 1999, pp. 476-483. ISBN 3-540-66490-4.
  • Rok: 1999

Meta-agent: A Workflow Mediator in Multi-Agent Systems

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Macůrek, F., Tichý, P., Štěpánková, O., Mařík, V.
  • Publikace: Intelligent Workflow and Process Management: The New Frontier for AI in Business. San Francisco: Morgan Kaufmann Publishers, 1999, pp. 110-116.
  • Rok: 1999

Meta-Knowledge Representation for Industrial Decision Making

  • Autoři: prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings: PAKeM '99. London: The Practical Application Company, 1999, pp. 115-133. ISBN 1-902426-02-9.
  • Rok: 1999

ProPlanT: A Multi-Agent System for Operative Planning of Production

  • Autoři: Hazdra, T., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Proceedings: PAAM '99. London: The Practical Application Company, 1999, pp. 315-324. ISBN 1-902426-05-3.
  • Rok: 1999

PVS 98 Agents: Structures, Models and Production Planning Applications

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Lažanský, J., Roche, C.
  • Publikace: Robotics and Autonomous Systems. 1999, 27(1), 29-43. ISSN 0921-8890.
  • Rok: 1999

Re-planning in the Multi-agent System for Production Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Lažanský, J., Koutník, J., Štěpánková, O.
  • Publikace: Robotics and Applications. Calgary: IASTED, 1999, pp. 407-411. ISBN 0-88986-251-6.
  • Rok: 1999

Applications of Acquaintance-model-based Co-operative Agents in Production Planning

  • Autoři: Štěpánková, O., prof. Dr. Michal Pěchouček, MSc., Mařík, V., Lažanský, J.
  • Publikace: Telecooperation. Vienna: OCG - Austrian Computer Society, 1998, pp. 176-190. ISBN 3-85403-121-1.
  • Rok: 1998

Applications of Model-Based Co-operative Agents in Production Planning

  • Autoři: Štěpánková, O., prof. Dr. Michal Pěchouček, MSc., Mařík, V., Lažanský, J.
  • Publikace: Database and Expert Systems Applications. Berlin: Springer, 1998, pp. 620-629. ISBN 3-540-64950-6.
  • Rok: 1998

Applications of the Multi-Agent Approachin Production Planning and Modelling

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Štěpánková, O., Lažanský, J.
  • Publikace: Intelligent Manufacturing Systems IMS 98. Oxford: IFAC, 1998, pp. 131-136.
  • Rok: 1998

Multiagency and Production Planning

  • Autoři: Mařík, V., Štěpánková, O., Lažanský, J., prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: Innovative Produktions-technik. München: Carl Hanser Verlag, 1998. p. 187-198. ISBN 3-446-21062-8.
  • Rok: 1998

Proof Planning for Maintainable Configuration Systems

  • Autoři: Lowe, H., prof. Dr. Michal Pěchouček, MSc., Bundy, A.
  • Publikace: AI EDAM - Artificial Intelligence for Engineering Design, Analysis and Manufacturing. 1998, 12(4), 345-356. ISSN 0890-0604.
  • Rok: 1998

ProPlanT-Multi-Agent System for Productive Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Hazdra, T., Štěpánková, O.
  • Publikace: Cybernetics and Systems 98. Vienna: Austrian Society for Cybernetics Studies, 1998, pp. 725-730. ISBN 3-85206-139-3.
  • Rok: 1998

PVS 98 Agent Models and their Application in Production Planning

  • Autoři: Mařík, V., prof. Dr. Michal Pěchouček, MSc., Roche, C.
  • Publikace: Intelligent Systems for Manufacturing: Multi-Agent Systems and Virtual Organizations. Norwell, MA: Kluwer Academic Publishers, 1998, pp. 13-22. ISBN 0-412-84670-5.
  • Rok: 1998

Tri-Base Acquaintance Model for Project Driven Production Modelling

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Lažanský, J., Mařík, V., Štěpánková, O.
  • Publikace: Changing the Ways We Work. Amsterdam: IOS Press, 1998, pp. 623-631. ISBN 90-5199-426-5.
  • Rok: 1998

Tri-Base Model: An Approach to Project-Oriented Production Modelling

  • Autoři: prof. Dr. Michal Pěchouček, MSc., Mařík, V., Štěpánková, O., Hazdra, T.
  • Publikace: Simulation : Past, Present and Future. Delft: Society for Computer Simulation International, 1998, pp. 622-628. ISBN 1-56555-148-6.
  • Rok: 1998

Proof Planning and Industrial Configuration

  • Autoři: prof. Dr. Michal Pěchouček, MSc.,
  • Publikace: PAP '97 Proceedings. London: The Practical Application Company, 1997, pp. 233-240. ISBN 0-9525554-5-X.
  • Rok: 1997

Proof Plannning and Configuration

  • Autoři: Lowe, H., prof. Dr. Michal Pěchouček, MSc., Bundy, A.
  • Publikace: Proceedings of the Ninth Exhibition and Symposium on Industrial Applications of Prolog. Tokyo: REN Associates, 1996, pp. 221-228.
  • Rok: 1996

Za stránku zodpovídá: Ing. Mgr. Radovan Suk