Ing. Petr Benda

In this paper, a cooperative driver model for a multi-agent traffic simulation is proposed. The model combines maneuver-based trajectory planning of the vehicles with a cooperative conflict resolving. The proposed model is able to provide a safe drive in complex traffic situations at the highest possible speed. The idea of the model and its feasibility have been verified in complex scenarios such as line change under heavy traffic, highway entering or highway crossing. Moreover, the developed cooperative driver model is being integrated with a human operated driving simulator that enables verification of the proposed model in mixed scenarios enriching the simulation for a human driver with highly cooperative background traffic; thus, providing a platform for further studies on benefits of assistive technologies. The paper provides description of the proposed model and its early evaluation on the selected scenarios in a multi-agent traffic simulation.

The goal of the paper is to present an application of TARF (Task Agent Resource Function) in UAV domain. This TARF is used to optimize the tasks allocation in case of cooperation between multiple Unmanned Aerial Vehicles. It plays the role of a generic mission planner for cross domain such as UAV, maritime, automotive and manned aerial vehicle (MAV). This paper concentrates on how to integrate TARF in Paparazzi platform - an UAV platform based on PPRZ autopilot - in order to perform a swarm of aircrafts doing different tasks. The TARF contributes a new module to this platform for the simulation and real demonstrations.

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.

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.

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.

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.

Teams of autonomous robots are becoming a part of the field operations like disaster relief or battlefield. Although the situation drives towards the use of completely autonomous robotic teams, humans still remain inevitable part of those teams. Number of communication protocols for data streaming in mobile ad-hoc networks was developed, but they are usually suitable for communication among autonomous robots rather than for communication with human team members. In this paper a constraint-based data streaming algorithm that provides the reliable communication among autonomous robots and humans is presented. This algorithm is based on the use of social knowledge about other team members and ensures delivery of the on-demand data streams to human team members while allowing the robots to fulfill their tasks at the same time.

Nowadays, a lot of mobile routing protocols are used in mobile ad hoc networks in practice. However, all the protocols fail if a network topology consists of several mutually inaccessible components. In such a case, it is necessary to introduce artificial intelligence to the behavior of mobile routers to solve the problem of inaccessibility.

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.

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.

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.

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.

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.

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.

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.

The paper is about distributed graph searhching in RoboCup Rescue domain. Next, it presents algorithms and shows that there no communication between agents is needed for the negotiation of regions.