Lidé
Mgr. Martin Pecka, Ph.D.
Všechny publikace
UAVs Beneath the Surface: Cooperative Autonomy for Subterranean Search and Rescue in DARPA SubT
- Autoři: Ing. Matěj Petrlík, Ing. Pavel Petráček, Ph.D., Ing. Vít Krátký, Ph.D., Ing. Tomáš Musil, Stasinchuk, Y., Ing. Matouš Vrba, Ing. Tomáš Báča, Ph.D., Ing. Daniel Heřt, Mgr. Martin Pecka, Ph.D., prof. Ing. Tomáš Svoboda, Ph.D., doc. Ing. Martin Saska, Dr. rer. nat.,
- Publikace: Field Robotics. 2023, 3 1-68. ISSN 2771-3989.
- Rok: 2023
- DOI: 10.55417/fr.2023001
- Odkaz: https://doi.org/10.55417/fr.2023001
- Pracoviště: Vidění pro roboty a autonomní systémy, Multirobotické systémy
-
Anotace:
This paper presents a novel approach for autonomous cooperating UAVs in search and rescue operations in subterranean domains with complex topology. The proposed system was ranked second in the Virtual Track of the DARPA SubT Finals as part of the team CTU-CRAS-NORLAB. In contrast to the winning solution that was developed specifically for the Virtual Track, the proposed solution also proved to be a robust system for deployment onboard physical UAVs flying in the extremely harsh and confined environment of the real-world competition. The proposed approach enables fully autonomous and decentralized deployment of a UAV team with seamless simulation-to-world transfer, and proves its advantage over less mobile UGV teams in the flyable space of diverse environments. The main contributions of the paper are present in the mapping and navigation pipelines. The mapping approach employs novel map representations — SphereMap for efficient risk-aware long-distance planning, FacetMap for surface coverage, and the compressed topological-volumetric LTVMap for allowing multi-robot cooperation under low-bandwidth communication. These representations are used in navigation together with novel methods for visibility-constrained informed search in a general 3D environment with no assumptions about the environment structure, while balancing deep exploration with sensor-coverage exploitation. The proposed solution also includes a visual-perception pipeline for on-board detection and localization of objects of interest in four RGB stream at 5 Hz each without a dedicated GPU. Apart from participation in the DARPA SubT, the performance of the UAV system is supported by extensive experimental verification in diverse environments with both qualitative and quantitative evaluation.
DARPA Subterranean Challenge: Multi-robotic exploration of underground environments
- Autoři: Rouček, T., Mgr. Martin Pecka, Ph.D., Čížek, P., Petříček, T., Ing. Jan Bayer, Šalanský, V., Ing. Daniel Heřt, Ing. Matěj Petrlík, Ing. Tomáš Báča, Ph.D., Spurný, V., Pomerleau, F., Kubelka, V., prof. Ing. Jan Faigl, Ph.D., doc. Ing. Karel Zimmermann, Ph.D., doc. Ing. Martin Saska, Dr. rer. nat., prof. Ing. Tomáš Svoboda, Ph.D., doc. Ing. Tomáš Krajník, Ph.D.,
- Publikace: 6th International Workshop on Modelling and Simulation for Autonomous Systems. Wien: Springer, 2020. p. 274-290. ISSN 1611-3349. ISBN 9783030438890.
- Rok: 2020
- DOI: 10.1007/978-3-030-43890-6_22
- Odkaz: https://doi.org/10.1007/978-3-030-43890-6_22
- Pracoviště: Centrum umělé inteligence, Vidění pro roboty a autonomní systémy, Multirobotické systémy
-
Anotace:
The Subterranean Challenge (SubT) is a contest organised by the Defense Advanced Research Projects Agency (DARPA). The contest reflects the requirement of increasing safety and efficiency of underground search-and-rescue missions. In the SubT challenge, teams of mobile robots have to detect, localise and report positions of specific objects in an underground environment. This paper provides a description of the multi-robot heterogeneous exploration system of our CTU-CRAS team, which scored third place in the Tunnel Circuit round, surpassing the performance of all other non-DARPA-funded competitors. In addition to the description of the platforms, algorithms and strategies used, we also discuss the lessons-learned by participating at such contest.
Data-driven Policy Transfer with Imprecise Perception Simulation
- Autoři: Mgr. Martin Pecka, Ph.D., doc. Ing. Karel Zimmermann, Ph.D., Ing. Matěj Petrlík, prof. Ing. Tomáš Svoboda, Ph.D.,
- Publikace: IEEE Robotics and Automation Letters. 2018, 3(4), 3916-3921. ISSN 2377-3766.
- Rok: 2018
- DOI: 10.1109/LRA.2018.2857927
- Odkaz: https://doi.org/10.1109/LRA.2018.2857927
- Pracoviště: Katedra kybernetiky, Vidění pro roboty a autonomní systémy
-
Anotace:
This paper presents a complete pipeline for learning continuous motion control policies for a mobile robot when only a non-differentiable physics simulator of robot-terrain interactions is available. The multi-modal state estimation of the robot is also complex and difficult to simulate, so we simultaneously learn a generative model which refines simulator outputs. We propose a coarse-to-fine learning paradigm, where the coarse motion planning is alternated with guided learning and policy transfer to the real robot. The policy is jointly optimized with the generative model. We evaluate the method on a real-world platform.
Controlling Robot Morphology From Incomplete Measurements
- Autoři: Mgr. Martin Pecka, Ph.D., doc. Ing. Karel Zimmermann, Ph.D., Reinštein, M., prof. Ing. Tomáš Svoboda, Ph.D.,
- Publikace: IEEE Transactions on Industrial Electronics. 2017, 64(2), 1773-1782. ISSN 0278-0046.
- Rok: 2017
- DOI: 10.1109/TIE.2016.2580125
- Odkaz: https://doi.org/10.1109/TIE.2016.2580125
- Pracoviště: Katedra kybernetiky, Vidění pro roboty a autonomní systémy
-
Anotace:
Mobile robots with complex morphology are essential for traversing rough terrains in Urban Search & Rescue missions. Since teleoperation of the complex morphology causes high cognitive load of the operator, the morphology is controlled autonomously. The autonomous control measures the robot state and surrounding terrain which is usually only partially observable, and thus the data are often incomplete. We marginalize the control over the missing measurements and evaluate an explicit safety condition. If the safety condition is violated, tactile terrain exploration by the body-mounted robotic arm gathers the missing data.
Fast Simulation of Vehicles with Non-deformable Tracks
- Autoři: Mgr. Martin Pecka, Ph.D., doc. Ing. Karel Zimmermann, Ph.D., prof. Ing. Tomáš Svoboda, Ph.D.,
- Publikace: Intelligent Robots and Systems (IROS), 2017 IEEE/RSJ International Conference on. Piscataway: IEEE, 2017. p. 6414-6419. ISSN 2153-0866. ISBN 978-1-5386-2682-5.
- Rok: 2017
- DOI: 10.1109/IROS.2017.8206546
- Odkaz: https://doi.org/10.1109/IROS.2017.8206546
- Pracoviště: Katedra kybernetiky, Vidění pro roboty a autonomní systémy
-
Anotace:
This paper presents a novel technique that allows for both computationally fast and sufficiently plausible simulation of vehicles with non-deformable tracks. The method is based on an effect we have called Contact Surface Motion. A comparison with several other methods for simulation of tracked vehicle dynamics is presented with the aim to evaluate methods that are available off-the-shelf or with minimum effort in general-purpose robotics simulators. The proposed method is implemented as a plugin for the open-source physics-based simulator Gazebo using the Open Dynamics Engine.
Autonomous Flipper Control with Safety Constraints
- Autoři: Mgr. Martin Pecka, Ph.D., Šalanský, V., doc. Ing. Karel Zimmermann, Ph.D., prof. Ing. Tomáš Svoboda, Ph.D.,
- Publikace: Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on. Piscataway: IEEE, 2016. p. 2889-2894. ISSN 2153-0866. ISBN 978-1-5090-3762-9.
- Rok: 2016
- DOI: 10.1109/IROS.2016.7759447
- Odkaz: https://doi.org/10.1109/IROS.2016.7759447
- Pracoviště: Katedra kybernetiky, Vidění pro roboty a autonomní systémy
-
Anotace:
Policy Gradient methods require many real-world trials. Some of the trials may endanger the robot system and cause its rapid wear. Therefore, a safe or at least gentle-to-wear exploration is a desired property. We incorporate bounds on the probability of unwanted trials into the recent Contextual Relative Entropy Policy Search method. The proposed algorithm is evaluated on the task of autonomous flipper control for a real Search and Rescue rover platform.
Safe Exploration for Reinforcement Learning in Real Unstructured Environments
- Autoři: Mgr. Martin Pecka, Ph.D., doc. Ing. Karel Zimmermann, Ph.D., prof. Ing. Tomáš Svoboda, Ph.D.,
- Publikace: CVWW 2015: Proceedings of the 20th Computer Vision Winter Workshop. Graz: Graz University of Technology, 2015, pp. 85-93. ISBN 978-3-85125-388-7.
- Rok: 2015
- Pracoviště: Katedra kybernetiky
-
Anotace:
In USAR (Urban Search and Rescue) missions, robots are often required to operate in an unknown environment and with imprecise data coming from their sensors. However, it is highly desired that the robots only act in a safe manner and do not perform actions that could probably make damage to them. To train some tasks with the robot, we utilize reinforcement learning (RL). This machine learning method however requires the robot to perform actions leading to unknown states, which may be dangerous. We develop a framework for training a safety function which constrains possible actions to a subset of really safe actions. Our approach utilizes two basic concepts. First, a "core" of the safety function is given by a cautious simulator and possibly also by manually given examples. Second, a classifier training phase is performed (using Neyman-Pearson SVMs), which extends the safety function to the states where the simulator fails to recognize safe states.
Safe Exploration Techniques for Reinforcement Learning - An Overview
- Autoři: Mgr. Martin Pecka, Ph.D., prof. Ing. Tomáš Svoboda, Ph.D.,
- Publikace: Modelling and Simulation for Autonomous Systems. Cham: Springer, 2014. p. 357-375. Lecture Notes in Computer Science. ISSN 0302-9743. ISBN 978-3-319-13822-0.
- Rok: 2014
- DOI: 10.1007/978-3-319-13823-7_31
- Odkaz: https://doi.org/10.1007/978-3-319-13823-7_31
- Pracoviště: Katedra kybernetiky
-
Anotace:
We overview different approaches to safety in (semi)autonomous robotics. Part icularly, we focus on how to achieve safe behavior of a robot if it is requested to perform ex ploration of unknown states. Presented methods are studied from the viewpoint of reinforcement learning, a partially-supervised machine learning method. To collect training data for this a lgorithm, the robot is required to freely explore the state space - which can lead to possibly dangerous situations. The role of safe exploration is to provide a framework allowing explora tion while preserving safety. The examined methods range from simple algorithms to sophisticat ed methods based on previous experience or state prediction. Our overview also addresses the i ssues of how to define safety in the real-world applications (apparently absolute safety is un achievable in the continuous and random real world). In the conclusion we also suggest several ways that are worth researching more thoroughly.