Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning
Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths often requires anticipating interaction with neighboring...
Published in: | 2017 IEEE International Conference on Robotics and Automation (ICRA) |
---|---|
Main Authors: | , , , |
Other Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/114720 |
id |
ftmit:oai:dspace.mit.edu:1721.1/114720 |
---|---|
record_format |
openpolar |
spelling |
ftmit:oai:dspace.mit.edu:1721.1/114720 2023-06-11T04:15:47+02:00 Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning Chen, Yu Fan Liu, Miao Everett, Michael F How, Jonathan P Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Chen, Yu Fan Liu, Miao Everett, Michael F How, Jonathan P 2018-03-21T16:59:10Z application/pdf http://hdl.handle.net/1721.1/114720 unknown Institute of Electrical and Electronics Engineers (IEEE) http://dx.doi.org/10.1109/ICRA.2017.7989037 2017 IEEE International Conference on Robotics and Automation (ICRA) 978-1-5090-4633-1 978-1-5090-4634-8 http://hdl.handle.net/1721.1/114720 Chen, Yu Fan, Miao Liu, Michael Everett, and Jonathan P. How. “Decentralized Non-Communicating Multiagent Collision Avoidance with Deep Reinforcement Learning.” 2017 IEEE International Conference on Robotics and Automation (ICRA), May 2017, Singapore, Singapore, 2017. orcid:0000-0003-3756-3256 orcid:0000-0002-1648-8325 orcid:0000-0001-9377-6745 orcid:0000-0001-8576-1930 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ arXiv Article http://purl.org/eprint/type/ConferencePaper 2018 ftmit https://doi.org/10.1109/ICRA.2017.7989037 2023-05-29T08:45:37Z Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths often requires anticipating interaction with neighboring agents, the process of which can be computationally prohibitive. This work presents a decentralized multiagent collision avoidance algorithm based on a novel application of deep reinforcement learning, which effectively offloads the online computation (for predicting interaction patterns) to an offline learning procedure. Specifically, the proposed approach develops a value network that encodes the estimated time to the goal given an agent's joint configuration (positions and velocities) with its neighbors. Use of the value network not only admits efficient (i.e., real-time implementable) queries for finding a collision-free velocity vector, but also considers the uncertainty in the other agents' motion. Simulation results show more than 26% improvement in paths quality (i.e., time to reach the goal) when compared with optimal reciprocal collision avoidance (ORCA), a state-of-the-art collision avoidance strategy. Ford Motor Company Article in Journal/Newspaper Orca DSpace@MIT (Massachusetts Institute of Technology) 2017 IEEE International Conference on Robotics and Automation (ICRA) 285 292 |
institution |
Open Polar |
collection |
DSpace@MIT (Massachusetts Institute of Technology) |
op_collection_id |
ftmit |
language |
unknown |
description |
Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths often requires anticipating interaction with neighboring agents, the process of which can be computationally prohibitive. This work presents a decentralized multiagent collision avoidance algorithm based on a novel application of deep reinforcement learning, which effectively offloads the online computation (for predicting interaction patterns) to an offline learning procedure. Specifically, the proposed approach develops a value network that encodes the estimated time to the goal given an agent's joint configuration (positions and velocities) with its neighbors. Use of the value network not only admits efficient (i.e., real-time implementable) queries for finding a collision-free velocity vector, but also considers the uncertainty in the other agents' motion. Simulation results show more than 26% improvement in paths quality (i.e., time to reach the goal) when compared with optimal reciprocal collision avoidance (ORCA), a state-of-the-art collision avoidance strategy. Ford Motor Company |
author2 |
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Chen, Yu Fan Liu, Miao Everett, Michael F How, Jonathan P |
format |
Article in Journal/Newspaper |
author |
Chen, Yu Fan Liu, Miao Everett, Michael F How, Jonathan P |
spellingShingle |
Chen, Yu Fan Liu, Miao Everett, Michael F How, Jonathan P Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
author_facet |
Chen, Yu Fan Liu, Miao Everett, Michael F How, Jonathan P |
author_sort |
Chen, Yu Fan |
title |
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
title_short |
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
title_full |
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
title_fullStr |
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
title_full_unstemmed |
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
title_sort |
decentralized non-communicating multiagent collision avoidance with deep reinforcement learning |
publisher |
Institute of Electrical and Electronics Engineers (IEEE) |
publishDate |
2018 |
url |
http://hdl.handle.net/1721.1/114720 |
genre |
Orca |
genre_facet |
Orca |
op_source |
arXiv |
op_relation |
http://dx.doi.org/10.1109/ICRA.2017.7989037 2017 IEEE International Conference on Robotics and Automation (ICRA) 978-1-5090-4633-1 978-1-5090-4634-8 http://hdl.handle.net/1721.1/114720 Chen, Yu Fan, Miao Liu, Michael Everett, and Jonathan P. How. “Decentralized Non-Communicating Multiagent Collision Avoidance with Deep Reinforcement Learning.” 2017 IEEE International Conference on Robotics and Automation (ICRA), May 2017, Singapore, Singapore, 2017. orcid:0000-0003-3756-3256 orcid:0000-0002-1648-8325 orcid:0000-0001-9377-6745 orcid:0000-0001-8576-1930 |
op_rights |
Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ |
op_doi |
https://doi.org/10.1109/ICRA.2017.7989037 |
container_title |
2017 IEEE International Conference on Robotics and Automation (ICRA) |
container_start_page |
285 |
op_container_end_page |
292 |
_version_ |
1768372904186085376 |