Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning
Author(s)
Chen, Yu Fan; Liu, Miao; Everett, Michael F; How, Jonathan P
Download1609.07845.pdf (3.205Mb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
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.
Date issued
2017-07Department
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 SystemsJournal
2017 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
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.
Version: Original manuscript
ISBN
978-1-5090-4633-1
ISSN
978-1-5090-4634-8