Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning
Yu Fan Chen, Miao Liu, Michael Everett et al. · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 2017
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.
Cited by 645 works. doi:10.1109/icra.2017.7989037 Open-access PDF
Authors
References
- Human-level control through deep reinforcement learning
- Mastering the game of Go with deep neural networks and tree search
- Reciprocal n-Body Collision Avoidance
- Reciprocal Velocity Obstacles for real-time multi-agent navigation
- Unfreezing the robot: Navigation in dense, interacting crowds
- Mixed-integer quadratic program trajectory generation for heterogeneous quadrotor teams
- Socially compliant mobile robot navigation via inverse reinforcement learning
- The Hybrid Reciprocal Velocity Obstacle
- ClearPath
- SIPP: Safe interval path planning for dynamic environments