DeepMNavigate: Deep Reinforced Multi-Robot Navigation Unifying Local & Global Collision Avoidance

Abstract

We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning (DRL). Our approach uses local and global information for each robot from motion information maps. We use a three-layer CNN that takes these maps as input to generate a suitable action to drive each robot to its goal position. Our approach is general, learns an optimal policy using a multi-scenario, multi-state training algorithm, and can directly handle raw sensor measurements for local observations. We demonstrate the performance on dense, complex benchmarks with narrow passages and environments with tens of agents. We highlight the algorithm's benefits over prior learning methods and geometric decentralized algorithms in complex scenarios.

References in corpus (4)

• Social Force Model for Pedestrian Dynamics
• From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
• Uncertainty-Aware Reinforcement Learning for Collision Avoidance
• Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios