Collision Avoidance among Dense Heterogeneous Agents Using Deep Reinforcement Learning

Navigating in a complex congested social environ- ment without collision is a crucial and challenging task. Recent studies have demonstrated the considerable success of Deep Reinforcement Learning (DRL) in multi-agent collision avoid- ance. However, the assumption of these studies that agents are homogeneous circles deviates from reality, leading to performance deterioration in congested scenarios. The current work extends the DRL-based approaches to develop a collision avoidance method for congested scenarios wherein the heterogeneity of agents can no longer be disregarded. Considering shape het- erogeneity, we use the Orientated Bounding Capsule (OBC) to model the agents and transform the interactive state space of Robot-Obstacle agent pair. For speed heterogeneity, we design a velocity-related collision risk function to shape the behavior of the robot. Experimental results demonstrate that our proposed method outperforms state-of-the-art DRL-based approaches in terms of success rate and safety. It also exhibits desired collision avoidance behavior.