Learning the Subsystem of Local Planning for Autonomous Racing
This addresses autonomous racing for robotics applications with limited sensing, though it appears incremental as it builds on existing hierarchical methods.
The paper tackles autonomous racing without maintaining an updated obstacle map by proposing a hierarchical planning architecture where a reinforcement learning agent modifies path-follower references for obstacle avoidance. Results show faster average times than an end-to-end baseline and a 94% success rate in F1/10th racing.
The problem of autonomous racing is to navigate through a race course as quickly as possible while not colliding with any obstacles. We approach the autonomous racing problem with the added constraint of not maintaining an updated obstacle map of the environment. Several current approaches to this problem use end-to-end learning systems where an agent replaces the entire navigation pipeline. This paper presents a hierarchical planning architecture that combines a high level planner and path following system with a reinforcement learning agent that learns that subsystem of obstacle avoidance. The novel "modification planner" uses the path follower to track the global plan and the deep reinforcement learning agent to modify the references generated by the path follower to avoid obstacles. Importantly, our architecture does not require an updated obstacle map and only 10 laser range finders to avoid obstacles. The modification planner is evaluated in the context of F1/10th autonomous racing and compared to a end-to-end learning baseline, the Follow the Gap Method and an optimisation based planner. The results show that the modification planner can achieve faster average times compared to the baseline end-to-end planner and a 94% success rate which is similar to the baseline.