Reward Signal Design for Autonomous Racing

TL;DR

This paper explores reward signal design for reinforcement learning in autonomous racing, proposing new methods and evaluating their effectiveness in simulation to improve lap times and control behavior.

Contribution

It introduces a novel reward based on state relative to an optimal trajectory and compares multiple reward strategies for autonomous racing.

Findings

Distance and velocity-based rewards yield fastest lap times

Rewarding on state relative to an optimal trajectory improves performance

Different reward signals significantly affect agent behavior and efficiency

Abstract

Reinforcement learning (RL) has shown to be a valuable tool in training neural networks for autonomous motion planning. The application of RL to a specific problem is dependent on a reward signal to quantify how good or bad a certain action is. This paper addresses the problem of reward signal design for robotic control in the context of local planning for autonomous racing. We aim to design reward signals that are able to perform well in multiple, competing, continuous metrics. Three different methodologies of position-based, velocity-based, and action-based rewards are considered and evaluated in the context of F1/10th racing. A novel method of rewarding the agent on its state relative to an optimal trajectory is presented. Agents are trained and tested in simulation and the behaviors generated by the reward signals are compared to each other on the basis of average lap time and completion rate. The results indicate that a reward based on the distance and velocity relative to a minimum curvature trajectory produces the fastest lap times.