Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car

TL;DR

This paper explores using deep reinforcement learning for end-to-end control of an autonomous Formula SAE race car, demonstrating successful simulation training and transfer to real-world racing, with insights into future improvements.

Contribution

It introduces a novel application of deep RL algorithms for autonomous racing in Formula SAE, including simulation training and real-world transfer, with analysis of limitations and future directions.

Findings

RL algorithms successfully learned to race in simulation

Transferred learned policies from simulation to real-world platform

Identified key limitations and future research directions

Abstract

With the rising popularity of autonomous navigation research, Formula Student (FS) events are introducing a Driverless Vehicle (DV) category to their event list. This paper presents the initial investigation into utilising Deep Reinforcement Learning (RL) for end-to-end control of an autonomous FS race car for these competitions. We train two state-of-the-art RL algorithms in simulation on tracks analogous to the full-scale design on a Turtlebot2 platform. The results demonstrate that our approach can successfully learn to race in simulation and then transfer to a real-world racetrack on the physical platform. Finally, we provide insights into the limitations of the presented approach and guidance into the future directions for applying RL toward full-scale autonomous FS racing.