Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture

TL;DR

This paper introduces a hybrid imitation-reinforcement learning approach and a custom simulator for autonomous racing, achieving faster lap times than human drivers through optimized trajectory planning and quick reactions.

Contribution

The paper presents a novel hybrid learning architecture and a dedicated simulator for autonomous racing, enabling rapid training and superior performance over human drivers.

Findings

Autonomous agent reduced lap time by 0.96 seconds compared to best manual lap.

Autonomous system outperformed human players by 1.46 seconds on average.

Training was completed in less than 20 hours using the proposed method.

Abstract

In this work, we present a rigorous end-to-end control strategy for autonomous vehicles aimed at minimizing lap times in a time attack racing event. We also introduce AutoRACE Simulator developed as a part of this research project, which was employed to simulate accurate vehicular and environmental dynamics along with realistic audio-visual effects. We adopted a hybrid imitation-reinforcement learning architecture and crafted a novel reward function to train a deep neural network policy to drive (using imitation learning) and race (using reinforcement learning) a car autonomously in less than 20 hours. Deployment results were reported as a direct comparison of 10 autonomous laps against 100 manual laps by 10 different human players. The autonomous agent not only exhibited superior performance by gaining 0.96 seconds over the best manual lap, but it also dominated the human players by 1.46 seconds with regard to the mean lap time. This dominance could be justified in terms of better trajectory optimization and lower reaction time of the autonomous agent.