Accelerating Real-World Overtaking in F1TENTH Racing Employing Reinforcement Learning Methods

TL;DR

This paper introduces a reinforcement learning-based racing agent for F1Tenth vehicles that reliably performs overtaking maneuvers in real-world wheel-to-wheel racing, achieving an 87% overtaking success rate.

Contribution

It presents a novel reinforcement learning approach for autonomous overtaking in real-world racing, demonstrating improved reliability over previous methods.

Findings

Overtaking success rate of 87% in real-world tests.

Agent trained against opponents learns deliberate overtaking behaviors.

Method outperforms agents trained only for racing without overtaking focus.

Abstract

While autonomous racing performance in Time-Trial scenarios has seen significant progress and development, autonomous wheel-to-wheel racing and overtaking are still severely limited. These limitations are particularly apparent in real-life driving scenarios where state-of-the-art algorithms struggle to safely or reliably complete overtaking manoeuvres. This is important, as reliable navigation around other vehicles is vital for safe autonomous wheel-to-wheel racing. The F1Tenth Competition provides a useful opportunity for developing wheel-to-wheel racing algorithms on a standardised physical platform. The competition format makes it possible to evaluate overtaking and wheel-to-wheel racing algorithms against the state-of-the-art. This research presents a novel racing and overtaking agent capable of learning to reliably navigate a track and overtake opponents in both simulation and reality. The agent was deployed on an F1Tenth vehicle and competed against opponents running varying competitive algorithms in the real world. The results demonstrate that the agent's training against opponents enables deliberate overtaking behaviours with an overtaking rate of 87% compared 56% for an agent trained just to race.