The Edge of Disaster: A Battle Between Autonomous Racing and Safety

TL;DR

This paper presents a model predictive control approach for autonomous racing that balances speed and safety, enabling vehicles to adapt to new tracks while minimizing the risk of losing control.

Contribution

We introduce a safe MPC baseline that can adapt to unseen racetracks in a single lap, demonstrating competitive performance in simulation.

Findings

Successfully adapts to new racetracks in one lap

Achieves competitive lap times while maintaining safety

Demonstrates effectiveness in simulation environment

Abstract

Autonomous racing represents a uniquely challenging control environment where agents must act while on the limits of a vehicle's capability in order to set competitive lap times. This places the agent on a knife's edge, with a very small margin between success and loss of control. Pushing towards this limit leads to a practical tension: we want agents to explore the limitations of vehicle control to maximise speed, but inadvertently going past that limit and losing control can cause irreparable damage to the vehicle itself. We provide a model predictive control (MPC) baseline that is able to, in a single lap, safely adapt to an unseen racetrack and achieve competitive lap times. Our approaches efficacy is demonstrated in simulation using the Learn To Race Challenge's environment and metrics.