A predictive safety filter for learning-based racing control

TL;DR

This paper introduces a predictive safety filter using model predictive control to ensure safety in learning-based racing control, enabling aggressive maneuvers while maintaining track boundary safety.

Contribution

It develops a minimally invasive safety filter with a real-time extendable safe set for nonlinear vehicle models, supporting aggressive racing with safety guarantees.

Findings

Successfully maintains vehicle safety during aggressive maneuvers

Supports learning-based control methods with safety guarantees

Real-time safe set extension improves performance

Abstract

The growing need for high-performance controllers in safety-critical applications like autonomous driving has been motivating the development of formal safety verification techniques. In this paper, we design and implement a predictive safety filter that is able to maintain vehicle safety with respect to track boundaries when paired alongside any potentially unsafe control signal, such as those found in learning-based methods. A model predictive control (MPC) framework is used to create a minimally invasive algorithm that certifies whether a desired control input is safe and can be applied to the vehicle, or that provides an alternate input to keep the vehicle in bounds. To this end, we provide a principled procedure to compute a safe and invariant set for nonlinear dynamic bicycle models using efficient convex approximation techniques. To fully support an aggressive racing performance without conservative safety interventions, the safe set is extended in real-time through predictive control backup trajectories. Applications for assisted manual driving and deep imitation learning on a miniature remote-controlled vehicle demonstrate the safety filter's ability to ensure vehicle safety during aggressive maneuvers.