Lipschitz Safe Bayesian Optimization for Automotive Control

TL;DR

This paper introduces a Lipschitz-based safe Bayesian optimization algorithm that guarantees safety and handles multiple constraints, demonstrated on tuning a self-driving car's controller without safety violations.

Contribution

It develops a safe Bayesian optimization method based on Lipschitz assumptions that is practical, interpretable, and capable of managing multiple safety constraints simultaneously.

Findings

Successfully tuned a self-driving car's controller in simulation and real tests.

The algorithm guarantees safety by avoiding constraint violations during optimization.

Demonstrated effectiveness in automotive control with safety assurances.

Abstract

Controller tuning is a labor-intensive process that requires human intervention and expert knowledge. Bayesian optimization has been applied successfully in different fields to automate this process. However, when tuning on hardware, such as in automotive applications, strict safety requirements often arise. To obtain safety guarantees, many existing safe Bayesian optimization methods rely on assumptions that are hard to verify in practice. This leads to the use of unjustified heuristics in many applications, which invalidates the theoretical safety guarantees. Furthermore, applications often require multiple safety constraints to be satisfied simultaneously. Building on recently proposed Lipschitz-only safe Bayesian optimization, we develop an algorithm that relies on readily interpretable assumptions and satisfies multiple safety constraints at the same time. We apply this algorithm to the problem of automatically tuning a trajectory-tracking controller of a self-driving car. Results both from simulations and an actual test vehicle underline the algorithm's ability to learn tracking controllers without leaving the track or violating any other safety constraints.