Efficient Learning of Vehicle Controller Parameters via Multi-Fidelity Bayesian Optimization: From Simulation to Experiment

TL;DR

This paper introduces a multi-fidelity Bayesian optimization method that efficiently tunes vehicle controller parameters by combining simulation data and limited real-world tests, reducing costs and time in automotive development.

Contribution

The paper presents an auto-regressive multi-fidelity Gaussian process model integrated into Bayesian optimization, enabling effective knowledge transfer across fidelity levels without extra low-fidelity evaluations.

Findings

Achieves high-quality vehicle controller performance with minimal real-world experiments.

Significantly reduces tuning time and costs compared to traditional methods.

Validated through both simulation and real-world experiments.

Abstract

Parameter tuning for vehicle controllers remains a costly and time-intensive challenge in automotive development. Traditional approaches rely on extensive real-world testing, making the process inefficient. We propose a multi-fidelity Bayesian optimization approach that efficiently learns optimal controller parameters by leveraging both low-fidelity simulation data and a very limited number of real-world experiments. Our approach significantly reduces the need for manual tuning and expensive field testing while maintaining the standard two-stage development workflow used in industry. The core contribution is the integration of an auto-regressive multi-fidelity Gaussian process model into Bayesian optimization, enabling knowledge transfer between different fidelity levels without requiring additional low-fidelity evaluations during real-world testing. We validate our approach through both simulation studies and realworld experiments. The results demonstrate that our method achieves high-quality controller performance with only very few real-world experiments, highlighting its potential as a practical and scalable solution for intelligent vehicle control tuning in industrial applications.