Semi-Active Suspension Control Design via Bayesian Optimization

Abstract

The fine tuning of semi-active suspension control systems for road vehicles is usually a costly and burdensome task, needing control expertise and many hours of professional driving. In this paper, we propose a data-driven tuning method enabling the automatic calibration of the parameters of the suspension controller using a small number of experiments and exploiting Bayesian Optimization tools. The effectiveness of the proposed approach is validated on a commercial multi-body simulator. As a side contribution, the approach is shown to be robust with respect to variations of the testing conditions.