Adaptive learning-based model predictive control strategy for drift vehicles

Bei Zhou, Cheng Hu, Jun Zeng, Zhouheng Li, Johannes Betz, Lei Xie, Hongye Su

Abstract: Highlights•An adaptive path tracking (APT) control method to improve path tracking performance.•Identify optimal drift equilibrium points (DEP) to compensate for modeling error.•The optimal APT control law and DEP are learned through Bayesian optimization.•This hierarchical structure can resolve the drifting-tracking control conflict.•We conduct two simulations to validate our approach on the Matlab-Carsim platform.