Adaptive learning-based model predictive control strategy for drift vehicles

  Autonomous Drifting     |      2025-03-07 17:02

Abstract

Drift vehicle control offers valuable insights to support safe autonomous driving in extreme conditions, which hinges on tracking a particular path while maintaining the vehicle states near the drift equilibrium points (DEP). However, conventional tracking methods are not adaptable for drift vehicles due to their opposite steering angle and yaw rate. In this paper, we propose an adaptive path tracking (APT) control method to dynamically adjust drift states to follow the reference path, improving the commonly utilized predictive path tracking methods with released computation burden. Furthermore, existing control strategies necessitate a precise system model to calculate the DEP, which can be more intractable due to the highly nonlinear drift dynamics and sensitive vehicle parameters. To tackle this problem, an adaptive learning-based model predictive control (ALMPC) strategy is proposed based on the APT method, where an upper-level Bayesian optimization is employed to learn the DEP and APT control law to instruct a lower-level MPC drift controller. This hierarchical system architecture can also resolve the inherent control conflict between path tracking and drifting by separating these objectives into different layers. The ALMPC strategy is verified on the Matlab-Carsim platform, and simulation results demonstrate its effectiveness in controlling the drift vehicle to follow a clothoid-based reference path even with the misidentified road friction parameter.

image.pngimage.pngimage.png

[Paper Link]

Contributions

1. The path tracking problem for drift vehicles is solved by executing smooth transitions among various drift states, and an APT control method is proposed to dynamically adjust the drift radius and steering angle to enhance the path tracking performance. 

2. An adaptive learning-based model predictive control (ALMPC) strategy is proposed in this paper, where an upper-level BO supervisor is employed to compensate for modeling error by learning the APT control law and optimal DEP, then provides the learned parameters to instruct the lower-level MPC drift controller. 

3. Simulation results indicate that the ALMPC strategy can effectively mitigate the drifting-tracking control conflict and compensate for modeling errors, outperforming traditional optimizationbased approaches.