Adaptive Learning-based Model Predictive Control Strategy for Drift Vehicles

TL;DR

The paper tackles drift-vehicle path tracking under nonlinear dynamics and parameter uncertainty by introducing an Adaptive Learning-based MPC (ALMPC) framework. An upper-level Bayesian optimization (BO) supervisor learns both the drift equilibrium point (DEP) and an Adaptive Path Tracking (APT) control law, which then informs a lower-level MPC drift controller to separately manage drifting and path tracking. Key innovations include a dynamic drift-radius update driven by look-ahead error and a steering-angle feedback mechanism, along with DEP identification to compensate for model errors; the approach is validated on a Matlab-Carsim setup with clothoid references and misidentified road friction, showing improved tracking accuracy and robust drifting compared to PPT, DEP, and deep reinforcement learning baselines. The results demonstrate that learning-based DEP and APT integration reduces control conflicts, lowers computational burden, and enhances robustness for autonomous drifting in uncertain environments, with practical implications for high-performance autonomous driving under extreme conditions.

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.

Figures (15)

• Figure 1: The principle of DEP identification.
• Figure 2: Single-track vehicle model for drifting.
• Figure 3: Prediction-based path tracking (PPT) control.
• Figure 4: Hierarchical system architecture of the ALMPC strategy.
• Figure 5: The proposed adaptive path tracking (APT) control.