Autonomous Vehicle Path Tracking Control based on Adaptive Dynamic Programming

Abstract

This paper presents a path tracking control method for autonomous vehicles by utilizing Adaptive Dynamic Programming (ADP). The primary goal is to enhance the path tracking performance under various longitudinal speeds. The proposed approach incorporates the consideration of nonlinear tire characteristics and establishes a nonlinear vehicle system model based on the fundamental principles of vehicle dynamics. By formulating a performance index function that captures the correlation between the vehicle's position and desired paths, the optimal control strategy is obtained using the Dual Heuristic Programming algorithm (DHP), known for its computational efficiency, within the ADP framework. The simulation results verify the effectiveness of the proposed path tracking control scheme, which can have better control performance under different vehicle speeds.