Path tracking control of autonomous vehicles via prescribed performance approach

• Published in: Neural computing & applications Vol. 37; no. 5; pp. 3839 - 3856
• Main Authors: Zhang, Sucai, Wang, Yongfu, Li, Gang, Wang, Yunlong
• Format: Journal Article
• Language: English
• Published: London Springer London 01.02.2025; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Autonomous vehicles; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Control systems design; Controllers; Data Mining and Knowledge Discovery; Design; Disturbance observers; Image Processing and Computer Vision; Methods; Motion control; Neural networks; Original Article; Path tracking; Probability and Statistics in Computer Science; Sensors; Sideslip; State observers; Tires; Tracking control; Tracking errors; Traffic control; Path tracking; Neural network; Prescribed performance; Autonomous vehicles
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-024-10680-7

This paper addresses the path tracking control problem for autonomous vehicles subject to the compound disturbance and unavailable variable. Before the controller design, a state observer and a disturbance observer are constructed to estimate the sideslip angle and the compound disturbance, respectively. Then, a prescribed performance function is proposed to bound the tracking error to improve the tracking accuracy. Finally, the controller is designed based on the backstepping scheme. The Lyapunov stability theory shows that the tracking error converges to a preset range. The effectiveness of the proposed method is verified by hardware-in-the-loop and real vehicle experiments.