Research on Learning-Based Model Predictive Path Tracking Control for Autonomous Vehicles

被引：0

作者：

Han, Mo ^{[1
]}

He, Hongwen ^{[1
]}

Shi, Man ^{[1
]}

Liu, Wei ^{[2
]}

Cao, Jianfei ^{[3
]}

Wu, Jingda ^{[4
]}

机构：

[1] Beijing Institute of Technology, National Key Laboratory of Advanced Vehicle Integration and Control, Beijing

[2] UTOPILOT, Shanghai

[3] Beijing Institute of Spacecraft System Engineering, Beijing

[4] The Hong Kong Polytechnic University

来源：

Qiche Gongcheng/Automotive Engineering | 2024年 / 46卷 / 07期

关键词：

Gaussian process regression; model predictive control; path tracking; vehicle model error analysis;

D O I：

10.19562/j.chinasae.qcgc.2024.07.007

中图分类号：

学科分类号：

摘要：

For the trade-off between prediction model accuracy and computational cost for path tracking control of autonomous vehicles，a learning-based model predictive control（LB-MPC）path tracking control strategy is proposed in this paper. A two-degree-of-freedom single-track vehicle dynamic model is established，and an in-depth analysis is conducted on its step response error with respect to variation in vehicle speed，pedal position，and front wheel steering angle compared to the IPG TruckMaker model.Methods for constructing error datasets and re⁃ ceding horizon updates are designed，and the Gaussian process regression（GPR）is employed to establish an error-fitting model for real-time error compensation and correction of the nominal single-track model. The error correction model is utilized as the prediction model，and a path tracking cost function is designed to formulate a quadratic pro⁃ gramming optimization problem，proposing a learning-based model predictive path tracking control architecture. Through joint simulation using the IPG TruckMaker & Simulink platform and real vehicle experiments，the real-time performance and effectiveness of the proposed GPR error correction model and LB-MPC path tracking control strategy are verified. The results show that compared to the traditional model predictive control（MPC）path tracking control strategy，the proposed LB-MPC strategy reduces the average path tracking error by 23.64%. © 2024 SAE-China. All rights reserved.

引用

页码：1197 / 1207

页数：10

共 25 条

[1] Notice of the state council on issuing the development plan for modern comprehensive transportation system during the 14th Five Year Plan Period［R］, The Bulletin of the State Council of the People's Republic of China, 4, pp. 8-28
[2] FANG P, CAI Y，, CHEN L，, Et al., Trajectory tracking control method based on vehicle dynamics hybrid model for intelligent vehicle［J］, Automotive Engineering, 44, 10, pp. 1469-1483, (2022)
[3] CHEN H, CHEN S, GONG J., A review on the research of lateral control for intelligent vehicles［J］, Acta Armamentarii, 38, 6, pp. 1203-1214, (2017)
[4] CHEN H, GONG J., Introduction to self-driving car ［M］, (2014)
[5] GONG J, GONG S，, LIN Y，, Et al., Review on machine learning methods for motion planning and control policy of intelligent vehicles［J］, Transactions of Beijing Institute of Technology, 42, 7, pp. 665-674, (2022)
[6] MAYNE D Q., Model predictive control：recent developments and future promise［J］, Automatica, 50, 12, pp. 2967-2986, (2014)
[7] RAJAGOPAL K R., A review of automatic vehicle following systems［J］, Journal of the Indian Institute of Science, 99, 4, pp. 567-587, (2019)
[8] Modelling and control strategies in path tracking control for autonomous ground vehicles：a review of state of the art and challenges［J］, Journal of Intelligent & Robotic Systems, 86, 2, pp. 225-254, (2017)
[9] XIONG L, Et al., Review on motion control of autonomous vehicles［J］, Journal of Mechanical Engineering, 56, 10, pp. 127-143, (2020)
[10] ZHANG K, Et al., A survey on learning-based model predictive control：toward path tracking control of mobile platforms［J］, Applied Sciences, 12, 4, (2022)

← 1 2 3 →