Simulation of intelligent vehicle trajectory tracking based on neural network adaptive MPC

doi:10.3969/j.issn.1674-8484.2025.04.014

Abstract

Abstract:

The weight matrix of traditional model predictive control (MPC) controllers usually relies on manual experience for parameter tuning, making it difficult to adapt to complex dynamic environments. Therefore, a method for adaptive adjustment of MPC weight matrices based on backpropagation (BP) neural networks was proposed. Firstly, the intelligent vehicle dynamics model with MPC control was established to analyze the influence of different weight coefficients on the vehicle trajectory tracking performance, secondly the data were constructed to train the BP neural network model, and the BP neural network adaptive MPC controller was constructed using the Matlab/Simulink module to jointly simulate with Carsim, and finally, a double-shift simulation condition was designed from different speeds and road adhesion coefficients to validate the robustness of the controller under different working conditions. The results show that the BP neural network-based adaptive MPC controller achieves favorable control performance across different speeds when the road surface adhesion coefficient is 0.85. At a speed of 65 km/h, the vehicle under the fixed-weight MPC control approaches destabilization, whereas the root-mean-squares (RMS) of the lateral displacement deviation and lateral angle deviation for the adaptive controller are reduced by 44.17% and 66.66%, respectively. The proposed controller also exhibits strong performance on road surfaces with varying adhesion coefficients—most notably on slippery roads with an adhesion coefficient of 0.35. When traveling at 30 km/h under such conditions, the RMS values of the two deviations are decreased by 27.49% and 49.54% compared to the fixed-weight MPC controller. This neural network-based approach for adaptive adjustment of MPC controller weights can provide valuable insights for enhancing trajectory tracking performance in medium-and high-speed cooperative control of intelligent connected vehicles, as well as in autonomous navigation systems for special operation vehicles.

Key words: intelligent connected vehicle, neural network, adaptive, trajectory tacking, model predictive control (MPC)

CLC Number:

U461

WANG Lin, CHEN Qinghua, YE Hongling, WANG Pengfei, XU Chi, QIAN Aiwen. Simulation of intelligent vehicle trajectory tracking based on neural network adaptive MPC[J]. Journal of Automotive Safety and Energy, 2025, 16(4): 638-647.

Figures/Tables 12

References 18

[1]	徐明泽, 刘清河. 基于LQR和PID的智能车轨迹跟踪控制算法设计与仿真[J]. 太原理工大学学报, 2022, 53(5): 52-53.
	XU Mingze, LIU Qinghe. Design and simulation of intelligent vehicle trajectory tracking control algorithm based on LQR and PID[J]. J Taiyuan Univ Tech, 2022, 53(5): 52-53. (in Chinese)
[2]	王怡萌, 仝秋红, 孙照翔, 等. 基于GA-PSO的智能汽车横向LQR控制器优化设计[J]. 汽车技术, 2024(3): 47-55.
	WANG Yimeng, TONG qiuhong, SUN Zhaoxiang, et al. Optimization design of lateral LQR controller for intelligent vehicle based on GA-PSO[J]. Autom Tech, 2024(3): 47-55. (in Chinese)
[3]	张炳力, 吕敏煜, 程进, 等. 两点预瞄轨迹跟踪横向控制系统[J]. 电子测量与仪器学报, 2019, 33(5): 158-163.
	ZHANG Bingli, Lü Minyu, CHENG Jin, et al. Track tracking lateral control system with two-point preview[J]. J Electr Meas Instrum, 2019, 33(5):158-163. (in Chinese)
[4]	邹俊逸, 吴伟伟, 严运兵, 等. 城市路况下基于模型预测控制的汽车主动避撞策略[J]. 武汉科技大学学报, 2017, 66(2): 952-964.
	ZOU Junyi, WU Weiwei, YAN Yunbing, et al. Active collision avoidance strategy based on model predictive control for vehicles under urban road conditions[J]. J Wuhan Univ Sci Tech, 2017, 66(2): 952-964. (in Chinese)
[5]	JI Jie, Khajepour A, Melek W W, et al. Path planning and tracking for vehicle collision avoidance based on model predictive control with multi-constraints[J]. IEEE Trans Vehi Tech, 2017, 66(2): 952-964.
[6]	CHEN Shuping, XIONG Guangming, CHEN Huiyan, et al. MPC-based path tracking with PID speed control for high-speed autonomous vehicles considering time-optimal travel[J]. J Cent South Univ, 2020, 27(12): 3702-3720.
[7]	张新荣, 许权宁, 宫新乐, 等. 人机共驾车辆路径跟踪集成控制策略[J]. 汽车安全与节能学报, 2022, 13(4): 686-695.
	ZHANG Xinrong, XU Quanning, GONG Xinle, et al. Integrated control strategy for path tracking of human machine co-driving vehicle[J]. J Autom Safe Energ, 2022, 13(4): 686-695. (in Chinese)
[8]	Earl C E, Gerdes J C. Model predictive control for vehicle stabilization at the limits of handling[J]. IEEE Trans Contr Syst Tech, 2013, 21(4): 1258-1269.
[9]	CUI Qingjia, DING Rongjun, WEI Chongfeng, et al. Path-tracking and lateral stabilisation for autonomous vehicles by using the steering angle envelope[J]. Vehi Syst Dyna, 2021, 59(11): 1672-1696.
[10]	李韶华, 杨泽坤, 王雪玮. 基于T-S模糊变权重MPC的智能车轨迹跟踪控制[J]. 机械工程学报, 2023, 59(4): 199-212. doi: 10.3901/JME.2023.04.199
	LI Shaohua, YANG Zekun, WANG Xuewei. Trajectory tracking control of an intelligent vehicle based on T-S fuzzy variable weight MPC[J]. J Mech Engi, 2023, 59(4): 199-212. (in Chinese)
[11]	杨泽坤, 李韶华, 王振峰. 基于自适应变参数MPC的分布式驱动智能车轨迹跟踪控制[J]. 机械工程学报, 2024, 60(6): 363-377.
	YANG Zekun, LI Shaohua, WANG Zhenfeng. Trajectory tracking control of distributed driving intelligent vehicles based on adaptive variable parameter MPC[J]. J Mech Engi, 2024, 60(6): 363-377. (in Chinese)
[12]	石贞洪, 江洪, 于文浩, 等. 适用于路径跟踪控制的自适应MPC算法研究[J]. 计算机工程与应用, 2020, 56(21): 266-271. doi: 10.3778/j.issn.1002-8331.1912-0397
	SHI Zhenhong, JIANG Hong, YU Wenhao, et al. Research on adaptive MPC algorithm for path tracking control[J]. Comput Engi Appl, 2020, 56(21): 266-271. (in Chinese)
[13]	金辉, 鲁坤. 基于多参数自适应优化的智能车轨迹跟踪[J]. 中国公路学报, 2023, 36(5): 260-272. doi: 10.19721/j.cnki.1001-7372.2023.05.022
	JIN Hui, LU Kun. Intelligent vehicle trajectory tracking based on multi-parameter adaptive optimization[J]. China J High Transport, 2023, 36(5): 260-272. (in Chinese)
[14]	WANG Huiran, WANG Qidong, CHEN Wuwei, et al. Path tracking based on model predictive control with variable predictive horizon[J]. Trans Inst Meas Contr, 2021, 43(12): 2676-2688.
[15]	杜荣华, 胡鸿飞, 高凯, 等. 基于变预测时域MPC的自动驾驶汽车轨迹跟踪控制研究[J]. 机械工程学报, 2022, 58(24): 275-288. doi: 10.3901/JME.2022.24.275
	DU Ronghua, HU Hongfei, GAO Kai, et al. Research on trajectory tracking control of autonomous vehicle based on MPC with variable predictive horizon[J]. J Mech Engi, 2022, 58(24): 275-288. (in Chinese)
[16]	WAN Yingxue, ZENG Ling. Active collision avoidance system design based on model predictive control with varying sampling time[J]. Autom Inno, 2020, 3(1): 62-72.
[17]	Amer N H, Zamzuri H, Hudha K, et al. Modelling and control strategies in path tracking control for autonomous ground vehicles: A review of state of the art and challenges[J]. J Intel Robot Syst, 2017, 86(2): 225-254.
[18]	龚建伟, 刘凯, 齐建永. 无人驾驶车辆模型预测控制[M]. 北京: 北京理工大学出版社, 2019: 27-146.
	GONG Jianwei, LIU Kai, QI Jianyong. Model Predictive Control for Self-Driving Vehicles[M]. Beijing: Beijing Institute of Technology Press, 2019: 27-146. (in Chinese)

指标	RMSE	R²
λ_?	0.032 1	0.985 0
λ_Y	0.054 7	0.968 6
R_δ	0.021 1	0.993 0

指标	RMSE	R²
λ_?	0.032 1	0.985 0
λ_Y	0.054 7	0.968 6
R_δ	0.021 1	0.993 0

整备质量	1 370 Kg
轴距	2 866 mm
前后轮侧偏刚度	前轮 55 652 N/rad 后轮 48 802 N/rad
前后轮的滑移率	前轮0.2 后轮0.2
质心到前轴的距离	1 308 mm

整备质量	1 370 Kg
轴距	2 866 mm
前后轮侧偏刚度	前轮 55 652 N/rad 后轮 48 802 N/rad
前后轮的滑移率	前轮0.2 后轮0.2
质心到前轴的距离	1 308 mm

v / (km·h^-1)	横向位移偏差峰值/ m		横向位移偏差均方根/ m		横摆角偏差峰值/ (°)		横摆角偏差均方根/ (°)
v / (km·h^-1)	BPMPC	MPC	BPMPC	MPC	BPMPC	MPC	BPMPC	MPC
30	0.469 8	0.526 4	0.171 4	0.186 4	3.268 0	5.754 9	0.994 9	1.981 3
35	0.427 7	0.560 0	0.164 6	0.199 0	3.339 0	5.672 7	1.015 2	1.955 0
40	0.389 7	0.593 3	0.159 5	0.210 9	3.383 5	5.560 6	1.021 9	1.914 4
45	0.356 8	0.626 0	0.157 1	0.222 7	3.397 8	5.405 1	1.019 1	1.861 3
50	0.332 3	0.659 3	0.158 1	0.234 5	3.384 0	5.224 4	1.003 8	1.796 5
55	0.374 8	0.693 9	0.163 2	0.246 6	3.293 7	4.997 1	0.970 7	1.719 4
60	0.398 0	0.728 2	0.166 9	0.258 5	3.113 3	4.739 0	0.897 7	1.621 0
65	0.352 3	0.659 0	0.146 1	0.261 7	2.886 7	4.486 4	0.826 6	1.493 2