一种时变扰动下的无人车辆智能跟踪控制方法

doi:10.16182/j.issn1004731x.joss.23-1494

摘要/Abstract

摘要：

针对具有有界时变干扰的无人车辆跟踪控制问题，提出了一种策略迭代智能跟踪控制方法。通过设计自适应干扰消解器对外界干扰进行补偿，确保了哈密顿-雅克比-贝尔曼(Hamilton-Jacobi-Bellman，HJB)方程的有效性；通过设计标识符网络对未知车辆动力学进行估计，并利用重构的标识符跟踪误差推导出全新的HJB方程；借助演员-评论家网络，在线获得标识符估计状态下的无人车辆最优跟踪控制策略。基于李雅普诺夫理论，证明了标识符跟踪误差、标识符近似误差、神经网络权值误差均为半全局最终一致有界，无人车辆可以达到理想的跟踪性能。仿真结果表明：在上界为10.331 1 N的外界干扰影响下，该方法的跟踪误差至少收敛到了0.054 8 m，具有良好的抗干扰性能，与滑模控制方法相比，跟踪精度提高了40%，控制代价减少了22%。

关键词: 无人车辆, 时变扰动, 标识符网络, 策略学习, 跟踪控制

Abstract:

An intelligent policy iteration tracking control method is proposed for the tracking control problem with bounded time-varying disturbances. An adaptive disturbance compensator is designed to counteract the bounded disturbance and guarantee the validity of the Hamilton-Jacobi-Bellman (HJB) equation. An identifier network is proposed to estimate the unknown vehicle dynamics, and a new HJB equation is derived using the reconstructed identifier tracking error. An online optimal tracking control strategy for unmanned vehicles is obtained in the state of identifier estimation with the assistance of actor-critic network. Based on Lyapunov theory, it is demonstrated that the identifier tracking error, identifier approximation error and neural network weight errors are all semi-globally uniformly ultimately bounded, and the unmanned vehicle can achieve ideal tracking performance. Simulation results indicate that with a disturbance upper-bounded by 10.331 1 N, the tracking error converges to at least 0.054 8 m which exhibits better anti-interference performance. Compared with sliding mode control, tracking accuracy is improved by 40% and control cost is reduced by 22%.

Key words: unmanned vehicles, time-varying disturbance, identifier network, strategy learning, tracking control

中图分类号:

TP391.9

黄捷,黄捷 . 一种时变扰动下的无人车辆智能跟踪控制方法[J]. 系统仿真学报, 2025, 37(4): 1063-1075.

Huang Jie,Huang Jie . An Intelligent Tracking Control Method for Unmanned Vehicles with Time-varying Disturbances[J]. Journal of System Simulation, 2025, 37(4): 1063-1075.

图/表 12

图1

图2

表1

无人车辆模型参数设置

参数	数值	参数	数值
$M$ /kg	6	$I w$ /(kg·m²)	0.094 5
$B$ /m	0.05	$a$ /(N/V)	0.087
$l a$ /m	0.11	$b$ /(kg/s)	11.4
$l b$ /m	0.18	$υ f x = υ f y$ /(m/s)	0.15

表1

图3

图4

图5

图6

图7

图8

图9

图10

表2

参考文献 27

1	张国辉, 王璇, 张雅楠, 等. 实际环境中多无人车协同路径规划模型研究[J]. 系统仿真学报, 2023, 35(2): 408-422.
	Zhang Guohui, Wang Xuan, Zhang Yanan, et al. Research on Cooperative Path Planning Model of Multiple Unmanned Vehicles in Real Environment[J]. Journal of System Simulation, 2023, 35(2): 408-422.
2	Kakkar S, Minor M A. Fast and Reliable Motion Model for Articulated Wheeled Mobile Robots on Extremely Rough and Rocky Terrains[J]. IEEE Robotics and Automation Letters, 2019, 4(3): 2252-2259.
3	Ren Chao, Li Xiaohan, Yang Xuebo, et al. Extended State Observer-based Sliding Mode Control of an Omnidirectional Mobile Robot with Friction Compensation[J]. IEEE Transactions on Industrial Electronics, 2019, 66(12): 9480-9489.
4	Li Jing, Wu Qingbin, Wang Junzheng, et al. Autonomous Tracking Control for Four-wheel Independent Steering Robot Based on Improved Pure Pursuit[J]. Journal of Beijing Institute of Technology, 2020, 29(4): 466-473.
5	张华强, 王国栋, 吕云飞, 等. 基于改进纯追踪模型的农机路径跟踪算法研究[J]. 农业机械学报, 2020, 51(9): 18-25.
	Zhang Huaqiqng, Wang Guodong, Yunfei Lü, et al. Agricultural Machinery Automatic Navigation Control System Based on Improved Pure Tracking Model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(9): 18-25.
6	邓海鹏, 麻斌, 赵海光, 等. 自主驾驶车辆紧急避障的路径规划与轨迹跟踪控制[J]. 兵工学报, 2020, 41(3): 585-594.
	Deng Haipeng, Ma Bin, Zhao Haiguang, et al. Path Planning and Tracking Control of Autonomous Vehicle for Obstacle Avoidance[J]. Acta Armamentarii, 2020, 41(3): 585-594.
7	Kanchwala H, Ícaro Bezerra Viana, Ceccoti M, et al. Model Predictive Tracking Controller for a High Fidelity Vehicle Dynamics Model[C]//2019 IEEE Intelligent Transportation Systems Conference (ITSC). Piscataway: IEEE, 2019: 1496-1503.
8	梁忠超, 张欢, 赵晶, 等. 基于自适应MPC的无人驾驶车辆轨迹跟踪控制[J]. 东北大学学报(自然科学版), 2020, 41(6): 835-840.
	Liang Zhongchao, Zhang Huan, Zhao Jing, et al. Trajectory Tracking Control of Unmanned Vehicles Based on Adaptive MPC[J]. Journal of Northeastern University(Natural Science), 2020, 41(6): 835-840.
9	陈亮, 秦兆博, 孔伟伟, 等. 基于最优前轮侧偏力的智能汽车LQR横向控制[J]. 清华大学学报(自然科学版), 2021, 61(9): 906-912.
	Chen Liang, Qin Zhaobo, Kong Weiwei, et al. Lateral Control Using LQR for Intelligent Vehicles Based on the Optimal Front-tire Lateral Force[J]. Journal of Tsinghua University(Science and Technology), 2021, 61(9): 906-912.
10	Wen Guoxing, Chen C L, Ge Shuzhi, et al. Optimized Adaptive Nonlinear Tracking Control Using Actor-critic Reinforcement Learning Strategy[J]. IEEE Transactions on Industrial Informatics, 2019, 15(9): 4969-4977.
11	Peng Zhinan, Luo Rui, Hu Jiangping, et al. Optimal Tracking Control of Nonlinear Multiagent Systems Using Internal Reinforce Q-learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(8): 4043-4055.
12	谭伟, 刘景升, 祖晖, 等. 参数不确定和扰动下智能汽车路径跟踪控制[J]. 浙江大学学报(工学版), 2023, 57(4): 702-711.
	Tan Wei, Liu Jingsheng, Zu Hui, et al. Intelligent Vehicle Path Tracking Control Under Parametric Uncertainties and External Disturbances[J]. Journal of Zhejiang University(Engineering Science), 2023, 57(4): 702-711.
13	Modares H, Lewis F L. Linear Quadratic Tracking Control of Partially-unknown Continuous-time Systems Using Reinforcement Learning[J]. IEEE Transactions on Automatic Control, 2014, 59(11): 3051-3056.
14	Gao Weinan, Jiang Zhongping. Learning-based Adaptive Optimal Tracking Control of Strict-feedback Nonlinear Systems[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(6): 2614-2624.
15	Chen Ci, Modares H, Xie Kan, et al. Reinforcement Learning-based Adaptive Optimal Exponential Tracking Control of Linear Systems with Unknown Dynamics[J]. IEEE Transactions on Automatic Control, 2019, 64(11): 4423-4438.
16	Liu Derong, Xue Shan, Zhao Bo, et al. Adaptive Dynamic Programming for Control: A Survey and Recent Advances[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 51(1): 142-160.
17	Luo Rui, Peng Zhinan, Hu Jiangping, et al. Adaptive Optimal Control of Affine Nonlinear Systems via Identifier-critic Neural Network Approximation with Relaxed PE Conditions[J]. Neural Networks, 2023, 167: 588-600.
18	Jiang Yi, Gao Weinan, Wu Jin, et al. Reinforcement Learning and Cooperative H_∞ Output Regulation of Linear Continuous-time Multi-agent Systems[J]. Automatica, 2023, 148: 110768.
19	Zhao Jianguo, Yang Chunyu, Gao Weinan, et al. Linear Quadratic Tracking Control of Unknown Systems: A Two-phase Reinforcement Learning Method[J]. Automatica, 2023, 148: 110761.
20	Yang Yunjie, Wan Yan, Zhu Jihong, et al. H_∞Tracking Control for Linear Discrete-time Systems: Model-free Q-learning Designs[J]. IEEE Control Systems Letters, 2021, 5(1): 175-180.
21	于欣波, 贺威, 薛程谦, 等. 基于扰动观测器的机器人自适应神经网络跟踪控制研究[J]. 自动化学报, 2019, 45(7): 1307-1324.
	Yu Xinbo, He Wei, Xue Chengqian, et al. Disturbance Observer-based Adaptive Neural Network Tracking Control for Robots[J]. Acta Automatica Sinica, 2019, 45(7): 1307-1324.
22	Wang Hongbo, Hu Chenglei, Zhou Juntao, et al. Path Tracking Control of an Autonomous Vehicle with Model-free Adaptive Dynamic Programming and RBF Neural Network Disturbance Compensation[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2022, 236(5): 825-841.
23	Ma Qingwen, Zhang Xinglong, Xu Xin, et al. Self-learning Sliding Mode Control Based on Adaptive Dynamic Programming for Nonholonomic Mobile Robots[J]. ISA Transactions, 2023, 142: 136-147.
24	Alakshendra Veer, Chiddarwar Shital S. A Robust Adaptive Control of Mecanum Wheel Mobile Robot: Simulation and Experimental Validation[C]//2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway: IEEE, 2016: 5606-5611.
25	Wen Guoxing, Chen C L, Li Bin. Optimized Formation Control Using Simplified Reinforcement Learning for a Class of Multiagent Systems with Unknown Dynamics[J]. IEEE Transactions on Industrial Electronics, 2020, 67(9): 7879-7888.
26	吴克坚, 刘烁, 徐清华, 等. 应用Cauchy-schwarz不等式证明积分不等式举例[J]. 高等数学研究, 2021, 24(2): 13-15, 54.
	Wu Kejian, Liu Shuo, Xu Qinghua, et al. Using Cauchy-schwarz Inequality to Prove Integral Inequalities[J]. Studies in College Mathematics, 2021, 24(2): 13-15, 54.
27	王永军, 郑丽. 关于Young不等式和Schwarz不等式的证明[J]. 数学学习与研究, 2020(26): 145-147.

指标	本文方法	滑模控制	RL
代价函数平均值	717.396 1	924.490 7	1 802.500 0
跟踪误差平均值/m	0.033 0	0.054 7	3.467 1
代价函数最大值	1 432.7	16 781.0	3 918.1
跟踪误差最大值/m	0.054 8	0.075 8	6.867 8

[1]	程磊, 王好友, 陈新节. 基于特征建模的全向车辆自适应跟踪控制研究[J]. 系统仿真学报, 2024, 36(10): 2277-2287.
[2]	郭明皓, 姬鹏, 黄海威. 基于改进人工势场法的无人车路径规划与跟踪控制[J]. 系统仿真学报, 2024, 36(10): 2423-2434.
[3]	路宏广, 赵树恩. 基于鲁棒模型预测的智能汽车轨迹跟踪控制研究[J]. 系统仿真学报, 2022, 34(1): 153-162.
[4]	吴小龙, 夏甫根, 陈静, 徐佳. 基于能量最优的无人驾驶汽车路径跟踪控制[J]. 系统仿真学报, 2022, 34(1): 163-169.
[5]	冷姚, 赵树恩. 智能车辆横向轨迹跟踪的显式模型预测控制方法[J]. 系统仿真学报, 2021, 33(5): 1177-1187.
[6]	马立新, 吕梦圆. 氨法脱硫自适应实时跟踪控制系统[J]. 系统仿真学报, 2018, 30(5): 1838-1843.
[7]	范云生, 孙晓界, 王国峰, 郭晨. 一种无人水面艇自主动态避碰跟踪控制方法[J]. 系统仿真学报, 2018, 30(10): 3781-3788.
[8]	马飞, 吴云洁, 程明智. 基于自抗扰解耦的BTT导弹非奇异终端滑模控制[J]. 系统仿真学报, 2017, 29(9): 2175-2181.
[9]	王允建, 刘晓云, 张荣志, 薛娜娜. 混合有源电力滤波器的状态反馈控制[J]. 系统仿真学报, 2017, 29(6): 1284-1289.