一种时变扰动下的无人车辆智能跟踪控制方法  

An Intelligent Tracking Control Method for Unmanned Vehicles with Time-varying Disturbances

作　　者：黄捷 黄捷[1,2] Huang Jie;Huang Jie(College of Electrical Engineering and Automation,Fuzhou University,Fuzhou 350108,China;5G+Industrial Internet Institute,Fuzhou University,Fuzhou 350108,China)

机构地区：[1]福州大学电气工程与自动化学院,福建福州350108 [2]福州大学5G+工业互联网研究院,福建福州350108

出　　处：《系统仿真学报》2025年第4期1063-1075,共13页Journal of System Simulation

基　　金：国家自然科学基金重大研究计划(92367109)。

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10.3311 N的外界干扰影响下,该方法的跟踪误差至少收敛到了0.0548 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%。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 10.3311 N,the tracking error converges to at least 0.0548 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%.

关 键 词：无人车辆 时变扰动 标识符网络 策略学习 跟踪控制 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]