Reinforcement learning-based optimal trajectory tracking control of surface vessels under input saturations

被引:10
作者
Wei, Ziping [1 ]
Du, Jialu [1 ,2 ]
机构
[1] Dalian Maritime Univ, Sch Marine Elect Engn, Dalian, Peoples R China
[2] Dalian Maritime Univ, Sch Marine Engn, Dalian 116026, Liaoning, Peoples R China
基金
中国国家自然科学基金;
关键词
input saturations; reinforcement learning; surface vessels; trajectory tracking; unknown dynamics; WAVE ENERGY CONVERTERS; ADAPTIVE NN CONTROL; NONLINEAR-SYSTEMS; CONTROL ALGORITHM; UNKNOWN DYNAMICS; CONTROL DESIGN; ROBUST-CONTROL;
D O I
10.1002/rnc.6597
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper develops a reinforcement learning (RL)-based optimal trajectory tracking control scheme of surface vessels with unknown dynamics, unknown disturbances, and input saturations of surface vessels. The control scheme is designed by combining the optimal control theory, adaptive neural networks, and the RL method in a unified actor-critic NN framework. A hyperbolic-type penalty function of the control input is designed so as to deal with the input saturations of surface vessels. An actor-critic NN-based RL mechanism is established to learn the optimal trajectory tracking control law without the knowledge of the surface vessel dynamics and disturbances, where NN weights are tuned online on the basis of devised tuning laws. Theoretical analysis and simulation results prove that the proposed RL-based optimal trajectory tracking control scheme can ensure surface vessels track the desired trajectory, while guaranteeing the boundedness of all signals in the surface vessel optimal trajectory tracking closed-loop control system.
引用
收藏
页码:3807 / 3825
页数:19
相关论文
共 50 条
[41]   Lifelong Learning-Based Optimal Trajectory Tracking Control of Constrained Nonlinear Affine Systems Using Deep Neural Networks [J].
Ganie, Irfan ;
Jagannathan, Sarangapani .
IEEE TRANSACTIONS ON CYBERNETICS, 2024, 54 (12) :7133-7146
[42]   Adaptive Output Feedback Tracking Control of Surface Vessels Under Input Saturation [J].
Li, Jian ;
Du, Jialu ;
Hu, Xin .
PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, :1288-1293
[43]   Off-policy integral reinforcement learning-based optimal tracking control for a class of nonzero-sum game systems with unknown dynamics [J].
Zhao, Jin-Gang ;
Chen, Fang-Fang .
OPTIMAL CONTROL APPLICATIONS & METHODS, 2022, 43 (06) :1623-1644
[44]   USV Trajectory Tracking Control Based on Receding Horizon Reinforcement Learning [J].
Wen, Yinghan ;
Chen, Yuepeng ;
Guo, Xuan .
SENSORS, 2024, 24 (09)
[45]   Trajectory Tracking Control for Underactuated Surface Vessels Based on Nonlinear Model Predictive Control [J].
Liu, Chenguang ;
Zheng, Huarong ;
Negenborn, Rudy R. ;
Chu, Xiumin ;
Wang, Le .
COMPUTATIONAL LOGISTICS (ICCL 2015), 2015, 9335 :166-180
[46]   Fixed-time sliding mode trajectory tracking control for marine surface vessels under mismatched conditions and input saturation [J].
Zhang, Jingqi ;
Yu, Shuanghe ;
Yan, Yan ;
Zhao, Ying .
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2024, 34 (09) :6142-6164
[47]   Reinforcement learning-based MPC for tracking control of 4WID4WIS [J].
Lin, Wenlong ;
Wang, Ping ;
Wu, Yu-Yao ;
Liu, Wanquan ;
Sun, Hui-Jie .
2023 2ND CONFERENCE ON FULLY ACTUATED SYSTEM THEORY AND APPLICATIONS, CFASTA, 2023, :839-844
[48]   Reinforcement learning based climb trajectory optimal control of ramjet aircraft [J].
Zhou G. ;
Yan D. ;
Liang Z. .
Zhongguo Guanxing Jishu Xuebao/Journal of Chinese Inertial Technology, 2022, 30 (01) :135-140
[49]   Reinforcement learning-based saturated adaptive robust output-feedback funnel control of surface vessels in different weather conditions [J].
Elhaki, Omid ;
Shojaei, Khoshnam ;
Moghtaderizadeh, Iman ;
Sajadian, Seyed Jalal .
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2023, 360 (18) :14237-14260
[50]   Reinforcement learning-based intelligent tracking control for wheeled mobile robot [J].
Nguyen Tan Luy ;
Nguyen Thien Thanh ;
Hoang Minh Tri .
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2014, 36 (07) :868-877