文献类型：期刊文献

英文题名：Reinforcement learning control for USVs using prescribed performance sliding surfaces and an event-triggered strategy

作者：Liu, Haitao[1,2,3];Chen, Yonggang[1,2,3];Tian, Xuehong[1,2,3];Mai, Qingqun[1,2,3]

机构：[1]Guangdong Ocean Univ, Sch Mech Engn, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, Shenzhen Inst, Shenzhen 518120, Peoples R China;[3]Guangdong Engn Technol Res Ctr Ocean Equipment & M, Zhanjiang 524088, Peoples R China

年份：2024

卷号：306

外文期刊名：OCEAN ENGINEERING

收录：SCI-EXPANDED(收录号：WOS:001241425000001)、、EI(收录号：20242016087786)、Scopus(收录号：2-s2.0-85192824208)、WOS

基金：This work was supported by the Key Project of the Key Project of the Department of Education of Guangdong Province [grant number 2021ZDZX1041, and 2023ZDZX1005] , the Shenzhen Science and Technology Program [grant number JCYJ20220530162014033] , the National Natural Science Foundation of China [grant number 62171143] , the Science and Technology Planning Project of Zhanjiang City [grant numbers 2021A05023 and 2021E05012] , and the Guang- dong Basic and Applied Basic Research Foundation [grant number 2024A1515011345] .

语种：英文

外文关键词：Underactuated surface vessel; Prescribed performance; Reinforcement learning; Optimal control; Switching threshold event-triggered strategy

外文摘要：An adaptive reinforcement learning (RL) optimal control method for trajectory tracking control of underactuated surface vessels (USVs) is proposed in this paper based on prescribed performance sliding surfaces and a switching threshold event-triggered strategy. First, a neural network (NN) is used to approximate the model's uncertainties and external unknown disturbances, and an actor-critic NN structure in the RL is developed to solve the Hamilton-Jacobi-Bellman (HJB) equations in optimal control. Second, a new cost function is designed by the new error variables, which are made of prescribed performance sliding surfaces that further reduce the size of the cost function in optimal control. Third, a switching threshold event-triggered strategy is introduced to balance the control performance and network constraints by reducing the update frequency of the controller. Then, the closed-loop system's stability is proven by the Lyapunov stability theorem. Finally, the effectiveness of the controller is verified via simulation experiments.