文献类型：期刊文献

英文题名：Adaptive control for multi-agent systems with actuator fault via reinforcement learning and its application on multi-unmanned surface vehicle

作者：Bai, Weiwei[1,2];Zhang, Wenjun[1,2];Cao, Liang[3];Liu, Qiang[1]

机构：[1]Dalian Maritime Univ, Nav Coll, Dalian 116026, Peoples R China;[2]Dalian Key Lab Safety & Secur Technol Autonomous S, Dalian 116026, Peoples R China;[3]Guangdong Ocean Univ, Maritime Coll, Zhanjiang 524000, Peoples R China

年份：2023

卷号：280

外文期刊名：OCEAN ENGINEERING

收录：SCI-EXPANDED(收录号：WOS:000988841900001)、、EI(收录号：20231714005958)、Scopus(收录号：2-s2.0-85153306175)、WOS

基金：Acknowledgments This work was partially supported in part by the Central Guid-ance on Local Science and Technology Development Fund of Liaoning Province (Grant No. 2023JH6/100100055) , in part by the National Nat-ural Science Foundation of China (Grant Nos. 52271360, 61903092) , the Fellowship of China Postdoctoral Science Foundation (Grant No. 2022T150096) , the Natural Science Foundation of Sichuan Province, China (Grant No. 2022NSFSC0891) , the Fundamental Research Funds for the Central Universities (Grant No. 3132023129) .

语种：英文

外文关键词：Actuator fault; Neural network; Multi-agent systems; Reinforcement learning; Multi-unmanned surface vehicle

外文摘要：In this paper, the adaptive cooperative control problem is studied for a class of second order multi -agent systems (MASs) with actuator fault via reinforcement learning (RL). The strategic utility function is approximated by the critic neural network (NN), and the uncertain dynamics in MASs are estimated by the action NN. The NN weight vectors are updated by employing the gradient descent strategy. Then, the distributed RL control strategy is developed to solve the consensus control design problem. In comparison with the existent RL control results, the actuator fault is taken into consideration in the controller design. The stability analysis is given based on the Lyapunov theory, and all signals in the closed-loop system are guaranteed to semi-globally uniformly ultimately bounded (SGUUB). Two simulation examples, including a multi-unmanned surface vehicle system, are presented to demonstrate the validation of this strategy.