Prescribed-time formation tracking in multi-agent systems via reinforcement learning-based hybrid impulsive control with time delays

被引:0
作者
Liang, Zhanlue
Gu, Yanlin [1 ]
Li, Ping [2 ]
Tao, Yiwen [3 ]
机构
[1] Northwestern Polytech Univ, Sch Elect & Informat, Xian, Peoples R China
[2] Southwest Minzu Univ, Sch Math, Chengdu 610041, Sichuan, Peoples R China
[3] Zhengzhou Univ, Sch Math & Stat, Zhengzhou 450001, Henan, Peoples R China
关键词
Prescribed-time formation tracking; Hybrid impulsive control; Multi-agent system; Reinforcement learning; Time delays; Average impulsive interval; TO-STATE STABILITY; FLOCKING CONTROL; STABILIZATION; CONSENSUS;
D O I
10.1016/j.eswa.2025.126723
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper addresses the prescribed-time formation stabilization in nonlinear multi-agent systems using a novel reinforcement learning-based hybrid impulsive control framework that incorporates delayed control impulses. The approach leverages Lyapunov functionals, impulsive comparison theory, average impulsive interval methods, and graph theory to derive sufficient conditions for achieving prescribed-time formation stabilization. These conditions are formulated in terms of continuous and impulsive feedback gains, time delay durations, and average impulsive interval lengths. Importantly, the inclusion of stabilizing control impulses counteracts the destabilizing effects of continuous dynamics. Additionally, deep reinforcement learning techniques are employed to optimize the impulsive control sequence, aiming to maximize rewards derived from the control objectives and system states. Numerical simulation examples are presented to demonstrate the effectiveness and validity of the proposed analytical results, providing comparative assessments of overall control performance.
引用
收藏
页数:16
相关论文
共 59 条
[1]   Decentralized Ergodic Control: Distribution-Driven Sensing and Exploration for Multiagent Systems [J].
Abraham, Ian ;
Murphey, Todd D. .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04) :2987-2994
[2]   Nezha-Mini: Design and Locomotion of a Miniature Low-Cost Hybrid Aerial Underwater Vehicle [J].
Bi, Yuanbo ;
Jin, Yufei ;
Lyu, Chenxin ;
Zeng, Zheng ;
Lian, Lian .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (03) :6669-6676
[3]   Cloud-based predictive formation control of networked multi-agent system and its application to air bearing spacecraft simulators✩ [J].
Cao, Lei ;
Liu, Guo-Ping ;
Zhang, Da -Wei .
ISA TRANSACTIONS, 2023, 138 :696-704
[4]   Distributed learning and cooperative control for multi-agent systems [J].
Choi, Jongeun ;
Oh, Songhwai ;
Horowitz, Roberto .
AUTOMATICA, 2009, 45 (12) :2802-2814
[5]   A Survey on Aerial Swarm Robotics [J].
Chung, Soon-Jo ;
Paranjape, Aditya Avinash ;
Dames, Philip ;
Shen, Shaojie ;
Kumar, Vijay .
IEEE TRANSACTIONS ON ROBOTICS, 2018, 34 (04) :837-855
[6]   Prescribed-time formation tracking of second-order multi-agent networks with directed graphs [J].
Ding, Teng-Fei ;
Ge, Ming-Feng ;
Xiong, Caihua ;
Liu, Zhi-Wei ;
Ling, Guang .
AUTOMATICA, 2023, 152
[7]   Time-Varying Formation Tracking for Second-Order Multi-Agent Systems Subjected to Switching Topologies With Application to Quadrotor Formation Flying [J].
Dong, Xiwang ;
Zhou, Yan ;
Ren, Zhang ;
Zhong, Yisheng .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2017, 64 (06) :5014-5024
[8]   Time-Varying Formation Control for Unmanned Aerial Vehicles: Theories and Applications [J].
Dong, Xiwang ;
Yu, Bocheng ;
Shi, Zongying ;
Zhong, Yisheng .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2015, 23 (01) :340-348
[9]  
Drew D. S., 2021, Curr. Robot. Rep., V2, P189, DOI [DOI 10.1007/S43154-021-00048-3, 10.1007/s43154-021-00048-3]
[10]   Safe deep reinforcement learning-based adaptive control for USV interception mission [J].
Du, Bin ;
Lin, Bin ;
Zhang, Chenming ;
Dong, Botao ;
Zhang, Weidong .
OCEAN ENGINEERING, 2022, 246