A New Coordinated Control Strategy of Multi-Agent System for Pollution Neutralization

被引:0
|
作者
Gao, Yun [2 ]
Luo, Kai [1 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Dept Automat, Shanghai 200240, Peoples R China
[2] Huazhong Univ Sci & Technol, Sch Civil & Hydraul Engn, Wuhan 430074, Peoples R China
关键词
Voronoi tessellation; multi-agent system; pollution neutralization; coverage control; COVERAGE;
D O I
10.1109/CAC51589.2020.9327600
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper. the coordination control of a group of mobile agents equipped with omnidirectional spraying devices for pollution neutralization in a bounded area is studied. In order to effectively remove the toxic pollutants, a large number of cheap static sensors are deployed in the task area in advance to measure and reconstruct the concentration distribution of pollutants in real-time. Once the pollutant is detected, the agent will immediately clean up the pollutant. On the premise that the control strategy of the neutralizing agent spraying device is known in advance, this paper proposes a novel objective function to be optimized, which can represent the average spraying effect of the multi-agent system in the whole task area. In order to maximize the objective function, a coordinated control algorithm based on the distributed gradient is designed to drive the multi-agent system to asymptotically converge to the generalized center of mass in their respective Voronoi cells. Finally, this paper presents a group of simulation examples of tracking and clearing multiple pollution sources in the convex polygon area by a group of mobile agents.
引用
收藏
页码:7445 / 7450
页数:6
相关论文
共 50 条
  • [31] Consensus of a new multi-agent system via multi-task, multi-control mechanism and multi-consensus strategy
    Hu, Xiang
    Xiong, Yu
    Zhang, Zufan
    Li, Chuandong
    NEUROCOMPUTING, 2024, 584
  • [32] Coordinated Multi-Agent Imitation Learning
    Le, Hoang M.
    Yue, Yisong
    Carr, Peter
    Lucey, Patrick
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [33] A Constrained Coordination Control Strategy for Multi-Agent Systems
    Yang, Xiaowu
    Fan, Xiaoping
    Li, Ganrong
    2018 13TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2018, : 848 - 854
  • [34] Coordinated Control for Multi-Agent Systems Based on Networked Predictive Control Schemes
    Tan, Haoran
    Wu, Min
    Huang, Zhiwu
    PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, : 2530 - 2535
  • [35] Coordinated control of gas supply system in PEMFC based on multi-agent deep reinforcement learning
    Li, Jiawen
    Yu, Tao
    Yang, Bo
    INTERNATIONAL JOURNAL OF HYDROGEN ENERGY, 2021, 46 (68) : 33899 - 33914
  • [36] Coordinated look-ahead control of multiple CSPS system by multi-agent reinforcement learning
    Tang H.
    Wan H.-F.
    Han J.-H.
    Zhou L.
    Zidonghua Xuebao/ Acta Automatica Sinica, 2010, 36 (02): : 289 - 296
  • [37] A New Coordinated Path-Following Control for Second-Order Multi-Agent Systems
    Zuo, Zongyu
    2014 IEEE 53RD ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2014, : 3005 - 3010
  • [38] Decomposing Temporal Equilibrium Strategy for Coordinated Distributed Multi-Agent Reinforcement Learning
    Zhu, Chenyang
    Si, Wen
    Zhu, Jinyu
    Jiang, Zhihao
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 16, 2024, : 17618 - 17627
  • [39] Risk avoiding strategy in multi-agent trading system
    Korczak, Jerzy
    Hernes, Marcin
    Bac, Maciej
    2013 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS), 2013, : 1131 - 1138
  • [40] Dynamic Arterial Coordinated Control Based on Multi-agent Reinforcement Learning
    Fang, Liangliang
    Zhang, Weibin
    PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 2716 - 2721