{"title":"基于 DQN 的线路交叉区域多代理系统覆盖控制","authors":"Zuo Lei, Zhang Tengfei, Zhang Jinqi, Yan Maode","doi":"10.1049/cth2.12670","DOIUrl":null,"url":null,"abstract":"<p>Generally, the coverage control is studied in a convex region, in which the agent kinematics and the coverage environment both have strong limitations. It is difficult to directly apply these results to practical scenarios, such as the road environment or indoor environment. In this study, the multi-agent coverage control problems in a line intersection region is investigated, where the agents can only move along the given lines. To present the agents motion in this line intersection region, the moving directions and velocities of the agents are analyzed in the first part. Then, the coverage control model for the multi-agent system in line intersection region is presented, in which the cost function is provided based on the agent's minimum moving distance and the agent motions are used as the constraints. To solve this constrained coverage problem, the deep Q-learning network (DQN) is employed to find the optimal positions for each agent in the line intersection region. In final, numerical simulations are presented to validate the feasibility and effectiveness of proposed approaches.</p>","PeriodicalId":50382,"journal":{"name":"IET Control Theory and Applications","volume":"18 18","pages":"2777-2785"},"PeriodicalIF":2.2000,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cth2.12670","citationCount":"0","resultStr":"{\"title\":\"DQN based coverage control for multi-agent system in line intersection region\",\"authors\":\"Zuo Lei, Zhang Tengfei, Zhang Jinqi, Yan Maode\",\"doi\":\"10.1049/cth2.12670\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Generally, the coverage control is studied in a convex region, in which the agent kinematics and the coverage environment both have strong limitations. It is difficult to directly apply these results to practical scenarios, such as the road environment or indoor environment. In this study, the multi-agent coverage control problems in a line intersection region is investigated, where the agents can only move along the given lines. To present the agents motion in this line intersection region, the moving directions and velocities of the agents are analyzed in the first part. Then, the coverage control model for the multi-agent system in line intersection region is presented, in which the cost function is provided based on the agent's minimum moving distance and the agent motions are used as the constraints. To solve this constrained coverage problem, the deep Q-learning network (DQN) is employed to find the optimal positions for each agent in the line intersection region. In final, numerical simulations are presented to validate the feasibility and effectiveness of proposed approaches.</p>\",\"PeriodicalId\":50382,\"journal\":{\"name\":\"IET Control Theory and Applications\",\"volume\":\"18 18\",\"pages\":\"2777-2785\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-04-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cth2.12670\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IET Control Theory and Applications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/cth2.12670\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Control Theory and Applications","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cth2.12670","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
DQN based coverage control for multi-agent system in line intersection region
Generally, the coverage control is studied in a convex region, in which the agent kinematics and the coverage environment both have strong limitations. It is difficult to directly apply these results to practical scenarios, such as the road environment or indoor environment. In this study, the multi-agent coverage control problems in a line intersection region is investigated, where the agents can only move along the given lines. To present the agents motion in this line intersection region, the moving directions and velocities of the agents are analyzed in the first part. Then, the coverage control model for the multi-agent system in line intersection region is presented, in which the cost function is provided based on the agent's minimum moving distance and the agent motions are used as the constraints. To solve this constrained coverage problem, the deep Q-learning network (DQN) is employed to find the optimal positions for each agent in the line intersection region. In final, numerical simulations are presented to validate the feasibility and effectiveness of proposed approaches.
期刊介绍:
IET Control Theory & Applications is devoted to control systems in the broadest sense, covering new theoretical results and the applications of new and established control methods. Among the topics of interest are system modelling, identification and simulation, the analysis and design of control systems (including computer-aided design), and practical implementation. The scope encompasses technological, economic, physiological (biomedical) and other systems, including man-machine interfaces.
Most of the papers published deal with original work from industrial and government laboratories and universities, but subject reviews and tutorial expositions of current methods are welcomed. Correspondence discussing published papers is also welcomed.
Applications papers need not necessarily involve new theory. Papers which describe new realisations of established methods, or control techniques applied in a novel situation, or practical studies which compare various designs, would be of interest. Of particular value are theoretical papers which discuss the applicability of new work or applications which engender new theoretical applications.