{"title":"RFID-enabled localization system for mobile robot in the workshop","authors":"Haishu Ma, Zongzheng Ma, Lixia Li, Ya Gao","doi":"10.3233/rft-221511","DOIUrl":null,"url":null,"abstract":"The development of RFID enabled intelligent localization system in the workshop is of great importance for reducing the operation cost, increasing production efficiency and improving management capabilities. From the aspects of feature extraction of RF fingerprint and localization algorithm, the scheme of mobile target tracking based on the fusion of inertial navigation and fingerprinting is explored. The deep neural network is used to establish the nonlinear relationship between fingerprint and coordinates. After the initial position of the mobile robot is obtained, Kalman filter is used to fuse the data collected by IMU and wheel encoder. Experimental results show that the proposed method is feasible and be able to track the mobile robot accurately.","PeriodicalId":42288,"journal":{"name":"International Journal of RF Technologies-Research and Applications","volume":"15 1","pages":"0"},"PeriodicalIF":1.6000,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of RF Technologies-Research and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3233/rft-221511","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
The development of RFID enabled intelligent localization system in the workshop is of great importance for reducing the operation cost, increasing production efficiency and improving management capabilities. From the aspects of feature extraction of RF fingerprint and localization algorithm, the scheme of mobile target tracking based on the fusion of inertial navigation and fingerprinting is explored. The deep neural network is used to establish the nonlinear relationship between fingerprint and coordinates. After the initial position of the mobile robot is obtained, Kalman filter is used to fuse the data collected by IMU and wheel encoder. Experimental results show that the proposed method is feasible and be able to track the mobile robot accurately.