{"title":"触觉感应垫:形状识别","authors":"D. Famularo, P. Muraca","doi":"10.1109/ISIC.1995.525080","DOIUrl":null,"url":null,"abstract":"Most robot tactile sensing research has focused on object shape recognition with tactile sensors. In this paper we examine the model of a tactile pad sensor, assumed to be a finite dimension medium. The model of the tactile pad sensor is obtained using an integral relation between the boundary conditions and the stress tensor. A set of stress sensors is allocated in the tactile pad, the model is discretized and a direct relation between the parameters of the shape to be recognized and the measured stress is obtained. Due to the ill-posedness of the problem, classical least squares estimation and regularized estimation are examined. Numerical simulations in order to evaluate the inversion technique with different shapes of the object, are presented.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Tactile sensor pad: shape recognition\",\"authors\":\"D. Famularo, P. Muraca\",\"doi\":\"10.1109/ISIC.1995.525080\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Most robot tactile sensing research has focused on object shape recognition with tactile sensors. In this paper we examine the model of a tactile pad sensor, assumed to be a finite dimension medium. The model of the tactile pad sensor is obtained using an integral relation between the boundary conditions and the stress tensor. A set of stress sensors is allocated in the tactile pad, the model is discretized and a direct relation between the parameters of the shape to be recognized and the measured stress is obtained. Due to the ill-posedness of the problem, classical least squares estimation and regularized estimation are examined. Numerical simulations in order to evaluate the inversion technique with different shapes of the object, are presented.\",\"PeriodicalId\":219623,\"journal\":{\"name\":\"Proceedings of Tenth International Symposium on Intelligent Control\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1995-08-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of Tenth International Symposium on Intelligent Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISIC.1995.525080\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of Tenth International Symposium on Intelligent Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIC.1995.525080","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Most robot tactile sensing research has focused on object shape recognition with tactile sensors. In this paper we examine the model of a tactile pad sensor, assumed to be a finite dimension medium. The model of the tactile pad sensor is obtained using an integral relation between the boundary conditions and the stress tensor. A set of stress sensors is allocated in the tactile pad, the model is discretized and a direct relation between the parameters of the shape to be recognized and the measured stress is obtained. Due to the ill-posedness of the problem, classical least squares estimation and regularized estimation are examined. Numerical simulations in order to evaluate the inversion technique with different shapes of the object, are presented.