{"title":"Timed Automata based provably correct robot control","authors":"A. Anier, J. Vain","doi":"10.1109/BEC.2010.5631008","DOIUrl":null,"url":null,"abstract":"This paper presents a feasibility study on the usage of Uppaal Timed Automata (UPTA) for deliberative level robotic control. The study is based on the Scrub Nurse Robot case-study. Our experience confirms that UPTA model based control enables the control loop to be defined and maintained during the robot operation autonomously with minimum human intervention. Specifically, in our robot architecture the control model is constructed automatically using unsupervised learning. Correctness of the model is verified on-the-fly against safety, reachability, and performance requirements. Finally, it is demonstrated that UPTA model based robot control, action planning and model updates have natural implementation based on existing model execution and conformance testing tool Uppaal Tron.","PeriodicalId":228594,"journal":{"name":"2010 12th Biennial Baltic Electronics Conference","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 12th Biennial Baltic Electronics Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BEC.2010.5631008","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
This paper presents a feasibility study on the usage of Uppaal Timed Automata (UPTA) for deliberative level robotic control. The study is based on the Scrub Nurse Robot case-study. Our experience confirms that UPTA model based control enables the control loop to be defined and maintained during the robot operation autonomously with minimum human intervention. Specifically, in our robot architecture the control model is constructed automatically using unsupervised learning. Correctness of the model is verified on-the-fly against safety, reachability, and performance requirements. Finally, it is demonstrated that UPTA model based robot control, action planning and model updates have natural implementation based on existing model execution and conformance testing tool Uppaal Tron.