{"title":"Fuzzy control of a mobile robot for the push-a-box operation","authors":"Y. Okawa, J. Aoki","doi":"10.1109/TAI.1992.246358","DOIUrl":null,"url":null,"abstract":"As an example of the intelligent actions of robots, the situation in which a mobile robot pushes a square box is considered. The operation of pushing is unstable, in that once a small disturbance forces the system to abandon the stable position, the pushing operation itself makes the deviation wider. The state space is divided into 25 subregions, in each of which a control rule is specified manually. To avoid crisp division of the control space, fuzzy control logic is used. Various possibilities are summed up by membership functions. Three membership functions, one of which is made active according to the distance from the goal being near, medium, or far, are prepared. A mobile robot was built and experiments were performed.<<ETX>>","PeriodicalId":265283,"journal":{"name":"Proceedings Fourth International Conference on Tools with Artificial Intelligence TAI '92","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1992-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Fourth International Conference on Tools with Artificial Intelligence TAI '92","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TAI.1992.246358","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
As an example of the intelligent actions of robots, the situation in which a mobile robot pushes a square box is considered. The operation of pushing is unstable, in that once a small disturbance forces the system to abandon the stable position, the pushing operation itself makes the deviation wider. The state space is divided into 25 subregions, in each of which a control rule is specified manually. To avoid crisp division of the control space, fuzzy control logic is used. Various possibilities are summed up by membership functions. Three membership functions, one of which is made active according to the distance from the goal being near, medium, or far, are prepared. A mobile robot was built and experiments were performed.<>