Dawei Dai, Guolai Jiang, Junbo Xin, Xiang Gao, Liangliang Cui, Y. Ou, Guoqiang Fu
{"title":"Detecting, locating and crossing a door for a wide indoor surveillance robot","authors":"Dawei Dai, Guolai Jiang, Junbo Xin, Xiang Gao, Liangliang Cui, Y. Ou, Guoqiang Fu","doi":"10.1109/ROBIO.2013.6739719","DOIUrl":null,"url":null,"abstract":"Crossing a door is usually a necessary action for autonomous patrol of an indoor surveillance robot. However, it is difficult for a large robot to cross narrow doors. In this paper, a method for detecting, locating and crossing a door for an indoor surveillance robot with Kinect is presented. Firstly, doors are detected and located based on RGB-D data collected form Kinect. Then, the conversion between robot coordinate system and world coordinate system is discussed. Thirdly, a nonlinear adaptive controller is designed for the robot to move perpendicularly through the door. Experiments were taken on a surveillance robot and the results illustrated the effectiveness of this method.","PeriodicalId":434960,"journal":{"name":"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"17","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROBIO.2013.6739719","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 17
Abstract
Crossing a door is usually a necessary action for autonomous patrol of an indoor surveillance robot. However, it is difficult for a large robot to cross narrow doors. In this paper, a method for detecting, locating and crossing a door for an indoor surveillance robot with Kinect is presented. Firstly, doors are detected and located based on RGB-D data collected form Kinect. Then, the conversion between robot coordinate system and world coordinate system is discussed. Thirdly, a nonlinear adaptive controller is designed for the robot to move perpendicularly through the door. Experiments were taken on a surveillance robot and the results illustrated the effectiveness of this method.