基于直线和单特征点的移动机器人视觉推算定位法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1493 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
韩立伟, 徐德. 基于直线和单特征点的移动机器人视觉推算定位法[J]. 机器人, 2008, 30(1): 79-84,90.. HAN Li-wei, XU De. A Visual Dead Reckoning Positioning Method Based on Lines and Single Feature Point for Mobile Robot. ROBOT, 2008, 30(1): 79-84,90..

摘要提出了一种基于直线和单特征点的视觉推算定位方法．将摄像机固定安装在移动机器人上，并使摄像机的方向垂直于天花板．提取天花板图像中的两条相交直线及其交点作为特征，利用直线的方向估计机器人的方位，再结合相交点的像素坐标变化量推算出机器人的位置．机器人运动过程中，用作特征的交点接近图像边缘时，更换新的交点作为特征点．室内定位实验结果验证了该方法的有效性．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	韩立伟
	徐德

关键词 ：视觉定位, 推算定位, 特征提取, 移动机器人

Abstract：A new visual dead reckoning positioning method is presented for mobile robot,which is based on lines and single feature points.A camera,whose optical direction is adjusted to be perpendicular to the ceiling,is fixed on the mobile robot.Two intersecting lines in the images of the ceiling and their intersection are extracted as features,the orientation of the mobile robot is estimated based on the orientation of the lines,and then the position of the mobile robot is computed according to the variations of the image coordinates of the intersection pixels.When the mobile robot moves,the intersection may be nearing to the margin of the image,and at this time a new intersection will be selected to replace the old one as the new feature point.The results of positioning experiments in indoor environment verify the effectiveness of the proposed method.

Key words： visual positioning dead reckoning feature extraction mobile robot

收稿日期: 2007-06-22

TP24

基金资助:国家自然科学基金资助项目（60672039）

作者简介: 韩立伟（1972- ），男，博士生．研究领域：机器人视觉控制．
徐德（1965- ），男，博士，研究员．研究领域：机器人视觉控制，智能控制．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2008/V30/I1/79

[1] 厉茂海,洪炳镕,罗荣华,等.基于单目视觉的移动机器人全局定位[J].机器人,2007,29(2):140-144,178.
[2] Durrant-Whyte H,Bell E,Avery P.The design of a radar-based navigation system for large outdoor vehicles[A].Proceedings of the IEEE International Conference on Robotics and Automation[C].Piscataway,NJ,USA:IEEE,1995.764-769.
[3] Yu J X,Cai Z X,Duan Z H,et al.Design of dead reckoning system for mobile robot[J].Journal of Central South University of Technology (English Edition),2006,13(5):542-547.
[4] Murata S,Hirose T.Onboard locating system using real-time image processing for a self-navigating vehicle[J].IEEE Transactions on Industrial Electronics,1993,40(1):145-154.

[5] Moon I H,Miura J,Yanagi Y,et al.Planning of vision-based navigation for a mobile robot under uncertainty[A].Proceedings of the IEEE International Conference on Intelligent Robots and Systems[C].Piscataway,NJ,USA:IEEE,1997.1202-1207.
[6] Makela H,Koskinen K.Navigation of outdoor mobile robots using dead reckoning and visually detected landmarks[A].Proceedings of the 5th International Conference on Advanced Robotics[C].Piscataway,NJ,USA:IEEE,1991.1051-1056.
[7] Leonard J J,Durrant-Whyte H F.Mobile robot localization by tracking geometric beacons[J].IEEE Transactions on Robotics and Automation,1991,7(3):376 -382.

[8] Chenavier F,Crowley J L.Position estimation for a mobile robot using vision and odometry[A].Proceedings of the IEEE International Conference on Robotics and Automation[C].Piscataway,NJ,USA:IEEE,1992.2588-2593.
[9] 徐德,涂志国,谭民.基于单应性矩阵的室内移动机器人视觉定位研究[J].自动化学报,2005,31(3):464-469.
[10] 潘良晨,陈卫东.室内移动机器人的视觉定位方法研究[J].机器人,2006,28(5):504-509.
[11] 尚文,马旭东,戴先中.基于视觉特征的移动机器人Monte Carlo 定位方法[J].制造业自动化,2004,26(11):35-39.
[12] Asensio J R,Montiel J M M,Montano L.Goal directed reactive robot navigation with relocation using laser and vision[A].Proceedings of the IEEE International Conference on Robotics and Automation[C].Piscataway,NJ,USA:IEEE,1999.2905-2910.
[13] Xu D,Li Y F,Tan M.A visual positioning method based on relative orientation detection for mobile robots[A].Proceedings of the IEEE International Conference on Intelligent Robots and Systems[C].Piscataway,NJ,USA:IEEE,2006.1243-1248.