基于聚类的迭代双向最近点机器人位姿估计

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1471 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
徐玉华, 张崇巍, 徐海琴. 基于聚类的迭代双向最近点机器人位姿估计[J]. 机器人, 2010, 32(3): 352-357.. XU Yuhua, ZHANG Chongwei, XU Haiqin. An Iterative Dual Closest Point Method for Robot’s Pose Estimation Based on Clustering. ROBOT, 2010, 32(3): 352-357..

摘要针对迭代最近点(ICP)算法在存在严重遮挡的情况下容易陷入局部最小值的问题，对最近点规则(CP)进行了修改，提出双向最近点规则(DCP)．DCP规则包含两次CP规则对应，使计算量增加了一倍．为了降低算法的复杂度，继而提出基于聚类的迭代双向最近点(IDCP BoC)算法．IDCP BoC对扫描数据进行聚类，在聚类的基础上进行数据精简．在相邻两次迭代的残差之差小于某个阈值之前，用精简数据进行迭代以提高计算速度，之后再改用非精简数据以保证精度．实验结果表明，IDCP BoC算法能够有效避免陷入局部最小值的问题且其实时性也是可接受的．

	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
	徐玉华
	张崇巍
	徐海琴

关键词 ：移动机器人, 激光测距仪, 位姿估计, 迭代最近点, 聚类

Abstract：To overcome the problem of local extrema existing in iterative closest point(ICP) algorithm when severe occlusions occur,the closest point(CP) rule is modified and dual closest point(DCP) rule is proposed.DCP rule contains twice CP correspondences so that computation complexity is doubled.To decrease the computation complexity,iterative dual closest point based on clustering(IDCP BoC) is proposed.Scan range points are divided into clusters and then a procedure of data reduction is conducted.The reduced data set is used for iterative computation before the error of two consecutive iterations’ residual errors is less than a preset threshold to speed up the algorithm,and the data set without reduction is used after that to guarantee the accuracy.Experimental results show that IDCP BoC can avoid the problem of local extrema effectively and its real-time performance is also acceptable.

Key words： mobile robot laser range finder pose estimation ICP(iterative closest point) clustering

收稿日期: 2009-07-06 录用日期: 2009-12-16

TP242.6

基金资助:先进数控技术江苏省高校重点建设实验室基金资助项目（KXJ07127）

通讯作者: 徐玉华 E-mail: robot802@gmail.com

作者简介: 徐玉华(1985- )，男，博士生．研究领域：移动机器人定位、导航．
张崇巍(1945- )，男，教授，博士生导师．研究领域：可再生能源利用，特种电源，网络控制技术与自动化仪表等．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2010/V32/I3/352

[1] Cox I J.Blanche-An experiment in guidance and navigation of an autonomous robot vehicle[J].IEEE Transactions on Robotics and Automation,1991,7(2):193-204.

[2] Gutmann J S,Weigel T,Nebel B.A fast,accurate and robust method for self-localization in polygonal environments using laser range finders[J].Advanced Robotics,2001,14(8):651-667.

[3] Weiss G,Wetzler C,yon Puttkamer E.Keeping track of position and orientation of moving indoor systems by correlation of range-finder scans[C]//IEEE/RSJ/GI International Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,1994:595-601.
[4] Besl P J,McKay N D.A method for registration of 3-13 shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.

[5] Lu F,Milios E E.Robot pose estimation in unknown environments by matching 2D range scans[J].Journal of Intelligent and Robotic Systems,1997,18(3):249-275.

[6] 杨明,王宏,张钹.基于激光雷达的移动机器人位姿估计方法综述[J].机器人,2002,24(2):177-183.Yang Ming,Wang Hong,Zhang Bo.Overview of laser radar based pose estimation for mobile robots[J].Robot,2002,24(2):177-183.
[7] Gutmann J S,Schlegel C.AMOS:Comparison of scan matching approaches for self-localization in indoor environments[C]//First Euromicro Workshop on Advanced Mobile Robots.1996:61-67.
[8] Langis C,Greenspan M,Godin G.The parallel iterative closest point algorithm[C]//Third International Conference on 3-D Digital Imaging and Modeling.Los Aiamitos,CA,USA:IEEE Computer Society,2001:195-202.
[9] 杨明,董斌,王宏,等.基于激光雷达的移动机器人实时位姿估计方法研究[J].自动化学报,2004,30(5):679-687.Yang Ming,Dong Bin,Wang Hong,et al.Research on laser radar based real-time pose estimation for mobile robots[J].Acta Automatic Sinica,2004,30(5):679-687.
[10] Nuchter A,Lingemann K,Hertzberg J,et al.Cached k-d tree search for ICP algorithms[C]//Sixth International Conference on 3-D Digital Imaging and Modeling.Piscataway,NJ,USA:IEEE,2007:419-426.
[11] Barnea S,Filin S.Keypoint based autonomous registration of terrestrial laser point-clouds[J].ISPRS Journal of Photogrammetry and Remote Sensing,2008,63(1):19-35.

[12] Xu Y H,Zhang C W,Bao W,et al.A robust pose estimation algorithm for mobile robot based on clusters[C]//International Conference on Intelligent Robotics and Applications.Berlin,Germany:Springer-Verlag,2008:1003-1010.
[13] Zhang L,Ghosh B K.Line segment based map building and localization using 2D laser rangeflnder[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2000:2538-2543.
[14] Gutmann J S,Konolige IL Incremental mapping of large cycfic environments[C]//IEEE International Symposium on Computational Intelligence in Robotics and Automation.Piscataway,NJ,USA:IEEE,1999:318-325.