一种基于聚类分组的快速联合兼容SLAM数据关联算法

doi:10.13973/j.cnki.robot.170400

摘要
图/表
参考文献
相关文章 (5)

全文: PDF (1777 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
刘丹, 段建民, 王昶人. 一种基于聚类分组的快速联合兼容SLAM数据关联算法[J]. 机器人, 2018, 40(2): 158-168,177.DOI: 10.13973/j.cnki.robot.170400. LIU Dan, DUAN Jianmin, WANG Changren. A Fast Joint Compatibility Data Association Algorithm for SLAM Based on Clustering. ROBOT, 2018, 40(2): 158-168,177. DOI: 10.13973/j.cnki.robot.170400.

摘要针对在移动机器人同时定位与建图（SLAM）过程中如何快速准确获取数据关联结果的问题，提出了一种基于DBSCAN（density-based spatial clustering of application with noise）聚类分组的快速联合兼容SLAM数据关联算法（DFJCBB）．首先，采用局部关联策略将参与关联的特征点限定在局部地图中；其次，针对多数环境中量测都有较明显的分布，采用一种基于密度聚类的方法DBSCAN对当前时刻的量测进行分组，从而得到若干关联度小的观测小组；最后，在每个小组中采用联合兼容分支定界（JCBB）算法进行数据关联，以获得每个小组量测与局部地图特征之间的最优关联解，并将这些关联解组合获得最终的关联结果．基于模拟器和标准数据集的仿真实验验证了该关联算法的性能，结果表明该关联算法在保证获得较高关联准确度的同时，大大降低了算法复杂度、缩短了运行时间，适用于解决不同复杂环境中的SLAM数据关联问题．

	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

关键词 ：同时定位与建图, 联合兼容分支定界算法, 局部关联策略, 聚类分组, 关联准确度, 计算复杂度, 同时定位与建图, 联合兼容分支定界算法, 局部关联策略, 聚类分组, 关联准确度, 计算复杂度

Abstract：In order to quickly and accurately obtain data association results in simultaneous localization and mapping (SLAM) of mobile robot, a fast joint compatibility data association algorithm (DFJCBB) for SLAM based on DBSCAN (density-based spatial clustering of application with noise) is proposed. Firstly, the local association strategy is used to limit features in local map. Then, a density-based clustering method, that is DBSCAN method, is used to group all measurements at the current moment and get a number of measurement groups with small correlation, because the measurements appear a clear distribution in most environments. Finally, joint compatibility branch and bound (JCBB) algorithm is adopted in data association of each group to obtain the optimal association solution between each group of measurements and local map features, and the optimal association solutions are combined to obtain the final association result. The performance of the proposed algorithm is verified by simulation based on the simulator and benchmark dataset. The results show that the proposed algorithm can guarantee high association accuracy, reduce the computational complexity and shorten the running time. It is suitable for solving the data association problem of SLAM in different complex environments.

Key words： simultaneous localization and mapping (SLAM) joint compatibility branch and bound (JCBB) algorithm local association strategy clustering association accuracy computational complexity simultaneous localization and mapping (SLAM) joint compatible branch and bound (JCBB) algorithm local association strategy clustering algorithm correlation accuracy computational complexity

收稿日期: 2017-06-27 录用日期: 2017-12-14

ZTFLH:

TP242.6

基金资助:北京高等学校人才强教计划（038000543117004）

通讯作者: 刘丹,danaliu@yeah.net E-mail: danaliu@yeah.net

作者简介: 刘丹(1990-),女,博士生.研究领域:智能车的同时定位与建图;
段建民(1959-),男,博士,教授.研究领域:车辆环境识别与自动驾驶技术,网络化测控系统与现场总线技术,嵌入式汽车电子控制技术;
王昶人(1992-),男,硕士生.研究领域:基于激光雷达的车辆检测与识别技术,信息融合.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.170400 或 https://robot.sia.cn/CN/Y2018/V40/I2/158

[1] Dissanayake M W M G, Newman P, Clark S, et al. A solution to the simultaneous localization and map building (SLAM) problem[J]. IEEE Transactions on Robotics and Automation, 2001, 17(3): 229-241.
[2] Durrantwhyte H, Bailey T. Simultaneous localization and mapping: Part I[J]. IEEE Robotics and Automation Magazine, 2006, 13(3): 108-117.
[3] Hähnel D, Thrun S, Wegbreit B, et al. Towards lazy data association in SLAM[C]//The Eleventh International Symposium on Robotics Research. Berlin, German: Springer-Vlerlag, 2003: 421-431.
[4] 季秀才. 机器人同步定位与建图中数据关联问题研究[D]. 长沙:国防科学技术大学,2008.Ji X C. Data association problem for simultaneous localization and mapping of mobile robots[D]. Changsha: National University of Defense Technology, 2008.
[5] 陈白帆. 动态环境下移动机器人同时定位与建图研究[D]. 长沙:中南大学,2009.Chen B F. Research on simultaneous localization and mapping of mobile robots in dynamic environments[D]. Changsha: Central South University, 2009.
[6] 曾文静,张铁栋,姜大鹏. SLAM 数据关联方法的比较分析[J]. 系统工程与电子技术,2010,32(4):860-864.Zeng W J, Zhang T D, Jing D P. Analysis of data association methods of SLAM[J]. Systems Engineering & Electronics, 2010, 32(4): 860-864.
[7] Neira J, Tardos J D. Data association in stochastic mapping using the joint compatibility test[J]. IEEE Transactions on Robotics & Automation, 2001, 17(6): 890-897.
[8] 徐君,张国良,敬斌,等. 一种优化的联合极大似然 SLAM 数据关联方法[J]. 机器人,2012,34(4):492-497.Xu J, Zhang G L, Jing B, et al. A joint maximum likelihood method optimized data association approach to SLAM problem[J]. Robot, 2012, 34(4): 492-497.
[9] Chen B F, Cai Z X, Zou Z R. A hybrid data association approach for mobile robot SLAM[C]//IEEE International Conference on Control, Automation and Systems. Piscataway, USA: IEEE, 2010: 1900-1903.
[10] 张雪晶,孙作雷,曾连荪. 基于联合相容分支定界的关联算法研究[J]. 微型机与应用,2015,34(15):82-84. Zhang X J,Sun Z L,Zeng L S. Study on association algorithm based on joint compatibility branch and bound[J]. Microcomputer & Its Applications, 2015, 34(15): 82-84.
[11] 郭剑辉,赵春霞,石杏喜. 一种改进的联合相容SLAM 数据关联方法[J]. 仪器仪表学报,2008,29(11):2260-2265. Guo J H, Zhao C X, Shi X X. Improved joint compatibility data association approach for simultaneous localization and map building (SLAM)[J]. Chinese Journal of Scientific Instrument, 2008, 29(11): 2260-2265.
[12] 周武,赵春霞. SLAM 问题的一种优化数据关联算法[J]. 机器人,2009,31(3):217-223. Zhou W, Zhao C X. An optimized data association solution for SLAM[J]. Robot, 2009, 31(3): 217-223.
[13] 姚聪. 基于贝叶斯理论的移动机器人定位方法研究[D]. 重庆:重庆大学,2015. Yao C. The research of mobile robot localization method based on Bayesian theory[D]. Chongqing: Chongqing University, 2015.
[14] Zhou Z P, Wang J F, Zhu S W, et al. An improved adaptive and fast AF-DBSCAN clustering algorithm[J]. CAAI Transactions on Intelligent Systems, 2016, 11(1): 93-98.
[15] Bailey T, Nieto J, Guivant J, et al. Consistency of the EKFSLAM algorithm[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2006: 3562-3568.
[16] Nebot E. Victoria park data set[DB/OL]. (2001-04-29) [2017-03-10]. http://www-personal.acfr.usyd.edu.au/nebot/dataset.htm.