基于概率数据关联交互多模滤波的移动机器人未知环境下动态目标跟踪

doi:10.3724/SP.J.1218.2012.00668

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (969 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
伍明, 李琳琳, 孙继银 . 基于概率数据关联交互多模滤波的移动机器人未知环境下动态目标跟踪[J]. 机器人, 2012, 34(6): 668-679.DOI: 10.3724/SP.J.1218.2012.00668. WU Ming, LI Linlin, SUN Jiyin. PDA-IMM Based Moving Object Tracking with Mobile Robots in Unknown Environments. ROBOT, 2012, 34(6): 668-679. DOI: 10.3724/SP.J.1218.2012.00668.

摘要

为了解决未知环境条件下自主移动机器人机动目标跟踪问题，提出了一种概率数据关联交互多模滤波算法．算法基于全协方差扩展式卡尔曼滤波框架，系统状态由机器人状态、环境特征状态以及目标状态联合构成，采用交互多模滤波方法解决了机动目标运动过程中的模式不确定问题．针对实际应用中目标存在伪观测值的问题，在不同运动模式滤波器中采用概率数据关联方法加权计算不同观测值对系统状态更新的贡献．仿真实验验证了算法对机器人状态、环境状态以及机动运动目标状态的估计准确性，证明了算法对机动运动物体的跟踪能力，以及对于目标伪观测值的处理能力，实体机器人实验验证了算法的实用性．

	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
	伍明
	李琳琳
	孙继银

关键词 ：同时定位与地图构建, 交互多模滤波, 概率数据关联滤波, 目标跟踪

Abstract：

In order to solve the problem of maneuvering object tracking by autonomous mobile robots in unknown environments, a filtering algorithm adopting probabilistic data association (PDA) and interacting multiple model (IMM) is proposed. The algorithm is based on the framework of full covariance extended Kalman filter. The robot state, environment landmark states and target state are used to form the system state, and the problem of model uncertainty in the process of object moving is solved by IMM filter. For the problem of false object observations in practical application, a PDA method is used to weight the contribution of different observations to system state update in different moving model filters. Simulation results show the accuracy of the algorithm in estimating robot state, environment landmark states and target state, and prove the algorithm ability of tracking maneuvering object, as well as the ability of dealing with false object observations. A real robot experiment verifies the practicability of the algorithm.

Key words： SLAM (simultaneous localization and mapping) IMM (interacting multiple model) filter PDA (probabilistic data association) filter object tracking

收稿日期: 2012-01-25 录用日期: 2012-08-20

TP242.6

基金资助:

国家863计划资助项目（2006AA04Z258）

通讯作者: 伍明 E-mail: hyacinth531@163.com

作者简介: 伍明（1981-），男，博士，讲师．研究领域：自主机器人控制，多机器人协作，机器人环境构建．
李琳琳（1974-），女，博士，副教授．研究领域：信息融合，信息栅格技术，物联网技术．
孙继银（1952-），男，教授．研究领域：多媒体系统，图像处理，人工智能．

链接本文:

https://robot.sia.cn/CN/10.3724/SP.J.1218.2012.00668 或 https://robot.sia.cn/CN/Y2012/V34/I6/668

[1] Vu T D, Aycard O, Appenrodt N. Online localization and mapping with moving object tracking in dynamic outdoor environments[C]//IEEE Intelligent Vehicles Symposium. Piscataway, NJ, USA: IEEE, 2007: 190-195.

[2] Vidal R, Rashid S, Sharp C, et al. Pursuit-evasion games with unmanned ground and aerial vehicles[C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 2001: 2948-2955.

[3] Huang F F, Wang L, Wang Q N, et al. Coordinated control of multiple mobile robots in pursuit-evasion games[C]//Proceedings of the American Control Conference. Piscataway, NJ, USA: IEEE, 2008: 2861-2866.

[4] Wang C C, Thorpe C, Thrun S, et al. Simultaneous localization, mapping and moving object tracking[J]. International Journal of Robotics Research, 2007, 26(9): 889-916.

[5] Wang C C, Thorpe C, Thrun S. Online simultaneous localization and mapping with detection and tracking of moving objects: Theory and results from a ground vehicle in crowded urban areas[C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 2003: 842-849.

[6] Borrmann D, Elseberg J, Lingemann K, et al. Globally consistent 3D mapping with scan matching[J]. Robotics and Autonomous Systems, 2008, 56(2): 130-142.

[7] 伍明,孙继银.基于扩展式卡尔曼滤波的移动机器人未知环境下动态目标跟踪[J].机器人,2010,32(3):334-343. Wu M, Sun J Y. Extended Kalman filter based moving object tracking by mobile robot in unknown environment[J]. Robot, 2010, 32(3): 334-343.

[8] 伍明,孙继银.一种机器人未知环境下动态目标跟踪交互多模滤波算法[J].智能系统学报,2010,5(2):127-138. Wu M, Sun J Y. An interacting multiple model filtering algorithm for mobile robots to improve tracking of moving objects in unknown environments[J]. CAAL Transactions on Intelligent Systems, 2010, 5(2): 127-138.

[9] Wu M, Sun J Y. Simultaneous localization, mapping and detection of moving objects with mobile robot in dynamic environments[C]//Proceedings of the 2nd International Conference on Computer Engineering and Technology. Piscataway, NJ, USA: IEEE, 2010: 696-701.

[10] Cameron S, Probert P. Advanced guided vehicles: Aspects of the Oxford AGV project[M]. Hackensack, NJ, USA: World Scientific, 1994.

[11] Bar-Shalom Y. Tracking and data association[M]. Boston, USA: TE Fortmann Academic Press, 1988.

[12] Arras K O. Feature-based robot navigation in known and unknown environments[D]. Lausanne, Switzerland: Swiss Federal Institute of Technology, 2003.

[13] Musicki D, Evans R. Joint integrated probabilistic data association: JIPDA[J]. IEEE Transactions on Aerospace and Electronic Systems, 2004, 40(3): 1093-1099.

[14] Musicki D, Morelande M. Gate volume estimation for target tracking[C]//Proceedings of the International Conference on Information Fusion. Piscataway, NJ, USA: IEEE, 2004: 455-462.

[15] Musicki D, Evans R, Stankovic S. Integrated probabilistic data association (IPDA)[J]. IEEE Transactions on Automatic Control, 1994, 39(6): 1237-1241.

[16] Wolf D F, Sukhatme G S. Mobile robot simultaneous localization and mapping in dynamic environments[J]. Autonomous Robots, 2005, 19(1): 53-65.

[17] Wu M, Huang F F, Wang L, et al. A distributed multi-robot cooperative hunting algorithm based on limit-cycle[C]//Pro- ceedings of 2009 International Asia Conference on Informatics in Control, Automation and Robotics. Piscataway, NJ, USA: IEEE, 2009: 156-160.