一种针对人形足球机器人的分域自适应蒙特卡洛定位方法

doi:10.3724/SP.J.1218.2012.00652

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (852 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
洪伟, 周长久, 田彦涛 . 一种针对人形足球机器人的分域自适应蒙特卡洛定位方法[J]. 机器人, 2012, 34(6): 652-659,744.DOI: 10.3724/SP.J.1218.2012.00652. HONG Wei, ZHOU Changjiu, TIAN Yantao. Subsectional Adaptive Monte Carlo Localization for Humanoid Soccer Robot. ROBOT, 2012, 34(6): 652-659,744. DOI: 10.3724/SP.J.1218.2012.00652.

摘要

针对常规蒙特卡洛定位法中的粒子贫化和绑架问题，提出了一种分域自适应蒙特卡洛定位方法．该方法首先定义了两个用于描述粒子集合分布及其与真实位姿之间的差异的特征变量．然后根据特征变量的组合值将定位过程识别为全局定位、局部定位、局部跟踪和容错定位四种状态的交替过程，并为每种状态设计了自适应的控制策略来调整参数和重新采样规则．基于大型人形足球比赛机器人系统的物理和仿真实验的结果均表明，该定位方法有利于提高定位的准确性和实时性．同时，该方法还可以高效地解决绑架问题，提高了系统的鲁棒性．

	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
	洪伟
	周长久
	田彦涛

关键词 ：自适应蒙特卡洛定位, 绑架问题, 分域控制, 人形足球比赛机器人

Abstract：

A subsectional adaptive Monte Carlo localization method is presented to overcome some shortcomings in regular Monte Carlo localization, such as particle degeneracy and the kidnap problem. Firstly, two feature variables are proposed to describe distribution of particle set and its difference from the real posture. Secondly, four states (global localization, local localization, local tracking and fault-tolerant localization) are identified by the combination of the variable values during the whole process of localization, and different strategies are designed for each state in order to adjust parameters and resampling rules adaptively. Finally, the results of physical and simulative experiments based on adult-size humanoid soccer robot system show that the proposed method is effective in achieving an accurate and real-time localization. Furthermore, this method can enhance the robustness of localization system by solving the kidnap problem efficiently.

Key words： adaptive Monte Carlo localization kidnap problem subsectional control humanoid soccer robot

收稿日期: 2012-05-08 录用日期: 2012-09-07

TP24

基金资助:

吉林大学“985工程”工程仿生科技创新平台项目；吉林大学基本科研业务费资助项目（200903312）

通讯作者: 洪伟 E-mail: hongwei@jlu.edu.cn

作者简介: 洪伟（1970-），女，博士，副教授．研究领域：移动机器人，数据融合，智能交通．
周长久（1963-），男，博士，教授．研究领域：人与仿生机器人，移动机器人，服务机器人，足球机器人，智能控制，人机交互．
田彦涛（1958-），男，博士，教授．研究领域：移动机器人，人脸表情识别，智能假肢手臂．

链接本文:

https://robot.sia.cn/CN/10.3724/SP.J.1218.2012.00652 或 https://robot.sia.cn/CN/Y2012/V34/I6/652

[1] Dellaert F, Fox D, Burgard W, et al. Monte Carlo localization for mobile robots[C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 1999: 1322-1328.

[2] Rofer T, Jungel M. Vision-based fast and reactive Monte-Carlo localization[C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 2003: 856-861.

[3] Thompson S, Kagami S. Humanoid robot localisation using stereo vision[C]//IEEE-RAS International Conference on Humanoid Robotics. Piscataway, NJ, USA: IEEE, 2005: 19-25.

[4] 张霄汉,陈小平,李嘉玲,等.一种基于视觉的步行机器人Monte Carlo自定位系统[J].机器人,2006,28(4): 415-421.Zhang X H, Chen X P, Li J L, et al. A vision-based Monte Carlo self-localization system on a walking robot[J]. Robot, 2006, 28(4): 415-421.

[5] Thrun S, Fox D, Burgard W, et al. Robust Monte Carlo localization for mobile robots[J]. Artificial Intelligence, 2001, 128(1/2): 99-141.

[6] 方正,佟国锋,徐心和.一种鲁棒高效的移动机器人定位方法[J].自动化学报,2007,33(1): 48-53.Fang Z, Tong G F, Xu X H. A robust and efficient algorithm for mobile robot localization[J]. Acta Automatica Sinica, 2007, 33(1): 48-53.

[7] Gasparri A, Panzieri S, Pascucci F, et al. Monte Carlo filter in mobile robotics localization: A clustered evolutionary point of view[J]. Journal of Intelligent and Robotic Systems, 2006, 47(2): 155-174.

[8] 张恒,樊晓平,翟志华.基于多假设跟踪的移动机器人自适应蒙特卡洛定位研究[J].自动化学报,2007,33(9): 941- 946.Zhang H, Fan X P, Zhai Z H. Mobile robot adaptive Monte Carlo localization based on multiple hypothesis tracking[J]. Acta Automatica Sinica, 2007, 33(9): 941-946.

[9] Thrun S, Fox D, Burgard W. Monte Carlo localization with mixture proposal distribution[C]//17th National Conference on Artificial Intelligence and 12th Conference on Innovative Application of Artificial Intelligence. Cambridge, MA, USA: MIT Press, 2000: 859-865.

[10] 宋宇,孙富春,李庆玲.移动机器人的改进无迹粒子滤波蒙特卡洛定位算法[J].自动化学报,2010,36(6): 851-857.Song Y, Sun F C, Li Q L. Mobile robot Monte Carlo localization based on improved unscented particle filter[J]. Acta Automatica Sinica, 2010, 36(6): 851-857.

[11] Milstein A, Sanchez J N, Williamson E T. Robust global localization using clustered particle filtering[C]//18th National Conference on Artificial Intelligence and 14th Innovative Applications of Artificial Intelligence Conference. Cambridge, MA, USA: MIT Press, 2002: 581-586.

[12] Fox D. Adapting the sample size in particle filters through KLD-sampling[J]. International Journal of Robotics Research, 2003, 22(12): 985-1103.

[13] 武二永,项志宇,刘济林.鲁棒的机器人蒙特卡洛定位算法[J].自动化学报,2008,34(8): 907-911.Wu E Y, Xiang Z Y, Liu J L. Robust robot Monte Carlo localization[J]. Acta Automatica Sinica, 2008, 34(8): 907-911.

[14] Hu L Y, Zhou C J. Gait generation and optimization using theestimation of distribution algorithm for teensize humanoid soccerrobot RESr-1[J]. International Journal of Humanoid Robotics, 2008,5(3): 437-456.

[15] RoboCup soccer humanoid league rules and setup for the 2010competition in Singapore[EB/OL]. [2009-12-20]. http://www.tzi.de/humanoid/pub/Website/Downloads/Humanoid League Rules2010.pdf.