李天成, 孙树栋, 司书宾, 王军强. 基于粒子聚合重采样的移动机器人蒙特卡洛定位[J]. 机器人, 2010, 32(5): 674-680..
LI Tiancheng, SUN Shudong, SI Shubin, WANG Junqiang . Particle Merging Resampling Based Monte Carlo Localization for Mobile Robot. ROBOT, 2010, 32(5): 674-680..
摘要提出了一种基于粒子聚合重采样的移动机器人聚合蒙特卡洛定位（Merge Monte Carlo localization，Merge-MCL）方法．首先将移动机器人作业空间划分为离散栅格，建立栅格集，然后提出一种基于粒子空间相近性的粒子聚合技术，在保证粒子空间分布合理性的同时自适应调整粒子集规模．提出的粒子聚合重采样方法能够缓解粒子权值退化问题，并避免了传统重采样方法导致的多样性匮乏问题．仿真结果表明，粒子聚合重采样方法能够有效控制粒子集规模，聚合蒙特卡洛定位方法是鲁棒、有效的．
Abstract：A merge Monte Carlo localization(Merge-MCL) method for mobile robot based on particle merging resampling is presented.Grid cells and grid sets are established to represent the workspace of mobile robot,and then a particle merging technique based on the particles' spatial similarity is proposed.The technique adapts the number of particles according to the rational distribution of spatial particles.Resampling using the particle merging technique mitigates the weight degeneracy problem of particles and avoids diversity impoverishment caused by the traditional resampling methods.Simulation results illustrate that the particle merging resampling can adapt the number of particles efficiently and the Merge-MCL method is efficient and robust.
[1] 李群明,熊蓉,褚健.室内自主移动机器人定位方法研究综述[J]. 机器人,2003,25(6):560-567,573.Li Qunming,Xiong Rong,Chu Jian.Localization approaches for indoor autonomous mobile robots:A review[J]. Robot,2003,25(6):560-567,573.
[2] Bar-Shalom Y,Li X R,Kirubarajan T.Estimation with applications to tracking and navigation:Theory,algorithms,and software[M]. New York,USA:John Wiley & Sons,2001:200-217.
[3] Fox D,Burgard W,Dellaert F,et al.Monte Carlo localization:Efficient position estimation for mobile robots[C]//National Conference on Artificial InteLligence.Menlo Park,CA,USA:AAAI,1999:343-349.
[4] 于金霞,蔡自兴,段琢华.基于粒子滤波的移动机器人定位关键技术研究综述[J]. 计算机应用研究,2007,24(11):9-14.Yu Jinxia,Cai Zixing,Duan Zhnohua.Survey on some key technologies of mobile robot localization based on particle filter[J]. Application Research of Computers,2007,24(11):9-14.
[5] Khan Z,Balch T,Dellaert F.MCMC-based particle filtering for tracking a variable number of interacting targets[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1805-1819.
[6] Fox D.Adapting the sample size in particle filters through KLDsampling[J]. International Journal of Robotics Research,2003,22(12):985-1003.
[7] Kwok C,Fox D,Meil M.Real-time particle filters[J]. Proceedings of the IEEE,2004,92(3):469-484.
[8] Soto A.Self adaptive particle fiiter[C]//International Joint Conferences on Artificial Intelligence.San Francisco,CA,USA:Morgan Kaufmann Publishers,2005:1398-1403.
[9] Liu Z B,Shi Z Y,Zhao M G,et al.Mobile robots global localization using adaptive dynamic clustered particle filters[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,2007:1059-1064.
[10] 候代文,殷福亮,陈喆.基于拟蒙特卡洛滤波的说话人跟踪方法[J]. 自动化学报,2009,35(7):1016-1021.Hou Daiwen,Yin Fuliang,Chen Zhe.Quasi-Monte Carlo filtering for speaker tracking[J]. Acta Automatica Sinica,2009,35(7):1016-1021.
[11] 刘俊承,原魁,邹伟,等.基于特征粒子的Monte Carlo自定位方法[J]. 机器人,2006,28(1):30-35.Liu Juncheng,Yuan Kui,Zou Wei,et al.Monte Carlo selflocalization based on characteristic particles[J]. Robot,2006,28(1):30-35.
[12] Milstein A,Sanchez J N,Williamson E T.Robust global localization using clustered particle filtering[C]//National Conference on Artificial Intelligence.Menlo Park,CA,USA:AAAI,2002:581-586.
[13] Liu J S,Chen R.Sequential Monte Carlo methods for dynamical systems[J]. Journal of the American Statistical Association,1998,93(5):1032-1044.
[14] 师义民,徐伟,秦超英,等.数理统计[M]. 3版.北京:科学出版社,2009.Shi Yimin,Xu Wei,Qin Chaoying,et al.Mathematical statistics[M]. 3rd ed.Beijing:Science Press,2009.
