进化粒子滤波算法及其应用  

Evolutionary particle filter and its application

作　　者：莫以为[1] 萧德云[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《控制理论与应用》2005年第2期269-272,共4页Control Theory & Applications

基　　金：国家高技术研究发展计划(863计划)资助项目(2002AA412510;2002AA412420).

摘　　要：样本贫化现象是应用粒子滤波算法的一个主要障碍,对估计长时间维持不变量的影响尤为严重.通过分析产生该现象的原因,本文引入进化规划算子构成进化粒子滤波算法,增加样本集的多样性而缓解样本贫化现象的影响,改善其估计与跟踪能力,仿真结果显示所提出的算法是可行的.Sample impoverishment phenomenon is a main handicap to particle filter application,especially in those cases to estimate the parameter that remains constant for a long time.Based on the analysis of the causes of sample impoverishment,the evolutionary particle filter is proposed,in which evolutionary programming is introduced.The improved approach relieves the effect caused by samples impoverishment through ameliorating the diversity of samples set.Simulation results demonstrate the feasibility of proposed evolutionary particle filter.

关 键 词：粒子滤波算法 样本贫化 进化规划 状态估计 

分 类 号：TN713[电子电信—电路与系统]