一种基于均值筛选的粒子滤波算法  

A new particle filtering basing on mean selecting

作　　者：王光[1] 邱云飞[1] 李红霞[1] 

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125100

出　　处：《信息化纵横》2009年第17期63-66,共4页

基　　金：国家自然科学基金项目(70572070)

摘　　要：针对基于均值筛选的粒子滤波算法MPF,利用无迹卡尔曼粒子滤波产生一步预测。在重采样阶段,利用对粒子按照权值大小进行排序的确定性重采样策略。为了克服样本耗尽问题,在统计所有粒子权值的均值后,对于权值小于均值的粒子进行一步权值平缓化变异。仿真实验表明MPF精确度优于其他5种流行的滤波算法。This paper proposed a novel filtering method-mixed unscented particle filtering （MPF） for nonlinear dynamic systems, MPF mainly includes two steps. At first unscented extended Kalman filter was used as proposal distribution to generate particles; Secondly, after getting means and variances of the proposal distribution, these particles were refined using unscented transformation. The proposed MPF algorithm was compared with other five filtering algorithms and the simulating results show that means and variances of MPF are lower than other filtering algorithms.

关 键 词：非线性滤波 粒子滤波 无忌卡尔曼滤波 均值筛选 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]