一种改进的粒子滤波算法及其性能分析  

Improved PF algorithm and performance analysis

作　　者：曹洁[1] 李伟[1] 

机构地区：[1]兰州理工大学计算机与通信学院,兰州730050

出　　处：《计算机工程与应用》2012年第8期144-147,共4页Computer Engineering and Applications

基　　金：甘肃省自然科技基金(No.1010RJZA046);甘肃省教育厅硕导基金项目(No.0914ZTB003);甘肃省财政厅项目(No.0914ZTB148)

摘　　要：针对非线性、非高斯系统状态的在线估计问题,提出了一种改进的粒子滤波算法。该算法采用Unscented卡尔曼滤波器(UKF)产生系统的状态估计,并在量测更新过程中加入衰减记忆因子,消弱滤波器对历史信息的依赖,增强当前量测信息对滤波器的修正作用,从而产生一个优选的建议分布函数,较好地抑制了粒子退化问题。理论分析和实验表明:引入记忆衰减因子的粒子滤波,即衰减记忆无味粒子滤波(MAUPF)的性能明显优于标准的粒子滤波以及Unscented粒子滤波。A new particle filter is proposed for the on-line estimation problem of non-Gauss nonlinear systems. In order to weaken the effect of historical information and enhance the effect of up-to-date measurement, it introduces attenuation memory factor for generat- ing the important density function based on the Unscented Kalman filter（UKF） for a better performance in inhibiting the particle degradation problems in the new algorithm. As a result, the theoretical analysis and experimental results show that the new particle filter outperforms obviously superior to the standard particle filter and Unscented particle filter.

关 键 词：状态估计 粒子滤波器 记忆衰减因子 重要性概率密度函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]