一种改进的迭代无迹卡尔曼滤波算法  

AN IMPROVED ITERATED UNSCENTED KALMAN FILTER ALGORITHM

作　　者：陈波[1] Chen Bo(College of Mechanical and Electrical Engineering,Xinxiang University,Xinxiang 453003,Henan,China)

机构地区：[1]新乡学院机电工程学院

出　　处：《计算机应用与软件》2019年第10期274-278,共5页Computer Applications and Software

基　　金：国家自然科学基金项目(61501391);河南省高等学校重点科技项目(15A510035);新乡市创新平台项目(CP1504)

摘　　要：针对非线性系统目标跟踪中状态估计的线性问题,在滤波过程的不同部分,利用统计和分析原理对状态估计进行线性化,提出一种改进的迭代无迹卡尔曼滤波(Improved Iterated Unscented Kalman Filter,IIUKF)。在系统方程和测量方程都具有较严重的非线性条件下,与无迹卡尔曼滤波器(UKF)和迭代扩展卡尔曼滤波(IEKF)进行仿真验证比较。结果显示该方法的跟踪性能优于UKF和IEKF,提高了系统的跟踪效果。Aiming at the linear problem of state estimation in target tracking of nonlinear systems,this paper proposed an improved iterated unscented Kalman filter(IIUKF) by linearizing the state estimation in different parts of the filtering process using statistical and analytical principles.Under the condition that both the system equation and the measurement equation have serious nonlinearity,the proposed method was compared with the unscented Kalman filter(UKF) and the iterated extended Kalman filter(IEKF) for simulation verification.The results show that the tracking performance of this method is better than that of UKF and IEKF,and the tracking effect of the system is improved.

关 键 词：卡尔曼滤波 迭代 目标跟踪 线性化 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术] N945[自然科学总论—系统科学]