Performance evaluation of UKF-based nonlinear filtering

被引:416
作者
Xiong, K [1 ]
Zhang, HY
Chan, CW
机构
[1] Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100083, Peoples R China
[2] Univ Hong Kong, Dept Mech Engn, Hong Kong, Hong Kong, Peoples R China
基金
中国国家自然科学基金;
关键词
nonlinear systems; stochastic systems; extended Kalman filter; unscented Kalman filter; stability;
D O I
10.1016/j.automatica.2005.10.004
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The performance of the modified unscented Kalman filter (UKF) for nonlinear stochastic discrete-time system with linear measurement equation is investigated. It is proved that under certain conditions, the estimation error of the UKF remains bounded. Furthermore, it is shown that the design of noise covariance matrix plays an important role in improving the stability of the algorithm. Error behavior of the UKF is then derived in terms of mean square error (MSE), and the Cramer-Rao lower bound (CRLB) is introduced as a performance measure. The modified UKF is found to approach the CRLB if the difference between the real noise covariance matrix and the selected one is small enough. These results are verified by using Monte Carlo simulations on two example systems. (c) 2005 Elsevier Ltd. All rights reserved.
引用
收藏
页码:261 / 270
页数:10
相关论文
共 26 条