DocumentCode :
2882224
Title :
An adaptive nonlinear filter of discrete-time system with uncertain covariance using unscented Kalman filter
Author :
Li, Wan-Chun ; Wei, Ping ; Xiao, Xian-Ci
Author_Institution :
Sch. of Electron. Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China
Volume :
2
fYear :
2005
fDate :
12-14 Oct. 2005
Firstpage :
1436
Lastpage :
1439
Abstract :
A novel adaptive unscented Kalman nonlinear filter (AUKF) is presented in this paper. In many system, the noise covariance is unknown exact, but the approximate can been obtained by many methods. The approximate is used to initialize the unscented Kalman filter (UKF). Each step these noise covariance are adjusted based on the prior noise covariance and state information. To reduce obsolete measure value and covariance, a limited memory method is used. On the performance, UKF is better than EKF. The AUKF are better than these adaptive Kalman filters which based on extended Kalman filter (EKF). A target tracking is used to demonstrate this.
Keywords :
adaptive Kalman filters; nonlinear filters; target tracking; adaptive nonlinear filter; discrete-time system; extended Kalman filter; memory method; noise covariance; state information; uncertain covariance; unscented Kalman nonlinear filter; Adaptive filters; Communication system control; Electronic mail; Kalman filters; Linear systems; Nonlinear control systems; Nonlinear filters; Nonlinear systems; Statistics; Target tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications and Information Technology, 2005. ISCIT 2005. IEEE International Symposium on
Print_ISBN :
0-7803-9538-7
Type :
conf
DOI :
10.1109/ISCIT.2005.1567140
Filename :
1567140
Link To Document :
بازگشت