Lyapunov stability of a tracking filter with the uncertainty of measurement origin

Author

Kim, Yong-Shik ; Hong, Keum-Shik

Author_Institution

Dept. of Mech. & Intelligent Syst. Eng., Pusan Nat. Univ., South Korea

fYear

2001

fDate

2001

Firstpage

304

Lastpage

309

Abstract

The probabilistic data association filter (PDAF) is known to provide better tracking performance than the standard Kalman filter (KF) in a cluttered environment. In this paper, the stability of the PDAF of Fortmann et al. (1985), in the presence of uncertainties with regard to the origin of measurement, is investigated. The modified Riccati equation derived by approximating two random terms with their expectations is used to evaluate the stability of the PDAF. A new Lyapunov function based approach, which is different from the quantitative evaluation of Li and Bar-Shalom (1991), is pursued. With the assumption that the system and observation noises are bounded, specific tracking error bounds are established

Keywords

Lyapunov matrix equations; Riccati equations; filtering theory; noise; stability; state estimation; target tracking; Kalman filter; Lyapunov stability; PDAF; bounded observation noises; bounded system; cluttered environment; measurement origin uncertainty; modified Riccati equation; probabilistic data association filter; tracking error bounds; tracking filter; Convergence; Filters; Lyapunov method; Measurement uncertainty; Riccati equations; Signal processing algorithms; Stability analysis; State estimation; Steady-state; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE 2001. Proceedings of the 40th SICE Annual Conference. International Session Papers

Conference_Location

Nagoya

Print_ISBN

0-7803-7306-5

Type

conf

DOI

10.1109/SICE.2001.977851

Filename

977851