For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Particle Filter Approach to Robust State Estimation for a Class of Nonlinear Systems with Stochastic Parameter Uncertainty
Sehoon KIM Sangchul WON
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2011/05/01
Online ISSN: 1745-1337
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Systems and Control
robust state estimation, particle filter, stochastic parameter uncertainty, mixture of Gaussians, Chua's circuit,
Full Text: PDF>>
In this paper, we propose a robust state estimation method using a particle filter (PF) for a class of nonlinear systems which have stochastic parameter uncertainties. A robust PF was designed using prediction and correction structure. The proposed PF draws particles from a simple proposal density function and corrects the particles with particle-wise correction gains. We present a method to obtain an error variance of each particle and its upper bound, which is minimized to determine the correction gain. The proposed method is less restrictive on system nonlinearities and noise statistics; moreover, it can be applied regardless of system stability. The effectiveness of the proposed robust PF is illustrated via an example based on Chua's circuit.