Suboptimal discrete filters for stochastic systems with different types of observations

Abstract

In [1], we developed a new suboptimal filtering methods for a class of linear and nonlinear continuous dynamic systems with multidimensional observation vector. The methods are based on the decomposition of Kalman filtering and extended Kalman filtering equations by observation vector. In this paper, we present a generalization of these filtering methods to discrete stochastic systems determined by difference equations. The obtained filtering equations have a parallel structure and are very suitable for parallel programming. Example demonstrating the efficiency of the proposed suboptimal filters is given.