Square-root filtering for discrete-time systems with multiplicative and additive noises

The paper addresses the problem of constructing numerically efficient linear filtering algorithms for discrete-time linear stochastic systems with multiplicative and additive noises. A new square-root covariance algorithm for optimal linear filtering is proposed. We demonstrate that the developed algorithm is algebraically equivalent to the standard covariance filter. Also it has the improved computational properties inherent to all square-root algorithms. The results of numerical experiments confirming the operability of the proposed algorithm are presented.