Self-tuning decoupled fusion Kalman filter based on the Riccati equation

Abstract

An online noise variance estimator for multi-sensor systems with unknown noise variances is proposed by using the correlation method. Based on the Riccati equation and optimal fusion rule weighted by scalars for state components, a self-tuning component decoupled information fusion Kalman filter is presented. It is proved that the filter converges to the optimal fusion Kalman filter in a realization by dynamic error system analysis method, so that it has asymptotic optimality. Its effectiveness is demonstrated by simulation for a tracking system with 3 sensors.

Keywords

multi-sensor information fusion / decoupled fusion / self-tuning fuser / Kalman filter / convergence in a realization