Centralized Fusion Estimators for Multi-sensor Systems with Multiplicative Noises and Missing Measurements

This paper is concerned with the centralized fusion estimation problem for multi-sensor systems with multiplicative noises in state and measurement matrices and missing measurements. Based on the innovation analysis approach, the centralized fusion estimators including filter, predictor and smoother are developed in the least mean square sense. The steady-state estimators are also studied. A sufficient condition for the existence of the steady-state centralized fusion estimators is obtained. An illustrative example shows the effectiveness of the proposed algorithm.