Design of Information Fusion Filter for a Class of Multi-sensor Asynchronous Sampling Systems

For the discrete-time linear stochastic systems with multiple sensors of different sampling rates, a distributed information fusion filter weighted by matrices is given in the linear minimum variance sense. The correlation of estimation errors between any two local filters is considered. Compared with the fusion filter where the correlation of local estimation errors isn't taken into account, the proposed filter improves the accuracy. An example shows the feasibility and effectiveness of the proposed algorithm.