Diffusion Kalman filtering based on covariance intersection

This paper is concerned with distributed Kalman filtering for linear time-varying systems over multi-agent sensor networks. We propose a diffusion Kalman filtering algorithm based on a covariance intersection method, where local estimates are fused by incorporating the covariance information of local Kalman filters. Our algorithm leads to a stable estimate for each agent regardless of whether the system is uniformly observable with respect to local measurements as long as the system is uniformly observable under global sensor measurements and the communication is sufficiently fast compared to the sampling period. Simulation results validate the effectiveness of the proposed distributed Kalman filtering algorithm.