Sample greedy gossip distributed Kalman filter

This paper investigates the problem of distributed state estimation over a low-cost sensor network and proposes a new sample greedy gossip distributed Kalman filter. The proposed algorithm leverages the information weighted fusion concept and the sample greedy gossip averaging protocol. By introducing a stochastic sampling strategy in the greedy sensor node selection process, the proposed algorithm finds a suboptimal communication path for each local sensor node during the process of information exchange. Theoretical analysis on global convergence and uniform boundedness is also performed to investigate the characteristics of the proposed distributed Kalman filter. The main advantage of the proposed algorithm is that it provides well trade-off between communication burden and estimation performance. Extensive empirical numerical simulations are carried out to demonstrate the effectiveness of the proposed algorithm.