Distributed consensus-based unscented Kalman filtering with missing measurements

In this paper, the state estimation problem is investigated for a class of nonlinear stochastic systems. In order to deal with the effects of missing measurements, a consensus-based unscented Kalman filtering algorithm is presented on the basis of distributed sensor networks. Moreover, a sufficient condition is derived to ensure that the estimate error is bounded in mean square. Finally, simulation results show that the proposed filters can estimate the true state of the target plant under undesirable conditions.