Distributed state estimation for heterogeneous mobile sensor networks with stochastic observation loss

The problem of distributed fusion and random observation loss for mobile sensor networks is investigated herein. In view of the fact that the measured values, sampling frequency and noise of various sensors are different, the observation model of a heterogeneous network is constructed. A binary random variable is introduced to describe the drop of observation component and the topology switching problem caused by complete observation loss is also considered. A cubature information filtering algorithm is adopted to design local filters for each observer to suppress the negative effects of measurement noise. To derive a consistent and accurate estimation result, a novel weighted average consensus-based filtering approach is put forward. For the sensor that suffers from observation loss, its local prediction information vector is fused with the information contribution vectors of the neighbors to obtain the local estimation. Then the consensus weight matrix is designed for consensus-based distributed collaborative information fusion. The boundness of the estimation errors is proved by employing the stochastic stability theory. In the end, two numerical examples are offered to assert the validity of the presented method.