Estimating and Exploiting the Degree of Independent Information in Distributed Data Fusion

Double counting is a major problem in distributed data fusion systems. To maintain flexibility and scalability, distributed data fusion algorithms should just use local information. However globally optimal solutions only exist in highly restricted circumstances. Suboptimal algorithms can be applied in a far wider range of cases, but can be very conservative. In this paper we present preliminary work to develop distributed data fusion algorithms that can estimate and exploit the correlations between the estimates stored in different nodes in a distributed data fusion network. We show that partial information can be modelled as kind of "overweighted"' Covariance Intersection algorithm. We motivate the need for an adaptive scheme by analysing the correlation behaviour of a simple distributed data fusion network and show that it is complicated and counterintuitive. Two simple approaches to estimate the correlation structure are presented and their results analysed. We show that significant advantages can be obtained.