Inverse Covariance Intersection Fusion of Multiple Estimates

Linear fusion of estimates is a basic tool for combining probabilistic data. If the correlation of estimation errors is unknown, the fusion performance is evaluated with respect to the worst case. Inverse Covariance Intersection fusion is a rule for combining two estimates with partially known crosscorrelation matrix. This paper generalises the rule to fusing multiple estimates. First, the generalised assumption and the essential theory are presented. A suboptimal solution with a simple parametrisation is derived next and it is shown to be better than the solution for unknown correlation. Finally, a recursive fusion of multiple estimates is designed.