Fusion of dependent information in posegraphs

Abstract

In this paper, we consider the problem of fusing measurements which contain correlated noises within posegraph-based formulations of filtering and estimation problems. We develop a formulation of the Weighted Geometric Density (WGD) fusion algorithm, a generalisation of Covariance Intersection (CI), for posegraphs. We show that this form can generate covariance consistent estimates. We propose two methods for computing the weighting parameters by maximising the information or maximising the likelihood.