Observability analysis of SLAM using fisher information matrix

This paper presents a new technique for evaluating the observability of the simultaneous localization and mapping (SLAM) problem. The state vector of an estimation theoretic formulation of the SLAM problem is recast to include all robot poses from which the measurements are made. This converts SLAM to a problem of estimating a set of unknown, constant random variables. Fisher Information Matrix of the resulting static estimation problem is derived and analyzed to examine the observability of SLAM. Outcomes of the analysis and comparisons to the observability analysis presented in recent literature are presented. Proposed technique makes it possible to analyze the observability of a range of SLAM problems with ease.