Inferring laser-scan matching uncertainty with conditional random fields

This paper proposes a novel algorithm for computing robot motion estimates from ranging sensors. The algorithm utilises the recently proposed CRF-Matching procedure which matches laser scans based on shape descriptors. The motion estimates are computed in a sound probabilistic framework by performing inference on a probabilistic graphical model. The Sampling-Product inference algorithm is proposed for obtaining probable association hypothesis from the probabilistic model. The hypothesis are used to generate estimates on the uncertainty of translational and rotational movements of the mobile robot. Experiments demonstrate the benefits of the approach on simulated data sets and on laser scans from an urban environment. The approach is also combined with the well-established delayed-state information filter for a large-scale outdoor simultaneous localisation and mapping task.