Range scan-based localization methods for mobile robots in complex environments

Abstract

The work introduces design and comparison of different-brand methods for position localization of indoor mobile robots. Both the methods derive the robot relative position from a structure of the working environment based on measurements gathered by a TOF-based laser ranging system. The first presented method applies statistical description of the scene while the other one relies on a feature-based matching approach. Both the approaches provide method-specific behavior, which has been recognized in experiments with real data. The obtained results are compared and further improvements of the localization robustness via their combination are discussed.