A real-time robust global localization for autonomous mobile robots in large environments

Global localization aims to estimate a robot's pose in a learned map without any prior knowledge of its initial pose. Achieving highly accurate global localization remains a challenge for autonomous mobile robots especially in large-scale unstructured outdoor environments. This paper introduces a real-time reliable global localization approach with the capability of addressing the kidnapped robot problem using only laser sensors. Our approach includes four steps: 1) local Simultaneous Localization and Mapping 2) map matching 3) position tracking and 4) localization quality evaluation. For sensor perception, we use occupancy grid method to represent robot environment. A novel pyramid grid-map based coarse-to-fine matching approach is proposed to improve the localization accuracy. Experimental results including an outdoor environment of 25, 000 m
²
are presented to validate the feasibility and reliability of the proposed approach.