Outdoor mobile robot localization using Hausdorff distance-based matching between COAG features of elevation maps and laser range data

Abstract

Mobile robot localization is the task of estimating the robot pose in a given environment. Among many localization techniques, Monte Carlo localization (MCL) is known to be one of the most reliable methods for pose estimation of a mobile robot. However, as outdoor environments are large and contain many complex objects, it is difficult to robustly estimate the robot pose using MCL in outdoor environments. Therefore, this study proposes a novel approach, the Hausdorff distance-based matching method using the objects commonly observed from air and ground (COAG) features for outdoor MCL algorithm. The Hausdorff distance is exploited to measure the similarity between the COAG features extracted from the robot and the elevation map. The experimental results in real environments show that the success rate of outdoor MCL increases and the proposed method is useful for robust outdoor localization using an elevation map.