Abstract. The localization capability of a mobile robot is central to basic navigation and map building tasks. We describe a probabilistic environment model which facilitates global localization scheme by means of location recognition. In the exploration stage the environment is partitioned into several locations, each characterized by a set of scale-invariant keypoints. The descriptors associated with these keypoints can be robustly matched despite the changes in contrast, scale and affine distortions. We demonstrate the efficacy of these features for location recognition, where given a new view the most likely location from which this view came is determined. The misclassifications due to dynamic changes in the environment or inherent location appearance ambiguities are overcome by exploiting the location neighborhood relationships captured by a Hidden Markov Model. We report the recognition performance of this approach in an indoor environment consisting of eighteen locations and discuss the suitability of this approach for a more general class of recognition

The capability of maintaining the pose of the mobile robot is central for basic navigation and map building tasks. In this paper we describe a vision-based hybrid localization scheme based on scale-invariant keypoints. In the first stage the topological localization is accomplished by matching the keypoints detected in the current view with the database of model views. Once the best match has been found, the relative pose between the model view and the current image is recovered. We demonstrate the efficiency of the location recognition approach and present a closed form solution to the relative pose recovery for the case of planar motion and unknown focal length of the camera. The approach is demonstrated on several examples of indoors environments. 1. Introduction and Related