Vision-based localization for mobile platforms

In this paper, we describe methods to localize a mobile robot in an indoor environment from visual information. An appearance-based approach is adopted in which the environment is represented by a large set of images from which features are extracted. We extended the appearance based approach with an active vision component, which fits well in our probabilistic framework. We also describe another extension, in which depth information is used next to intensity information. The results of our experiments show that a localization accuracy of less then 50 cm can be achieved even when there are un-modeled changes in the environment or in the lighting conditions.