Mobile robot localization by GPS and sequential appearance-based place recognition

Abstract

In this paper, we propose a mobile robot localization by GPS observations and appearance-based place recognition. These are critical issues for achieving a high accuracy and stable localization due to some challenging problems that GPS observations face still such as multipath and signal lost, especially under situations where there are narrow streets and so on. The appearance-based place recognition method that is combined with positional information has capability to overcome the issue. We apply both of observations derived from GPS and appearance-based place recognition to a mobile robot localization for the sake of achieving robust localization. Moreover sequential appearance-based place recognition makes it possible to recognize their own position even when we navigate a robot on a night. Our system uses not only multiple observations but also dead reckoning with gyrodometry model. To verify the validity of the proposed method, our experiment is conducted through an outdoor course.