Self-localization of mobile robot using omni-directional vision

Abstract

This paper describes self-localization of mobile robot in outdoor environment. Our robot uses omni-directional vision system to archive efficient self-localization. This vision system acquires the visible information of all direction views. The robot uses feature of landmarks whose size is bigger than that of others in image such as building, sculptures, placard etc. Robot uses vertical edges and those merged regions as the feature. After acquiring the feature, robot must compare with them in order to know the same landmark fair between two images. To get more robustness in landmark matching procedure, robot uses the geometrical constraints within omni-directional images. The experiments implemented our campus and achieved the efficient self-localization result using robust landmark matching method.