Abstract
In this paper, we propose a reliable method for view-based navigation of mobile robots fully improved in positional accuracy by using feature-points extracted by SURF, and it is verified from the navigation experiments of them. View-based navigations that have used block matching method are not enough in positional accuracy for robots to avoid obstacles and pass narrow doorways. By applying SURF that is stable to illumination and scale changes in an image to the method for view-based navigation, the navigation for robots becomes more robust to variable indoor conditions. In experiments conducted in an indoor corridor with a robot for comparing the proposed method to conventional one, the positional precision was obtained in centimeter-order of within 10.0[cm]. In this view, it suggests that the proposed method is applied to the view-based navigation for robots in such narrow areas as obstacle avoidance and corridors.
