Visual Navigation Based on View-Sequenced Route Representation.

摘要

Previous work in vision-based mobile robot has been lacking models of the route which can be utilized for recognition of (1) position identification, (2) steering direction determination, and (3) obstacle detection, simultaneously. In this paper, we propose a new visual representation of the route, the“View-Sequenced Route Representation (VSRR) .”A VSRR is a non-metrical model of the route, which contains a sequence of front view images along a route memorized in the recording run. In the autonomous navigation, the three types of recognition described above are achieved in real-time by matching between the current view image and the memorized view sequence using correlation technique. We also developed an easy procedure for acquiring VSRRs, and a quick control procedure using VSRRs. The VSRR is especially useful for representing routes in the corridors. Experimental results of autonomous navigation using a two-wheeled robot in a real corridor are presented.