Mobile Robot Localization Based on an Omnidirectional Stereoscopic Vision Perception System

This paper presents a system of absolute localization based on the stereoscopic omnidirectional vision. To do it we use an original perception system which allows our omnidirectional vision sensor SYCLOP to move along a rail. The first part of our study will deal with the problem of building the sensorial model with the help of the two stereoscopic omnidirectional images. To solve this problem we propose an approach based on the fusion of several criteria which will be made according to Dempster-Shafer rules. As for the second part, it will be devoted to exploiting this sensorial model to localize the robot thanks to matching the sensorial primitives with the environment map. We analyze the performance of our global absolute localization system on several robot’s elementary moves, in different environments.