Visual navigation of a mobile robot integrating an heading sensor

Abstract

Visual navigation is the ability of a mobile robot to determine its position (relative or absolute) in the environment using visual sensors such as TV cameras. A goal-oriented autonomous mobile robot is a vehicle able to plan a path from its current position to a predefined goal and to navigate on the planned path, determining continuously its location, in order to verify if the route is correctly followed. We propose a visual self-location method to determine the vehicle location, based on cooperation of an heading sensor and a CCD TV camera. The approach is straightforward and suitable for real time performance on general purpose hardware. Experimental results are provided by implementation on our autonomous mobile vehicle SAURO.