Vision-based robot navigation in the 3D world

Abstract

The authors bring a robust approach to the solution of robot navigation in the 3-D environment utilizing visual information. The presented approach aims to enable a robot to process the scene image, gathered by a monocular camera, in order to recognize objects of the constrained 3-D environment. When the positions of the scene objects are known, the recognition process provides the information about robot position and orientation in the scene.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>