Navigation control of a mobile robot based on active vision

Abstract

The authors describe a navigational control method for a mobile robot based on active vision. The method controls the navigation guidance of the robots in real time by using the active vision system. Active vision based on a knowledge-based system plays an intelligent role in applying artificial intelligence to a robot visual system. A computational approach to accomplish the integration of depth estimation schemes is presented. Surface estimation of an object and obstacle avoidance are estimated by using optical flow and vergence. The result of the estimation shows that gaze control and camera translation have some problems. Mathematical equations and heuristics are described. A mathematical mechanism for navigation control is considered.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>