Qualitative vision for the guidance of legged robots in unstructured environments

摘要

Visual procedures especially tailored to the constraints and requirements of a legged robot are presented. They work for an uncalibrated camera, with pan and zoom, freely moving towards a stationary target in an unstructured environment that may contain independently moving objects. The goal is to dynamically analyse the image sequence in order to extract information about the robot motion, the target position and the environment structure. The development is based on the deformations of an active contour fitted to the target. Experimental results confirm that the proposed approach constitutes a promising alternative to the prevailing trend based on the costly computation of displacement or velocity fields.