Active vision-based control schemes for autonomous navigation tasks

Abstract

This paper deals with active-vision-based practical control schemes for collision avoidance as well as maintenance of clearance in a-priori unknown textured environments. These control schemes employ a visual motion cue, called the visual threat cue (VTC) as a sensory feedback signal to accomplish the desired tasks. The VTC provides some measure for a relative change in range as well as clearance between a 3D surface and a moving observer. It is a collective measure obtained directly from the raw data of gray level images, is independent of the type of 3D surface texture. It is measured in [time −1] units and needs no 3D reconstruction. The control schemes are based on a set of If–Then fuzzy rules with almost no knowledge about the vehicle dynamics, speed, heading direction, etc. They were implemented in real-time using a 486-based Personal Computer and a camera capable of undergoing 6-DOF motion.