STEREO VISION-BASED 3D LOCALIZATION OF KNOWN OBJECTS AND GRASPING USING ROBOT ARM

Abstract

The goal of this thesis is to develop an automated system for object picking and sorting. The developed system mainly consists of a customized vision system, PC, robot arm position controller, serial communication connections and robot which is five-axis articulated robot arm. The customized vision system feeds the scene images ahead of the robot arm to the PC, a computer vision algorithm on the PC receive the fed images. The computer vision algorithm process and extract the needed data for the system. Meanwhile due to use of customized stereo vision with low-end cameras a particle swarm optimization has been employed to minimize the estimated object coordinates error. The vision system is employed to perform two tasks.