A combined 2D-3D vision system for automatic robot picking

Abstract

This paper presents a new vision technique for an industrial robot to pick up randomly placed workpieces. The proposed approach combines 2D and 3D vision for efficiently determining the spatial position of a target object in cluttered scenes. 2D vision permits to quickly detect and locate objects of interest, thus reducing significantly the processing time. The location of an extracted 2D region (a detected object) is then passed to the 3D vision module to determine its world coordinate. Finally the 3D position information is sent to the robot manipulator for automatic picking. The test results show the effectiveness of the proposed system.