Stereo vision based robotic bin picking system for agile manufacturing

Abstract

This research aims at conducting a fundamental analysis on developing a stereo vision system for an industrial robot to perform bin picking operations similar to a human way of bin picking.A Vision System and a set of artificial intelligence software can provide these capabilities to a robot to operate independently. The vision sensors of the robot capture the image of an object from among jumbled objects in a bin. The vision system analyses and processes the images to identify the top most object and computes its (X,Y,Z) co-ordinates. In bin picking applications, robots are required to pick up an object from a pile of stacked or scattered objects placed in a bin. To perform such tasks, identification of the objects to be picked using a vision system is indispensable. The proposed bin picking process consists of two modules namely object segmentation module and object localization module. In the segmentation module, Fourier descriptor algorithm is proposed for segmentation of topmost object and in the localization module, the location of the object is estimated by computing the 'x\ 'y', 'z'co-ordinates of the object midpoint using a unified stereo imaging algorithm.