Constructing a Simple Visually-Guided Robotic Part-Grasping System with Off-the-Shelf Components

Abstract

A novel approach to grasping and recognizing parts in an industrial robotic work cell is presented in this paper. The centroid, orientation, and length of elongated parts lying on a flat work area are estimated by a sequence of simple algorithms. Off-the-shelf components and freely downloadable software APIs make this system inexpensive and easily implemented. The approach has been implemented and tested with a Staubli RX60 manipulator. Results and future research are presented