Workpiece Posture Measurement and Intelligent Robot Grasping Based on Monocular Vision

Abstract

Industrial robots have been widely applied in grasping static workpieces, but the measurement method for the three-dimensional position of known specifications and random location of online workpieces still cannot meet the application requirements of the industrial field. In this paper, system structure and installation design of hardware were introduced firstly. Then, image pre-processing and feature extraction were established, composing of image enhancement, image smooth, edge detection, corner detection and angle calculation. Finally, a monocular vision-guided robot grasping device platform was established as well as corresponding software control platform. Experimental results indicated that the monocular vision system could quickly identify the workpiece pose with high measurement accuracy and that the robot could successfully grasp random location workpieces.