A novel robotic 6DOF pose measurement strategy for large-size casts based on stereo vision

Abstract

Purpose This paper aims to study six degrees-of-freedom (6DOF) pose measurement of reflective metal casts by machine vision, analyze the problems existing in the positioning of metal casts by stereo vision sensor in unstructured environment and put forward the visual positioning and grasping strategy that can be used in industrial robot cell. Design/methodology/approach A multikeypoints detection network Binocular Attention Hourglass Net is constructed, which can complete the two-dimensional positioning of the left and right cameras of the stereo vision system at the same time and provide reconstruction information for three-dimensional pose measurement. Generate adversarial networks is introduced to enhance the image of local feature area of object surface, and the three-dimensional pose measurement of object is completed by combining RANSAC ellipse fitting algorithm and triangulation method. Findings The proposed method realizes the high-precision 6DOF positioning and grasping of reflective metal casts by industrial robots; it has been applied in many fields and solves the problem of difficult visual measurement of reflective casts. The experimental results show that the system exhibits superior recognition performance, which meets the requirements of the grasping task. Research limitations/implications Because of the chosen research approach, the research results may lack generalizability. The proposed method is more suitable for objects with plane positioning features. Originality/value This paper realizes the 6DOF pose measurement of reflective casts by vision system, and solves the problem of positioning and grasping such objects by industrial robot.