High-precision six-degree-of-freedom pose measurement and grasping system for large-size object based on binocular vision

Purpose The positioning and grasping of large-size objects have always had problems of low positioning accuracy, slow grasping speed and high application cost compared with ordinary small parts tasks. This paper aims to propose and implement a binocular vision-guided grasping system for large-size object with industrial robot. Design/methodology/approach To guide the industrial robot to grasp the object with high position and pose accuracy, this study measures the pose of the object by extracting and reconstructing three non-collinear feature points on it. To improve the precision and the robustness of the pose measuring, a coarse-to-fine positioning strategy is proposed. First, a coarse but stable feature is chosen to locate the object in the image and provide initial regions for the fine features. Second, three circular holes are chosen to be the fine features whose centers are extracted with a robust ellipse fitting strategy and thus determine the precise pose and position of the object. Findings Experimental results show that the proposed system has achieved high robustness and high positioning accuracy of −1 mm and pose accuracy of −0.5 degree. Originality/value It is a high accuracy method that can be used for industrial robot vision-guided and grasp location.