Method of Object Identification Using Joint Data of Multi-Joint Robotic Gripper for Bin-picking

Abstract

ARTICLE INFO ABSTRACTArticle history:In this study, we propose an object identification method for bin-picking developed for industrial robots. We identify the grasp posture and the associated geometric parameters of grasp objects using the joint data of a robotic gripper.Prior to grasp identification, we analyze the grasping motion in a low-dimensional space using principle component analysis (PCA) to reduce the dimensions. We collected the joint data from a human hand to demonstrate the grasp-identification algorithm. For data acquisition of the human grasp data, we conducted additional research on the motion characteristics of a human hand. We explain the method for using the algorithm of grasp identification for bin-picking. Finally, we present a subject for future research using our proposed algorithm of grasp model and identification.