Calibrating human hand for teleoperating the HIT/DLR hand

Abstract

Using human action to guide robot execution can greatly reduce the planning complexity. We calibrate a human hand model and map its motion to a four-finger dexterous robot hand. The parameters of human hand model are determined by open-loop kinematic calibration method based on a vision system. We analyze the kinematic difference between the human hand and dexterous robot hand, and present a modified fingertip mapping to solve the partial overlap of the fingertip workspaces. 3D graphic simulation and manipulation experiments show that the accuracy of the human hand model and the mapping method are sufficiently precise for teleoperation tasks.