Virtual robot teaching for humanoid hand robot using muti-fingered haptic interface

This paper presents a virtual robot teaching, consisting of human demonstration and motion-intention analysis in a virtual reality environment using a multi-fingered haptic interface which can displays 3D forces to operator´s fingertips. The position and orientation of the robot hand are determined so as to maximize the robot hand´s manipulability. In the segmentation method, human motion data consisting of contact points, 3D grasp force, hand and object position, and the like are segmented into plural primitive motions and the type of task is analyzed based on the sequence of the primitive motions. The use of multi-fingered haptic interface robot HIRO II provides new primitive motions such as Press and Follow because measured 3D forces are used to estimate a contact between the grasped object and the other object, which allow new tasks such as a pick and follow task. A trial task using a humanoid robot hand named Gifu Hand III is shown to demonstrate the effectiveness of the proposed method.