Virtual teaching based on hand manipulability for multi-fingered robots

A virtual robot teaching that consists of human demonstration and motion-intention analysis in a virtual reality environment is an advanced technology of automatic programming for multi-fingered robots. For the virtual hand model displayed on-screen, a human-hand model is better than a robot-hand model in terms of teaching time and a stable manipulation of virtual object. However, it may occurs that a robot cannot grasp an object at a teaching position and orientation of the robot hand because the geometrical size and motional function of the robot hand is not the same as that of human hand. To solve this problem, we propose a virtual teaching based on hand manipulability, in which a position and orientation of the robot hand is determined so as to maximize a manipulability of the robot hand on the condition that the robot grasps the object at the teaching contact points on the object. Experimental results of a pick-and-place task are shown to demonstrate the effectiveness of the proposed method.