Pick-Up Motion Based on Vision and Tactile Information in Hand/Arm Robot

Abstract

A multi-fingered robot hand receives much attention in various fields. We have developed the multi-fingered robot hand with the multi-axis force/torque sensors. For stable transportation, the robot hand must pick up an object without dropping it and places it without damaging it. This paper deals with a pick-up motion based on vision and tactile information by the eveloped robot hand. Here, the robot hand learns a posture for picking an object up by using tactile values and the visual image in advance, then determines the number of fingers in pick-up motion by the visual image. The effectiveness of the proposed grasp selection is verified through some experiments with the universal robot hand.