Fast and automatic robotic grasping of unknown objects

Abstract

In this work, we present fast and automatic robotic grasping of unknown objects by minimum number of mobile robots. A 2D range sensor is installed on a mobile robot to acquire the partial shape information of unknown objects. The candidate grasping points of unknown objects are determined for fast grasping by extracting features from partial shape information directly. After grasping trial, whether an object can be lifted by a robot is judged. If the robot fails to lift the object, then detects other candidate grasping points and performs grasping trials until the object is lifted. The other mobile robot is needed to lift the object cooperatively if the object is not lifted after performing all candidate grasps. An object handling system consisting of a Gripper robot and a Lifter robot for object grasping and lifting is designed. Object measurement and the strategy for fast transition between stable states during lifting object are proposed. Experiments are conducted, and the results illustrate the validity of the proposed algorithm.