Grasping unknown objects based on 2½D range data

The problem of grasping novel objects in a fully automatic way has gained increasing importance. In this work we consider the problem of grasping novel objects with the help of a laser range scanner. This includes autonomous object detection and grasp motion planning. The used system consists of a fixed working station equipped with a laser range scanner, a seven degrees of freedom manipulator and a hand prosthesis as gripper. We present a method for segmentation of a 2frac12D point cloud into parts, assembly of parts into objects and calculation of grasping points, which works for cylindrical objects and arbitrary objects. We successfully demonstrate this approach by grasping a variety of different shapes and present a step towards full automation.