Planning High-Quality Grasps Using Mean Curvature Object Skeletons

Abstract

In this letter, we present a grasp planner that integrates two sources of information to generate robust grasps for a robotic hand. First, the topological information of the object model is incorporated by building the mean curvature skeleton and segmenting the object accordingly in order to identify object regions which are suitable for grasping. We show how this information can be used to derive different grasping strategies, which also allows to distinguish between precision and power grasps. Second, the local surface structure is investigated to construct feasible and robust grasping poses by aligning the hand according to the local object shape. We apply the approach to a wide variety of object models of the KIT and the YCB real-world object model databases and evaluate it with several robotic hands. The results show that the skeleton-based grasp planner is capable to generate high-quality grasps in an efficient manner. In addition, we evaluate how robust the planned grasps are against hand positioning errors as they occur in real-world applications due to perception and actuation inaccuracies. The evaluation shows that the majority of the generated grasps are of high quality since they can be successfully applied even when the hand is not exactly positioned.