Direction Kernels: using a simplified 3D model representation for grasping

Humans decide how to carry out a spontaneous interaction with an object by using the whole geometric information obtained from their eyes. The aim of this paper is to present how our object representation model MWS (Adan in Comput Vis Image Underst 79:281-307, 2000) can help a robot manipulator to make a single and reliable interaction. The contribution of this paper is particularly focused on the grasp synthesis stage. The main idea is that the grasping system, through MWS, can use non-strict-local features of the contact points to find a consistent grasping configuration. The Direction Kernels (DK) concept, which is integrated into the MWS model, is used to define a set of candidate contact-points and interaction regions. The set of DK is a global feature which represents the principal normal vectors of the object and their relative weight in a three-connectivity mesh model. Our method calculates the optimal grasp points (which are ordered according to the quality function) for two-finger grippers, whilst maintaining the requirements of force closure and safety of the grasp. Our strategy has been extensively tested on real free-shape objects using a 6 DOF industrial robot.