Planning four grasping points from images of planar objects

This paper describes a method for the determination of the four grasping points that are necessary to get a force closure grasp for a planar object considering frictionless contacts. The geometric model of the object is assumed to be unknown. The proposed approach starts from the object boundary obtained from the binary digitalization of an object image, and then uses the dual representation of forces and the dual-force space span for the determination of the grasping points.