Grasping bulky objects with two anthropomorphic hands

Abstract

This paper presents an algorithm to compute precision grasps for bulky objects using two anthropomorphic hands. We use objects modeled as point clouds obtained from a sensor camera or from a CAD model. We process the point clouds dividing them into two set of slices, one for each hand, where we look for sets of triplets of points. Each triplet must accomplish some physical conditions based on the structure of the hands. Then, triplets of points from each set of slices are evaluated to find a combination that satisfies the force closure condition (FC). Once one valid couple of triplets have been found the inverse kinematics of the system is computed in order to know if the points are kinematically reachable by the hands, if so, motion planning and a collision check are performed to asses if the grasp configuration of the system is suitable. The paper includes application examples of the proposed approach.