A common 3-finger grasp search algorithm for a set of planar objects

This work proposes an algorithm for designing a simple End Effector configuration for a robotic arm which is able to grasp a given set of objects. The algorithm searches for a common 3-finger grasp over a set of objects. The search algorithm maps all possible grasps for each object which satisfy a quality criterion and takes into account an external wrench (force and torque) applied to the object. The mapped grasps are represented by feature vectors in a high-dimensional space. This feature vector describes the shape of the gripper. We then generate a database of all possible grasps for each object represented as points in the feature vector space. Then we use another search algorithm for intersecting all points over the entire sets and finding common points suitable for all objects. Each point (feature vector) is the grasp configuration for a group of objects, which implies for the end-effector design. The final step classifies the grasps found to subsets of the objects, according to the common points found, this with preference to find one grasp to all the objects. The algorithm will be useful for assembly line robots in reducing end-effector design time, end-effector manufacturing time and final product cost.