Authors : Robinson Jimenez Moreno, Mauricio Mauledoux and B. Javier Martinez
Abstract: The following study presents the development of an algorithm for the detection of the grasp point for an object using gripper. The algorithm receives as input a white background image of the object to be grasped as well as the dimensions of the gripper in pixels. Also, the grip parameters are defined that will allow to discard those sections of the object that the gripper cannot take, parameters such as the minimum and maximum thickness of the admissible grip section in order to prevent the fit between the gripper and the object section being too loose or too tight, the thickness of the tips of the gripper is taken as a parameter to avoid collisions and the maximum degree of inclination between the object section and the surface of the gripper, so that, in the adjustment between both, the object does not move too much. It was possible to obtain an algorithm that allows to achieve a suitable point for taking objects in all cases evaluated, however, because of the distance from the center of gravity of the object it requires a higher strength for its grasp.
Robinson Jimenez Moreno, Mauricio Mauledoux and B. Javier Martinez, 2018. Algorithm for Object Grasp Detection. Research Journal of Applied Sciences, 13: 162-175.