TY - CONF AU - Angel Valencia AU - Roger Idrovo AU - Angel Sappa AU - Douglas Plaza AU - Daniel Ochoa A2 - ECMSM PY - 2017// TI - A 3D Vision Based Approach for Optimal Grasp of Vacuum Grippers BT - IEEE International Workshop of Electronics, Control, Measurement, Signals and their application to Mechatronics N2 - In general, robot grasping approaches are based on the usage of multi-finger grippers. However, when large size objects need to be manipulated vacuum grippers are preferred, instead of finger based grippers. This paper aims to estimate the best picking place for a two suction cups vacuum gripper,when planar objects with an unknown size and geometry are considered. The approach is based on the estimation of geometric properties of object’s shape from a partial cloud of points (a single 3D view), in such a way that combine with considerations of a theoretical model to generate an optimal contact pointthat minimizes the vacuum force needed to guarantee a grasp.Experimental results in real scenarios are presented to show the validity of the proposed approach. L1 - http://refbase.cvc.uab.es/files/VIS2017.pdf N1 - ADAS; 600.086; 600.118 ID - Angel Valencia2017 ER -