PT Unknown
AU Angel Valencia
   Roger Idrovo
   Angel Sappa
   Douglas Plaza
   Daniel Ochoa
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
PY 2017
DI 10.1109/ECMSM.2017.7945886
AB 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.
ER