2017 · 26 citations · 16 references
EngineeringComputer ScienceRobotics EngineeringComputer VisionGraspingRoboticsDexterous ManipulationGrasp DetectionGrasp PlanningManipulation PerceptionMulti-fingered GraspingPoint Cloud ProcessingContact Point OptimizationContact Point PlanningGraspGrasp Contact Point PredictionObjectsRobot GraspingVacuum Suction GrippersVision-based Grasp Planning
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 point that minimizes the vacuum force needed to guarantee a grasp. Experimental results in real scenarios are presented to show the validity of the proposed approach.
16
3D is here: Point Cloud Library (PCL)
Radu Bogdan Rusu, Steve Cousins · 2011 · 4.8K citations
Mind the gap - robotic grasping under incomplete observation
Jeannette Bohg, Matthew Johnson‐Roberson, Beatriz León et al. · 2011 · 109 citations · Full text