A Cloud-based Network of 3D Objects for Robust Grasp Planning

Sergey Muravyov, Andrey Filchenkov

Abstract: Recent developments in the field of robot grasping have shown great improvements in the grasp success rates when dealing with unknown objects. In this work we improve on one of the most promising approaches, the Grasp Quality Convolutional Neural Network (GQ-CNN) trained on the DexNet 2.0 dataset. We propose a new GG-CNN architecture for DexNet, provide a new way for dataset generation for the GG-CNN and describe practical improvements that increase the model validation accuracy and other performance aspects of the whole system