Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps
Machine Learning
2018-02-19 v1 Artificial Intelligence
Robotics
Machine Learning
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 architecture for the GQ-CNN and describe practical improvements that increase the model validation accuracy from 92.2% to 95.8% and from 85.9% to 88.0% on respectively image-wise and object-wise training and validation splits.
Cite
@article{arxiv.1802.05992,
title = {Improved GQ-CNN: Deep Learning Model for Planning Robust Grasps},
author = {Maciej Jaśkowski and Jakub Świątkowski and Michał Zając and Maciej Klimek and Jarek Potiuk and Piotr Rybicki and Piotr Polatowski and Przemysław Walczyk and Kacper Nowicki and Marek Cygan},
journal= {arXiv preprint arXiv:1802.05992},
year = {2018}
}
Comments
6 pages, 3 figures