Konrad, Anna and McDonald, John and Villing, Rudi (2022) VGQ-CNN: Moving Beyond Fixed Cameras and Top-Grasps for Grasp Quality Prediction. International Joint Conference on Neural Networks (IJCNN) 2022. ISSN 978-1-7281-8671-9

Preview

Download (550kB) | Preview

Abstract

We present the Versatile Grasp Quality Convo- lutional Neural Network (VGQ-CNN), a grasp quality pre- diction network for 6-DOF grasps. VGQ-CNN can be used when evaluating grasps for objects seen from a wide range of camera poses or mobile robots without the need to retrain the network. By defining the grasp orientation explicitly as an input to the network, VGQ-CNN can evaluate 6-DOF grasp poses, moving beyond the 4-DOF grasps used in most image- based grasp evaluation methods like GQ-CNN. To train VGQ- CNN, we generate the new Versatile Grasp dataset (VG-dset) containing 6-DOF grasps observed from a wide range of camera poses. VGQ-CNN achieves a balanced accuracy of 82.1% on our test-split while generalising to a variety of camera poses. Meanwhile, it achieves competitive performance for overhead cameras and top-grasps with a balanced accuracy of 74.2% compared to GQ-CNN’s 76.6%. We also propose a modified network architecture, Fast-VGQ-CNN, that speeds up inference using a shared encoder architecture and can make 128 grasp quality predictions in 12ms on a CPU. Code and data are available at https://aucoroboticsmu.github.io/vgq-cnn/

Item Type:	Article
Keywords:	VGQ-CNN; Fixed Cameras; Top-Grasps; Grasp Quality Prediction;
Academic Unit:	Faculty of Science and Engineering > Computer Science Faculty of Science and Engineering > Electronic Engineering Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	16564
Identification Number:	https://doi.org/10.1109/IJCNN55064.2022.9892763
Depositing User:	John McDonald
Date Deposited:	22 Sep 2022 11:19
Journal or Publication Title:	International Joint Conference on Neural Networks (IJCNN) 2022
Publisher:	IEEE
Refereed:	Yes
URI:	Publisher
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads