elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from RGB

Ainetter, Stefan and Fraundorfer, Friedrich (2021) End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from RGB. In: 2020 IEEE International Conference on Robotics and Automation, ICRA 2021, pp. 13452-13458. 2021 IEEE International Conference on Robotics and Automation (ICRA), 30. May - 5. June 2021, Xi'an, China. doi: 10.1109/ICRA48506.2021.9561398. ISBN 978-166543678-6.

[img] PDF
2MB

Official URL: https://ieeexplore.ieee.org/document/9561398

Abstract

In this work, we introduce a novel, end-to-end trainable CNN-based architecture to deliver high quality results for grasp detection suitable for a parallel-plate gripper, and semantic segmentation. Utilizing this, we propose a novel refinement module that takes advantage of previously calculated grasp detection and semantic segmentation and further increases grasp detection accuracy. Our proposed network delivers state-of-the-art accuracy on two popular grasp dataset, namely Cornell and Jacquard. As additional contribution, we provide a novel dataset extension for the OCID dataset, making it possible to evaluate grasp detection in highly challenging scenes. Using this dataset, we show that semantic segmentation can additionally be used to assign grasp candidates to object classes, which can be used to pick specific objects in the scene.

Item URL in elib:https://elib.dlr.de/146134/
Document Type:Conference or Workshop Item (Speech)
Title:End-to-end trainable deep neural network for robotic grasp detection and semantic segmentation from RGB
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Ainetter, Stefanicg.tugraz.atUNSPECIFIED
Fraundorfer, Friedrichfriedrich.fraundorfer (at) dlr.dehttps://orcid.org/0000-0002-5805-8892
Date:2021
Journal or Publication Title:2020 IEEE International Conference on Robotics and Automation, ICRA 2021
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI :10.1109/ICRA48506.2021.9561398
Page Range:pp. 13452-13458
ISBN:978-166543678-6
Status:Published
Keywords:Deep learning, Automation, Conferences, Semantics, Feature extraction, Convolutional neural networks, Grippers
Event Title:2021 IEEE International Conference on Robotics and Automation (ICRA)
Event Location:Xi'an, China
Event Type:international Conference
Event Dates:30. May - 5. June 2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Optical remote sensing, R - Artificial Intelligence
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Knickl, Sabine
Deposited On:25 Nov 2021 11:15
Last Modified:25 Nov 2021 11:15

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.