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

Automatic Generation of Realistic Training Data for Learning Parallel-jaw Grasping from Synthetic Stereo Images

Drögemüller, Justus and Garcia, Carlos X. and Gambaro, Elena and Suppa, Michael and Steil, Jochen and Roa Garzon, Máximo Alejandro (2021) Automatic Generation of Realistic Training Data for Learning Parallel-jaw Grasping from Synthetic Stereo Images. IEEE Int. Conf. Advanced Robotics, 7-10 Dec 2021, Slovenia.

[img] PDF
501kB

Abstract

This paper proposes a novel approach to automatically generate labeled training data for predicting parallel-jaw grasps from stereo-matched depth images. We generate realistic depth images using Semi-Global Matching to compute disparity maps from synthetic data, which allows producing images that mimic the typical artifacts from real stereo matching in our data, thus reducing the gap from simulation to real execution. Our pipeline automatically generates grasp annotations for single or multiple objects on the synthetically rendered scenes, avoiding any manual image pre-processing steps such as inpainting or denoising. The labeled data is then used to train a CNN-model that predicts parallel-jaw grasps, even in scenarios with large amount of unknown depth values. We further show that scene properties such as the presence of obstacles (a bin, for instance) can be added to our pipeline, and the training process results in grasp prediction success rates of up to 90%

Item URL in elib:https://elib.dlr.de/147156/
Document Type:Conference or Workshop Item (Speech)
Title:Automatic Generation of Realistic Training Data for Learning Parallel-jaw Grasping from Synthetic Stereo Images
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Drögemüller, JustusTechnical University of BraunschweigUNSPECIFIED
Garcia, Carlos X.Technical University of MunichUNSPECIFIED
Gambaro, ElenaRoboceptionUNSPECIFIED
Suppa, MichaelMichael.Suppa (at) dlr.dehttps://orcid.org/0000-0002-7362-9534
Steil, JochenTechnische Universität BraunschweigUNSPECIFIED
Roa Garzon, Máximo AlejandroMaximo.Roa (at) dlr.dehttps://orcid.org/0000-0003-1708-4223
Date:December 2021
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:grasp prediction, grasp learning
Event Title:IEEE Int. Conf. Advanced Robotics
Event Location:Slovenia
Event Type:international Conference
Event Dates:7-10 Dec 2021
Organizer:IEEE
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Autonomy & Dexterity [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Autonomy and Teleoperation
Deposited By: Roa Garzon, Dr. Máximo Alejandro
Deposited On:10 Dec 2021 00:12
Last Modified:10 Dec 2021 00:12

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.