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

Rock Instance Segmentation from Synthetic Images for Planetary Exploration Missions

Boerdijk, Wout and Müller, Marcus Gerhard and Durner, Maximilian and Sundermeyer, Martin and Friedl, Werner and Gawel, Abel and Stürzl, Wolfgang and Marton, Zoltan-Csaba and Siegwart, Roland and Triebel, Rudolph (2021) Rock Instance Segmentation from Synthetic Images for Planetary Exploration Missions. In: 2021 IEE/RSJ International Conference on Intelligent Robots and Systems, IROS (Workshops). Advances in Space Robotics and Back to Earth (IROS WS), 01 Oct 2021, Prague (online).

[img] PDF
3MB
[img] PDF
3MB

Official URL: https://sites.google.com/view/spacerobots2021/home

Abstract

As the complexity and operation distance of space missions rises, the demand of highly autonomous rovers increases as well. An aspect of autonomous rovers that has been specifically attracting much attention from the space community is semi-autonomous sampling from celestrial bodies. Detecting possible samples is important for their extraction, which is challenging due to the unstructured and unknown enviroment, and the lack of suitable datasets. This work addresses the task of sample collection in an unknown and unstructured environment by presenting a module for visual stone segmentation. Due to the limited training data for such scenarios, we apply a photo-realistic simulator to optimize an unknown instance segmentation network. We evaluate various manners of fine-tuning and show the positive effect of training on data highly related to the test data.

Item URL in elib:https://elib.dlr.de/144626/
Document Type:Conference or Workshop Item (Poster, Other)
Title:Rock Instance Segmentation from Synthetic Images for Planetary Exploration Missions
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Boerdijk, WoutWout.Boerdijk (at) dlr.dehttps://orcid.org/0000-0003-0789-5970
Müller, Marcus GerhardMarcus.Mueller (at) dlr.dehttps://orcid.org/0000-0003-4283-6693
Durner, MaximilianMaximilian.Durner (at) dlr.dehttps://orcid.org/0000-0001-8885-5334
Sundermeyer, Martinmartin.sundermeyer (at) dlr.dehttps://orcid.org/0000-0003-0587-9643
Friedl, WernerWerner.Friedl (at) dlr.dehttps://orcid.org/0000-0003-3002-7274
Gawel, AbelAutonomous Systems Lab, ETH ZurichUNSPECIFIED
Stürzl, WolfgangWolfgang.Stuerzl (at) dlr.dehttps://orcid.org/0000-0003-2440-5857
Marton, Zoltan-CsabaZoltan.Marton (at) dlr.dehttps://orcid.org/0000-0002-3035-493X
Siegwart, RolandAutonomous Systems Lab, ETH ZurichUNSPECIFIED
Triebel, Rudolphrudolph.triebel (at) dlr.dehttps://orcid.org/0000-0002-7975-036X
Date:1 October 2021
Journal or Publication Title:2021 IEE/RSJ International Conference on Intelligent Robots and Systems, IROS (Workshops)
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Planetary Exploration Simulation Instance Segmentation
Event Title:Advances in Space Robotics and Back to Earth (IROS WS)
Event Location:Prague (online)
Event Type:Workshop
Event Dates:01 Oct 2021
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 - Multisensory World Modelling (RM) [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Perception and Cognition
Institute of Robotics and Mechatronics (since 2013) > Mechatronic Systems
Institute of Robotics and Mechatronics (since 2013)
Deposited By: Durner, Maximilian
Deposited On:19 Oct 2021 10:42
Last Modified:19 Oct 2021 10:42

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.