Object Detection Using Sim2Real Domain Randomization for Robotic Applications

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on robotics Ročník 39; číslo 2; s. 1225 - 1243
Hlavní autori:	Horvath, Daniel, Erdos, Gabor, Istenes, Zoltan, Horvath, Tomas, Foldi, Sandor
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.04.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Adaptation models Artificial neural networks Computational modeling Computer vision for automation Datasets Deep learning deep learning in robotics and automation Industrial applications localization Object detection Object recognition Randomization Robotics Robots Service robots sim2real knowledge transfer Synthetic data Task analysis Training
ISSN:	1552-3098, 1941-0468
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% <inline-formula><tex-math notation="LaTeX">\mathrm{{mAP}}_{50}</tex-math></inline-formula> scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.
AbstractList	Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% [Formula Omitted] scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints. Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% <inline-formula><tex-math notation="LaTeX">\mathrm{{mAP}}_{50}</tex-math></inline-formula> scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.
Author	Horvath, Daniel Erdos, Gabor Foldi, Sandor Istenes, Zoltan Horvath, Tomas
Author_xml	– sequence: 1 givenname: Daniel orcidid: 0000-0002-6450-5193 surname: Horvath fullname: Horvath, Daniel email: daniel.horvath@sztaki.hu organization: Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Eötvös Loránd Research Network, Budapest, Hungary – sequence: 2 givenname: Gabor orcidid: 0000-0002-3531-3803 surname: Erdos fullname: Erdos, Gabor email: erdos.gabor@sztaki.hu organization: Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Eötvös Loránd Research Network, Budapest, Hungary – sequence: 3 givenname: Zoltan orcidid: 0000-0002-0169-4791 surname: Istenes fullname: Istenes, Zoltan email: istenes@inf.elte.hu organization: CoLocation Center for Academic and Industrial Cooperation, Eötvös Loránd University, Budapest, Hungary – sequence: 4 givenname: Tomas orcidid: 0000-0002-9438-840X surname: Horvath fullname: Horvath, Tomas email: tomas.horvath@inf.elte.hu organization: Department of Data Science and Engineering, Eötvös Loránd University, Budapest, Hungary – sequence: 5 givenname: Sandor orcidid: 0000-0002-6573-0659 surname: Foldi fullname: Foldi, Sandor email: sandorfoldi98@gmail.com organization: Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Eötvös Loránd Research Network, Budapest, Hungary
BookMark	eNp9kEtLAzEUhYMo2Fb3gpsB11PznmRZWl9QKYx1HdJMIikzkzGZLvTXO33gwoWrc7l8597DGYPzNrQWgBsEpwhBeb8uV1MMMZ4SDAuO5BkYIUlRDikX58PMGM4JlOISjFPaQoiphGQEXlebrTV9trD9ID602Xvy7Uf25htcWl1ni9Bo32albqvQ-G99YFyIWRk2ofcmm3Vd7c1hn67AhdN1stcnnYD148N6_pwvV08v89kyN4SQPheGSEtxxQsOGbYWSiMkd4Vz2lbYCK6NcciYiiNqKswcZdQZgigzhdAVmYC749kuhs-dTb3ahl1sh48KF5IJyJmQA8WPlIkhpWidMr4_5Oyj9rVCUO2bU0Nzat-cOjU3GOEfYxd9o-PXf5bbo8Vba39xKdGQBJEfNdh7hA
CODEN	ITREAE
CitedBy_id	crossref_primary_10_1007_s11263_025_02472_w crossref_primary_10_1016_j_procir_2025_08_154 crossref_primary_10_1109_JSEN_2025_3552822 crossref_primary_10_1109_TDSC_2024_3518500 crossref_primary_10_1016_j_autcon_2025_106252 crossref_primary_10_1016_j_ins_2023_120052 crossref_primary_10_1109_ACCESS_2024_3427012 crossref_primary_10_3390_electronics14132738 crossref_primary_10_1016_j_asoc_2024_112365 crossref_primary_10_1109_JIOT_2024_3363036 crossref_primary_10_1016_j_procs_2025_02_002 crossref_primary_10_1016_j_solener_2025_113728 crossref_primary_10_1038_s44182_023_00006_5 crossref_primary_10_1016_j_neucom_2024_129215 crossref_primary_10_1109_TNNLS_2023_3282958 crossref_primary_10_1016_j_cviu_2023_103907 crossref_primary_10_1007_s00170_024_13168_9 crossref_primary_10_1109_TIM_2025_3580815 crossref_primary_10_1109_TASE_2024_3410891 crossref_primary_10_1016_j_iswa_2023_200295 crossref_primary_10_1109_TIE_2025_3532733 crossref_primary_10_1016_j_compositesb_2025_112656 crossref_primary_10_1007_s11042_024_19087_x crossref_primary_10_1016_j_eij_2025_100680 crossref_primary_10_1016_j_procir_2025_02_205 crossref_primary_10_1109_ACCESS_2025_3526458 crossref_primary_10_1109_TASE_2024_3432405 crossref_primary_10_1016_j_asoc_2024_112568 crossref_primary_10_1007_s00371_025_04043_z crossref_primary_10_1109_ACCESS_2024_3493755 crossref_primary_10_1049_hve2_70091
Cites_doi	10.1109/CVPR.2018.00352 10.1109/IROS.2013.6696520 10.1109/TPAMI.2016.2577031 10.1007/978-3-319-10578-9_23 10.1145/2601097.2601152 10.1109/TRO.2020.2974099 10.1109/CVPR.2017.690 10.1109/ICCV.2015.169 10.1016/j.mfglet.2014.12.001 10.1109/CVPR.2012.6248074 10.1109/CVPR42600.2020.00625 10.1007/978-3-319-10602-1_48 10.1109/ICRA.2017.7989092 10.1109/JPROC.2023.3238524 10.1109/CVPRW.2018.00143 10.1109/CVPR.2018.00395 10.1109/CVPR.2016.90 10.1109/TPAMI.2022.3158902 10.1109/ICAR.2015.7251504 10.1177/105971239700600205 10.1016/j.ifacol.2021.08.068 10.1007/978-3-030-11009-3_42 10.1109/IROS.2017.8202133 10.1016/j.eng.2019.07.015 10.1109/IROS.2012.6386109 10.1109/LRA.2021.3063925 10.1177/0278364917710318 10.1109/CVPR.2014.81 10.1109/CVPR.2014.461 10.1145/566654.566636 10.l007/978-3-319-46448-0_2 10.1109/TKDE.2009.191 10.1017/9781108891530.013 10.1109/ICRA.2018.8460875 10.1007/978-3-540-75538-8_7 10.1145/360825.360839 10.1109/TRO.2020.2994002 10.1109/TPAMI.2018.2858826 10.1109/TRO.2020.2988642 10.1109/CVPR.2017.106 10.1109/CVPR.2016.352 10.1109/CVPR.2016.470 10.1109/CVPR.2016.91 10.1109/ICARSC.2018.8374189 10.1177/0278364919870227 10.1007/s11263-015-0816-y 10.21105/joss.00500 10.1109/TPAMI.2022.3155712 10.1109/IROS40897.2019.8968139 10.1007/978-3-319-46475-6_7 10.1186/s40537-016-0043-6 10.1007/s11263-018-1072-8 10.5555/3454287.3455008 10.1109/IROS.2018.8593933 10.1109/IROS.2004.1389727 10.1109/IROS40897.2019.8967622
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D
DOI	10.1109/TRO.2022.3207619
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals (WRLC) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0468
EndPage	1243
ExternalDocumentID	10_1109_TRO_2022_3207619 9916581
Genre	orig-research
GrantInformation_xml	– fundername: Development and Innovation Office – fundername: National Lab for Autonomous Systems – fundername: Ministry for Innovation and Technology and the National Research – fundername: Application Domain Specific Highly Reliable IT Solutions – fundername: Thematic Excellence Programme grantid: 2020-4.1.1.-TKP2020 – fundername: Research on prime exploitation of the potential provided by the industrial digitalisation grantid: ED_18-2-2018-0006 – fundername: National Challenges Subprogramme – fundername: National Research, Development and Innovation Fund of Hungary grantid: TKP2020-NKA-06
GroupedDBID	.DC 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL F5P HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS VJK AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c333t-8c39e42d676052ee09c896f7ffaed2c86accf1ccd614cd25f454fc3145c78ad3
IEDL.DBID	RIE
ISICitedReferencesCount	36
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000869385100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1552-3098
IngestDate	Mon Jun 30 04:55:31 EDT 2025 Tue Nov 18 22:32:09 EST 2025 Sat Nov 29 01:47:30 EST 2025 Wed Aug 27 02:14:18 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	2
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c333t-8c39e42d676052ee09c896f7ffaed2c86accf1ccd614cd25f454fc3145c78ad3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-9438-840X 0000-0002-6450-5193 0000-0002-0169-4791 0000-0002-6573-0659 0000-0002-3531-3803
OpenAccessLink	https://ieeexplore.ieee.org/document/9916581
PQID	2795806589
PQPubID	27625
PageCount	19
ParticipantIDs	ieee_primary_9916581 proquest_journals_2795806589 crossref_citationtrail_10_1109_TRO_2022_3207619 crossref_primary_10_1109_TRO_2022_3207619
PublicationCentury	2000
PublicationDate	2023-April 2023-4-00 20230401
PublicationDateYYYYMMDD	2023-04-01
PublicationDate_xml	– month: 04 year: 2023 text: 2023-April
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on robotics
PublicationTitleAbbrev	TRO
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref57 ref12 ref56 ref15 ref14 ref58 ref53 ref11 ref55 ref10 ref54 Tossy (ref76) 2022 ref17 DeVries (ref27) 2017 Wu (ref66) 2019 ref18 Coumans (ref25) 2016 ref51 ref50 (ref72) 2022 James (ref28) 2017 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 Matl (ref52) 2022 Kingma (ref16) 2014 ref49 ref7 (ref30) 2022 ref9 ref4 Bochkovskiy (ref8) 2020 ref3 ref6 ref5 ref40 (ref73) 2022 ref35 (ref71) 2022 ref34 ref37 ref36 ref31 ref33 ref32 ref2 ref1 ref38 Angel (ref65) 2014 (ref64) 2022 Simonyan (ref19) 2015 ref70 ref24 ref68 ref23 ref67 ref26 Redmon (ref59) 2018 ref69 ref20 ref22 ref21 ref29 Ordonez (ref75) 2022 Exner (ref74) 2022 ref60 (ref63) 2022 ref62 ref61 Dai (ref39) 2016
References_xml	– ident: ref31 doi: 10.1109/CVPR.2018.00352 – ident: ref49 doi: 10.1109/IROS.2013.6696520 – ident: ref6 doi: 10.1109/TPAMI.2016.2577031 – ident: ref55 doi: 10.1007/978-3-319-10578-9_23 – ident: ref51 doi: 10.1145/2601097.2601152 – ident: ref3 doi: 10.1109/TRO.2020.2974099 – ident: ref58 doi: 10.1109/CVPR.2017.690 – ident: ref56 doi: 10.1109/ICCV.2015.169 – year: 2015 ident: ref19 article-title: Very deep convolutional networks for large-scale image recognition – ident: ref70 doi: 10.1016/j.mfglet.2014.12.001 – year: 2017 ident: ref27 article-title: Improved regularization of convolutional neural networks with cutout – ident: ref38 doi: 10.1109/CVPR.2012.6248074 – year: 2022 ident: ref30 article-title: Unreal engine – ident: ref45 doi: 10.1109/CVPR42600.2020.00625 – year: 2022 ident: ref72 article-title: ROS wrapper for intel RealSense devices – year: 2022 ident: ref71 article-title: Robotic operating system – year: 2022 ident: ref73 article-title: Universal robots ROS driver – ident: ref5 doi: 10.1007/978-3-319-10602-1_48 – ident: ref32 doi: 10.1109/ICRA.2017.7989092 – ident: ref53 doi: 10.1109/JPROC.2023.3238524 – year: 2022 ident: ref64 article-title: Texture ninja – ident: ref37 doi: 10.1109/CVPRW.2018.00143 – ident: ref34 doi: 10.1109/CVPR.2018.00395 – ident: ref61 doi: 10.1109/CVPR.2016.90 – ident: ref44 doi: 10.1109/TPAMI.2022.3158902 – ident: ref48 doi: 10.1109/ICAR.2015.7251504 – year: 2022 ident: ref76 article-title: YOLO V4 for darknet ROS – ident: ref18 doi: 10.1177/105971239700600205 – ident: ref69 doi: 10.1016/j.ifacol.2021.08.068 – volume-title: Proc. 2nd Int. Conf. Learn. Representations year: 2014 ident: ref16 article-title: Auto-encoding variational Bayes – ident: ref41 doi: 10.1007/978-3-030-11009-3_42 – ident: ref14 doi: 10.1109/IROS.2017.8202133 – ident: ref1 doi: 10.1016/j.eng.2019.07.015 – ident: ref20 doi: 10.1109/IROS.2012.6386109 – ident: ref47 doi: 10.1109/LRA.2021.3063925 – ident: ref9 doi: 10.1177/0278364917710318 – ident: ref54 doi: 10.1109/CVPR.2014.81 – year: 2016 ident: ref25 article-title: PyBullet, a python module for physics simulation for games, robotics and machine learning – ident: ref62 doi: 10.1109/CVPR.2014.461 – year: 2019 ident: ref66 article-title: Detectron2 – ident: ref24 doi: 10.1145/566654.566636 – ident: ref7 doi: 10.l007/978-3-319-46448-0_2 – ident: ref10 doi: 10.1109/TKDE.2009.191 – ident: ref17 doi: 10.1017/9781108891530.013 – ident: ref13 doi: 10.1109/ICRA.2018.8460875 – ident: ref26 doi: 10.1007/978-3-540-75538-8_7 – ident: ref42 doi: 10.1145/360825.360839 – ident: ref29 doi: 10.1109/TRO.2020.2994002 – ident: ref60 doi: 10.1109/TPAMI.2018.2858826 – ident: ref2 doi: 10.1109/TRO.2020.2988642 – ident: ref68 doi: 10.1109/CVPR.2017.106 – ident: ref35 doi: 10.1109/CVPR.2016.352 – ident: ref40 doi: 10.1109/CVPR.2016.470 – ident: ref57 doi: 10.1109/CVPR.2016.91 – year: 2020 ident: ref8 article-title: YOLOv4: Optimal speed and accuracy of object detection – ident: ref22 doi: 10.1109/ICARSC.2018.8374189 – start-page: 379 volume-title: Proc. 30th Int. Conf. Neural Inf. Process. Syst. year: 2016 ident: ref39 article-title: R-FCN: Object detection via region-based fully convolutional networks – ident: ref43 doi: 10.1177/0278364919870227 – ident: ref4 doi: 10.1007/s11263-015-0816-y – ident: ref50 doi: 10.21105/joss.00500 – ident: ref46 doi: 10.1109/TPAMI.2022.3155712 – ident: ref15 doi: 10.1109/IROS40897.2019.8968139 – year: 2022 ident: ref52 article-title: Pyrender – year: 2022 ident: ref75 article-title: Robotiq 2-Finger grippers – ident: ref36 doi: 10.1007/978-3-319-46475-6_7 – year: 2017 ident: ref28 article-title: Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task – year: 2018 ident: ref59 article-title: YOLOv3: An incremental improvement – ident: ref11 doi: 10.1186/s40537-016-0043-6 – ident: ref33 doi: 10.1007/s11263-018-1072-8 – year: 2022 ident: ref63 article-title: Free stock textures – year: 2022 ident: ref74 article-title: Universal robot – ident: ref67 doi: 10.5555/3454287.3455008 – ident: ref21 doi: 10.1109/IROS.2018.8593933 – ident: ref23 doi: 10.1109/IROS.2004.1389727 – volume-title: Interactive Computer Graphics: A Top-Down Approach With WebGL year: 2014 ident: ref65 – ident: ref12 doi: 10.1109/IROS40897.2019.8967622
SSID	ssj0024903
Score	2.5993834
Snippet	Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1225
SubjectTerms	Adaptation models Artificial neural networks Computational modeling Computer vision for automation Datasets Deep learning deep learning in robotics and automation Industrial applications localization Object detection Object recognition Randomization Robotics Robots Service robots sim2real knowledge transfer Synthetic data Task analysis Training
Title	Object Detection Using Sim2Real Domain Randomization for Robotic Applications
URI	https://ieeexplore.ieee.org/document/9916581 https://www.proquest.com/docview/2795806589
Volume	39
WOSCitedRecordID	wos000869385100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1941-0468 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024903 issn: 1552-3098 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZKxQADr4IoFOSBBYn0YSexPVaUigFaVDp0i5yzLVWiCeqD34_tpKUIhEQmD3YUfU5y9_nuvkPoppOSlLvk1tCOLEEBEkgIZSAj625QEytWiCQ9scGATybipYLuNrUwWmuffKabbuhj-SqHlTsqazlfJnJ11juMsaJW60tXT_guyE5RLKBtwdchybZojUdDSwQJaVLiWfs3E-R7qvz4EXvr0j_833MdoYPSi8TdYtuPUUVnJ2h_S1uwhp6HqTtiwT299NlWGfbZAfh1OiMj6x3iXj6T0wyPZKbyWVmNia0Li0d5mtv74u5WbPsUjfsP4_vHoOydEACldBlwoEKHRMXM8hWidVsAF7FhxkitCPBYApgOgLLmGRSJTBiFBmgnjIBxqegZqmZ5ps8RjmOgEKdUcAjtJbm2DIfTUJlUUjBxHbXWaCZQ6oq79hZviecXbZFY_BOHf1LiX0e3mxXvhabGH3NrDu_NvBLqOmqsNywpP7pFQpiIXJyYi4vfV12iPdctvki8aaDqcr7SV2gXPpbTxfzav0-faXzIEw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5EBfXgW1yfOXgRrLubpG1yFB8orquse_BW0kkCC24r6-rvN0m7q6II9pRDUsqXtjNfZuYbgKN2TnPhk1u5GzmCgjRSyFWkYuduMJvotBJJ6qTdrnh6kg8zcDKthTHGhOQzc-qHIZavS3zzR2VN78vEvs56LuactqtqrU9lPRn6IHtNsYi1pJgEJVuy2e_dOypI6Smjgbd_M0Khq8qPX3GwL1cr_3uyVViu_UhyVm38GsyYYh2WvqgLbsDdfe4PWciFGYd8q4KE_ADyOBjSnvMPyUU5VIOC9FShy2Fdj0mcE0t6ZV66-5KzL9HtTehfXfbPr6O6e0KEjLFxJJBJw6lOUsdYqDEtiUImNrVWGU1RJArRthG1M9CoaWx5zC2yNo8xFUqzLZgtysJsA0kSZJjkTArk7lLCOI4jGNc2Vwxt0oDmBM0Ma2Vx3-DiOQsMoyUzh3_m8c9q_BtwPF3xUqlq_DF3w-M9nVdD3YC9yYZl9Wf3mtFUxj5SLOTO76sOYeG6f9fJOjfd211Y9L3jqzScPZgdj97MPszj-3jwOjoI79YH-5jLWg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Object+Detection+Using+Sim2Real+Domain+Randomization+for+Robotic+Applications&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Horv%C3%A1th%2C+D%C3%A1niel&rft.au=Erd%C5%91s%2C+G%C3%A1bor&rft.au=Istenes%2C+Zolt%C3%A1n&rft.au=Horv%C3%A1th%2C+Tom%C3%A1%C5%A1&rft.date=2023-04-01&rft.issn=1552-3098&rft.eissn=1941-0468&rft.volume=39&rft.issue=2&rft.spage=1225&rft.epage=1243&rft_id=info:doi/10.1109%2FTRO.2022.3207619&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TRO_2022_3207619
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1552-3098&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1552-3098&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1552-3098&client=summon