RLOC: Terrain-Aware Legged Locomotion Using Reinforcement Learning and Optimal Control

We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a re...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on robotics Ročník 38; číslo 5; s. 2908 - 2927
Hlavní autoři:	Gangapurwala, Siddhant, Geisert, Mathieu, Orsolino, Romeo, Fallon, Maurice, Havoutis, Ioannis
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.10.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	AI-based methods Computational modeling deep learning in robotics and automation Learning Legged locomotion legged robots Locomotion Optimal control Perturbation Physical properties Planning Policies Quadrupedal robots Robots robust/adaptive control of robotic systems Terrain Tracking Tracking control Training
ISSN:	1552-3098, 1941-0468
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy. This RL policy is trained in simulation over a wide range of procedurally generated terrains. When run online, the system tracks the generated footstep plans using a model-based motion controller. We evaluate the robustness of our method over a wide variety of complex terrains. It exhibits behaviors that prioritize stability over aggressive locomotion. Additionally, we introduce two ancillary RL policies for corrective whole-body motion tracking and recovery control. These policies account for changes in physical parameters and external perturbations. We train and evaluate our framework on a complex quadrupedal system, ANYmal version B, and demonstrate transferability to a larger and heavier robot, ANYmal C, without requiring retraining.
AbstractList	We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy. This RL policy is trained in simulation over a wide range of procedurally generated terrains. When run online, the system tracks the generated footstep plans using a model-based motion controller. We evaluate the robustness of our method over a wide variety of complex terrains. It exhibits behaviors that prioritize stability over aggressive locomotion. Additionally, we introduce two ancillary RL policies for corrective whole-body motion tracking and recovery control. These policies account for changes in physical parameters and external perturbations. We train and evaluate our framework on a complex quadrupedal system, ANYmal version B, and demonstrate transferability to a larger and heavier robot, ANYmal C, without requiring retraining.
Author	Gangapurwala, Siddhant Fallon, Maurice Geisert, Mathieu Orsolino, Romeo Havoutis, Ioannis
Author_xml	– sequence: 1 givenname: Siddhant orcidid: 0000-0002-1308-3744 surname: Gangapurwala fullname: Gangapurwala, Siddhant email: siddhant@robots.ox.ac.uk organization: Dynamic Robots Systems Group, Oxford Robotics Institute, University of Oxford, Oxford, U.K – sequence: 2 givenname: Mathieu orcidid: 0000-0002-5651-8736 surname: Geisert fullname: Geisert, Mathieu email: geisert.mathieu@gmail.com organization: Dynamic Robots Systems Group, Oxford Robotics Institute, University of Oxford, Oxford, U.K – sequence: 3 givenname: Romeo orcidid: 0000-0001-9847-2601 surname: Orsolino fullname: Orsolino, Romeo email: orsolino@arrival.com organization: Dynamic Robots Systems Group, Oxford Robotics Institute, University of Oxford, Oxford, U.K – sequence: 4 givenname: Maurice orcidid: 0000-0003-2940-0879 surname: Fallon fullname: Fallon, Maurice email: mfallon@robots.ox.ac.uk organization: Dynamic Robots Systems Group, Oxford Robotics Institute, University of Oxford, Oxford, U.K – sequence: 5 givenname: Ioannis orcidid: 0000-0002-4371-4623 surname: Havoutis fullname: Havoutis, Ioannis email: ioannis@robots.ox.ac.uk organization: Dynamic Robots Systems Group, Oxford Robotics Institute, University of Oxford, Oxford, U.K
BookMark	eNp9kM9LwzAUx4MouE3vgpeC5878apt4G8VfUCiMzWtI05fRsSUz7RD_e1M2PHjw9B6P74_HZ4ounXeA0B3Bc0KwfFwt6znFlM4ZKSjP5QWaEMlJinkuLuOeZTRlWIprNO37LcaUS8wm6GNZ1eVTsoIQdOfSxZcOkFSw2UCbVN74vR8675J137lNsoTOWR8M7MENUaWDG8_atUl9GLq93iWld0Pwuxt0ZfWuh9vznKH1y_OqfEur-vW9XFSpoZIMqWBE8JbQjHBBLUijOeHMUt4a0eZ5QwUUjPMmN8KypskFyExom3PLJGG2ZTP0cMo9BP95hH5QW38MLlYqWtCYxZjMogqfVCb4vg9g1SHEb8O3IliN9FSkp0Z66kwvWvI_FtMNemQxRFC7_4z3J2MHAL89sigkp5L9AAX6fXI
CODEN	ITREAE
CitedBy_id	crossref_primary_10_3390_s23041873 crossref_primary_10_1017_S0263574724000626 crossref_primary_10_1126_scirobotics_adh5401 crossref_primary_10_1109_LRA_2023_3329766 crossref_primary_10_1109_TRO_2022_3186804 crossref_primary_10_1109_LRA_2021_3136645 crossref_primary_10_3390_s24123825 crossref_primary_10_1007_s11071_024_10510_4 crossref_primary_10_1109_LRA_2024_3375086 crossref_primary_10_1109_TRO_2023_3275384 crossref_primary_10_3390_machines12120902 crossref_primary_10_1126_scirobotics_adv3604 crossref_primary_10_3390_s23115194 crossref_primary_10_1109_LRA_2024_3524890 crossref_primary_10_1109_TASE_2024_3354830 crossref_primary_10_1177_02783649241312698 crossref_primary_10_1109_LRA_2025_3595037 crossref_primary_10_1016_j_eswa_2023_121798 crossref_primary_10_1108_RIA_09_2024_0207 crossref_primary_10_1109_LRA_2023_3304561 crossref_primary_10_3390_s24113675 crossref_primary_10_1126_scirobotics_adi9641 crossref_primary_10_1109_LRA_2022_3184779 crossref_primary_10_1109_TRO_2023_3324580 crossref_primary_10_1109_LRA_2025_3592067 crossref_primary_10_1109_TRO_2023_3302239 crossref_primary_10_1109_LRA_2023_3323893 crossref_primary_10_1109_TASE_2023_3345876 crossref_primary_10_1109_ACCESS_2023_3311141 crossref_primary_10_1109_TRO_2023_3297015 crossref_primary_10_1109_ACCESS_2025_3582523 crossref_primary_10_1109_TCST_2024_3377949 crossref_primary_10_1007_s10489_025_06584_1 crossref_primary_10_1109_TMECH_2024_3421251 crossref_primary_10_1146_annurev_control_030323_022510
Cites_doi	10.1109/ICRA40945.2020.9196777 10.1126/scirobotics.abk2822 10.1109/LRA.2018.2792536 10.1109/ICRA40945.2020.9196673 10.1109/IROS.2017.8202133 10.1242/jeb.202.23.3325 10.1109/LRA.2020.2979656 10.1007/s10514-013-9341-4 10.1109/TBME.1969.4502596 10.1109/ICHR.2006.321385 10.1177/0278364906066768 10.1126/scirobotics.abc5986 10.1109/IROS.2018.8593722 10.1109/LRA.2019.2931284 10.1109/IROS40897.2019.8968251 10.1109/IROS.2001.973365 10.1145/2185520.2185539 10.1109/TRO.2018.2862902 10.1002/rob.21964 10.1109/LRA.2018.2849506 10.1109/IROS51168.2021.9636474 10.1109/ICRA48506.2021.9561639 10.15607/RSS.2019.XV.011 10.1109/IROS.2004.1389727 10.1109/LRA.2020.2979660 10.1109/TAC.2009.2024565 10.1109/HUMANOIDS.2016.7803333 10.1109/LRA.2020.3007427 10.1109/IROS.2017.8206174 10.1109/IROS.2016.7758092 10.1109/TRO.2020.2983318 10.15607/rss.2020.xvi.064 10.1109/LRA.2018.2794620
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D
DOI	10.1109/TRO.2022.3172469
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) 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 Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0468
EndPage	2927
ExternalDocumentID	10_1109_TRO_2022_3172469 9779429
Genre	orig-research
GrantInformation_xml	– fundername: Engineering and Physical Sciences Research Council; EPSRC grantid: EP/S002383/1 funderid: 10.13039/501100000266 – fundername: EU H2020 – fundername: UKRI/EPSRC RAIN Hub grantid: EP/R026084/1 – fundername: Royal Society University Research Fellowship
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 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-c291t-83184d1251482fe9ca4143f24dc8d66b28e7344b6c8f3bb68e958af64f3913fd3
IEDL.DBID	RIE
ISICitedReferencesCount	66
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000800818100001&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	Sun Jun 29 16:57:33 EDT 2025 Tue Nov 18 20:38:46 EST 2025 Sat Nov 29 01:47:29 EST 2025 Wed Aug 27 02:14:17 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	5
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-83184d1251482fe9ca4143f24dc8d66b28e7344b6c8f3bb68e958af64f3913fd3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-2940-0879 0000-0002-1308-3744 0000-0002-4371-4623 0000-0002-5651-8736 0000-0001-9847-2601
PQID	2721433395
PQPubID	27625
PageCount	20
ParticipantIDs	crossref_primary_10_1109_TRO_2022_3172469 crossref_citationtrail_10_1109_TRO_2022_3172469 proquest_journals_2721433395 ieee_primary_9779429
PublicationCentury	2000
PublicationDate	2022-Oct. 2022-10-00 20221001
PublicationDateYYYYMMDD	2022-10-01
PublicationDate_xml	– month: 10 year: 2022 text: 2022-Oct.
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on robotics
PublicationTitleAbbrev	TRO
PublicationYear	2022
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 ref12 ref15 ref14 ref11 ref10 ref17 ref16 ref18 Sutton (ref32) 1998; 135 ref46 ref47 ref49 ref8 ref7 Levine (ref24) 2013 ref9 ref4 ref6 ref5 Glorot (ref48) 2010 Haarnoja (ref44) 2018; abs/1812.05905 ref37 ref36 ref31 ref30 ref33 Yang (ref26) 2020 ref1 ref39 ref38 Schulman (ref43) 2017 Lee (ref20) 2019 Iscen (ref35) 2018 Fujimoto (ref45) 2018 Liang (ref41) 2018 Ackerman (ref2) 2019 ref23 ref25 Hwangbo (ref19) 2019; 4 ref22 ref21 ref28 ref27 ref29 Haarnoja (ref40) 2018 Rudin (ref34) 2022 Smith (ref50) 2005 Schulman (ref42) 2015 Ackerman (ref3) 2018
References_xml	– year: 2019 ident: ref20 article-title: Robust recovery controller for a quadrupedal robot using deep reinforcement learning – year: 2017 ident: ref43 article-title: Proximal policy optimization algorithms – ident: ref18 doi: 10.1109/ICRA40945.2020.9196777 – ident: ref30 doi: 10.1126/scirobotics.abk2822 – ident: ref46 doi: 10.1109/LRA.2018.2792536 – start-page: 1582 volume-title: Proc. Int. Conf. Mach. Learn. year: 2018 ident: ref45 article-title: Addressing function approximation error in actor-critic methods – volume: 135 volume-title: Introduction to Reinforcement Learning year: 1998 ident: ref32 – start-page: 916 volume-title: Proc. Conf. Robot Learn. year: 2018 ident: ref35 article-title: Policies modulating trajectory generators – start-page: 249 volume-title: Proc. 13th Int. Conf. Artif. Intell. Statist. year: 2010 ident: ref48 article-title: Understanding the difficulty of training deep feedforward neural networks – ident: ref6 doi: 10.1109/ICRA40945.2020.9196673 – ident: ref27 doi: 10.1109/IROS.2017.8202133 – start-page: 91 volume-title: Proc. Conf. Robot Learn. year: 2022 ident: ref34 article-title: Learning to walk in minutes using massively parallel deep reinforcement learning – ident: ref8 doi: 10.1242/jeb.202.23.3325 – ident: ref21 doi: 10.1109/LRA.2020.2979656 – start-page: 1 volume-title: Proc. Int. Conf. Mach. Learn. year: 2013 ident: ref24 article-title: Guided policy search – start-page: 1861 volume-title: Proc. Int. Conf. Mach. Learn. year: 2018 ident: ref40 article-title: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor – ident: ref14 doi: 10.1007/s10514-013-9341-4 – ident: ref12 doi: 10.1109/TBME.1969.4502596 – ident: ref13 doi: 10.1109/ICHR.2006.321385 – ident: ref10 doi: 10.1177/0278364906066768 – ident: ref29 doi: 10.1126/scirobotics.abc5986 – ident: ref23 doi: 10.1109/IROS.2018.8593722 – ident: ref37 doi: 10.1109/LRA.2019.2931284 – year: 2005 ident: ref50 article-title: Open dynamics engine – ident: ref7 doi: 10.1109/IROS40897.2019.8968251 – ident: ref9 doi: 10.1109/IROS.2001.973365 – start-page: 3053 volume-title: Proc. Int. Conf. Mach. Learn. year: 2018 ident: ref41 article-title: RLlib: Abstractions for distributed reinforcement learning – ident: ref5 doi: 10.1145/2185520.2185539 – ident: ref16 doi: 10.1109/TRO.2018.2862902 – ident: ref4 doi: 10.1002/rob.21964 – ident: ref33 doi: 10.1109/LRA.2018.2849506 – volume-title: IEEE Spectr. year: 2019 ident: ref2 article-title: Anybotics introduces sleek new ANYmal C quadruped – ident: ref39 doi: 10.1109/IROS51168.2021.9636474 – ident: ref47 doi: 10.1109/ICRA48506.2021.9561639 – start-page: 1889 volume-title: Proc. Int. Conf. Mach. Learn. year: 2015 ident: ref42 article-title: Trust region policy optimization – volume: abs/1812.05905 volume-title: CoRR year: 2018 ident: ref44 article-title: Soft actor-critic algorithms and applications – ident: ref25 doi: 10.15607/RSS.2019.XV.011 – start-page: 1 volume-title: Proc. Conf. Robot Learn. year: 2020 ident: ref26 article-title: Data efficient reinforcement learning for legged robots – ident: ref49 doi: 10.1109/IROS.2004.1389727 – ident: ref28 doi: 10.1109/LRA.2020.2979660 – ident: ref11 doi: 10.1109/TAC.2009.2024565 – volume-title: IEEE Spectr. year: 2018 ident: ref3 article-title: North sea deployment shows how quadruped robots can be commercially useful – ident: ref15 doi: 10.1109/HUMANOIDS.2016.7803333 – ident: ref17 doi: 10.1109/LRA.2020.3007427 – ident: ref36 doi: 10.1109/IROS.2017.8206174 – volume: 4 issue: 26 volume-title: Sci. Robot. year: 2019 ident: ref19 article-title: Learning agile and dynamic motor skills for legged robots – ident: ref1 doi: 10.1109/IROS.2016.7758092 – ident: ref38 doi: 10.1109/TRO.2020.2983318 – ident: ref22 doi: 10.15607/rss.2020.xvi.064 – ident: ref31 doi: 10.1109/LRA.2018.2794620
SSID	ssj0024903
Score	2.662384
Snippet	We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	2908
SubjectTerms	AI-based methods Computational modeling deep learning in robotics and automation Learning Legged locomotion legged robots Locomotion Optimal control Perturbation Physical properties Planning Policies Quadrupedal robots Robots robust/adaptive control of robotic systems Terrain Tracking Tracking control Training
Title	RLOC: Terrain-Aware Legged Locomotion Using Reinforcement Learning and Optimal Control
URI	https://ieeexplore.ieee.org/document/9779429 https://www.proquest.com/docview/2721433395
Volume	38
WOSCitedRecordID	wos000800818100001&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 Electronic Library (IEL) 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/eLvHCXMwlV3NS8MwFH-oeNCDX1OcX-TgRTCuS9I28SZD8TCcjCneSpu8DkFb6ab--yZpNweK4K2EpCnvNe8jefn9AE6tl5M2TWYUMQupCLFLZSpz6pBLMEYu04ZsIr67k09P6n4Jzud3YRDRF5_hhXv0Z_mm1O9uq6xjYxVl7ecyLMdxXN_V-sbVU54F2SGKUR4oOTuSDFRnNBzYRJAxm5_GTLjS5gUX5DlVfhhi711uNv_3XVuw0USR5KpW-zYsYbED6wvYgi14HPYHvUsywsqRQNCrz7RC0sfxGA3pl7qs6XuILxkgQ_QAqtrvFZIGc3VM0sKQgbUpr3auXl3TvgsPN9ej3i1tSBSoZqo7pdIuWmFcGCMky1HpVNgQKWfCaGmiKGMSYy5EFmmZ8yyLJKpQpnkkcq66PDd8D1aKssB9IFKjYbmJAqO0yESojOmidfeBbZUhmjZ0ZnJNdIMw7oguXhKfaQQqsZpInCaSRhNtOJuPeKvRNf7o23KSn_drhN6Go5nqkmb5TRJm81rBOVfhwe-jDmHNvbuuyjuClWn1jsewqj-mz5PqxP9ZX2bKyno
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD54A_XBuzivefBFMK5N0i7xTYaiWDcZU3wrbXI6BN1kTv37Jmk3BUXwrYSElHOSc0lOvg_g0Ho5adNkRhHziIoIQyozWVCHXIIN5DKryCYarZZ8eFC3U3A8eQuDiL74DE_cp7_LNwP95o7K6jZWUdZ-TsNsJAQLy9daX8h6yvMgO0wxygMlx5eSgap3O22bCjJmM9QGE664-ZsT8qwqP0yx9y8Xy__7sxVYquJIclYqfhWmsL8Gi9_QBdfhvpO0m6eki0NHA0HPPrIhkgR7PTQkGehBSeBDfNEA6aCHUNX-tJBUqKs9kvUNaVur8mznapZV7Rtwd3HebV7SikaBaqbCEZV22wrjAhkhWYFKZ8IGSQUTRksTxzmT2OBC5LGWBc_zWKKKZFbEouAq5IXhmzDTH_RxC4jUaFhh4sAoLXIRKWNCtA4_sK0yQlOD-liuqa4wxh3VxVPqc41ApVYTqdNEWmmiBkeTES8lvsYffded5Cf9KqHXYHesurTagK8ps5mt4JyraPv3UQcwf9m9SdLkqnW9AwtunrJGbxdmRsM33IM5_T56fB3u-1X2CRlXzcE
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=RLOC%3A+Terrain-Aware+Legged+Locomotion+Using+Reinforcement+Learning+and+Optimal+Control&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Gangapurwala%2C+Siddhant&rft.au=Geisert%2C+Mathieu&rft.au=Romeo+Orsolino&rft.au=Fallon%2C+Maurice&rft.date=2022-10-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1552-3098&rft.eissn=1941-0468&rft.volume=38&rft.issue=5&rft.spage=2908&rft_id=info:doi/10.1109%2FTRO.2022.3172469&rft.externalDBID=NO_FULL_TEXT
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