ViTAL: Vision-Based Terrain-Aware Locomotion for Legged Robots

This article focuses on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on robotics Ročník 39; číslo 2; s. 1 - 20
Hlavní autoři:	Fahmi, Shamel, Barasuol, Victor, Esteban, Domingo, Villarreal, Octavio, Semini, Claudio
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.04.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptation Algorithms Foot Forward error correction Legged locomotion Legged robots Locomotion Optimization optimization and optimal control Planning Robot dynamics Robots Strategy Terrain Trajectory visual learning whole-body motion planning and control
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	This article focuses on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot may end up in a state with no reachable safe footholds. Therefore, we present a vision-based terrain-aware locomotion (ViTAL) strategy that consists of novel pose adaptation and foothold selection algorithms. ViTAL introduces a different paradigm in pose adaptation that does not optimize the body pose relative to given footholds, but the body pose that maximizes the chances of the legs in reaching safe footholds. ViTAL plans footholds and poses based on skills that characterize the robot's capabilities and its terrain awareness. We use the 90-kg HyQ and 140-kg HyQReal quadruped robots to validate ViTAL and show that they are able to climb various obstacles, including stairs, gaps, and rough terrains, at different speeds and gaits. We compare ViTAL with a baseline strategy that selects the robot pose based on given selected footholds and show that ViTAL outperforms the baseline.
AbstractList	This article focuses on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot may end up in a state with no reachable safe footholds. Therefore, we present a vision-based terrain-aware locomotion (ViTAL) strategy that consists of novel pose adaptation and foothold selection algorithms. ViTAL introduces a different paradigm in pose adaptation that does not optimize the body pose relative to given footholds, but the body pose that maximizes the chances of the legs in reaching safe footholds. ViTAL plans footholds and poses based on skills that characterize the robot's capabilities and its terrain awareness. We use the 90-kg HyQ and 140-kg HyQReal quadruped robots to validate ViTAL and show that they are able to climb various obstacles, including stairs, gaps, and rough terrains, at different speeds and gaits. We compare ViTAL with a baseline strategy that selects the robot pose based on given selected footholds and show that ViTAL outperforms the baseline. This article focuses on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation. Current pose adaptation strategies optimize the robot's body pose relative to given footholds. If these footholds are not reached, the robot may end up in a state with no reachable safe footholds. Therefore, we present a vision-based terrain-aware locomotion (ViTAL) strategy that consists of novel pose adaptation and foothold selection algorithms. ViTAL introduces a different paradigm in pose adaptation that does not optimize the body pose relative to given footholds, but the body pose that maximizes the chances of the legs in reaching safe footholds. ViTAL plans footholds and poses based on skills that characterize the robot's capabilities and its terrain awareness. We use the 90-kg HyQ and 140-kg HyQReal quadruped robots to validate ViTAL and show that they are able to climb various obstacles, including stairs, gaps, and rough terrains, at different speeds and gaits. We compare ViTAL with a baseline strategy that selects the robot pose based on given selected footholds and show that ViTAL outperforms the baseline.
Author	Villarreal, Octavio Semini, Claudio Fahmi, Shamel Barasuol, Victor Esteban, Domingo
Author_xml	– sequence: 1 givenname: Shamel orcidid: 0000-0002-0892-7359 surname: Fahmi fullname: Fahmi, Shamel organization: Dynamic Legged Systems Lab, Istituto Italiano di Tecnologia, Genoa, Italy – sequence: 2 givenname: Victor surname: Barasuol fullname: Barasuol, Victor organization: Dynamic Legged Systems Lab, Istituto Italiano di Tecnologia, Genoa, Italy – sequence: 3 givenname: Domingo orcidid: 0000-0002-3134-0281 surname: Esteban fullname: Esteban, Domingo organization: Dynamic Legged Systems Lab, Istituto Italiano di Tecnologia, Genoa, Italy – sequence: 4 givenname: Octavio orcidid: 0000-0002-2822-9216 surname: Villarreal fullname: Villarreal, Octavio organization: Dynamic Legged Systems Lab, Istituto Italiano di Tecnologia, Genoa, Italy – sequence: 5 givenname: Claudio orcidid: 0000-0002-3034-4686 surname: Semini fullname: Semini, Claudio organization: Dynamic Legged Systems Lab, Istituto Italiano di Tecnologia, Genoa, Italy
BookMark	eNp9kEtrwzAQhEVJoUnae6EXQ89K9bBsbw-FNPQFhkBwcxWyLAWHxEolh5J_X4WEHnroaRd2Zof5RmjQuc4gdEvJhFICD9ViPmGEsQlnjIEoLtCQQkoxSbNiEHchGOYEiis0CmFNCEuB8CF6WrbVtHxMlm1oXYefVTBNUhnvVdvh6bfyJimddlvXx3NinU9Ks1pFzcLVrg_X6NKqTTA35zlGn68v1ewdl_O3j9m0xJoB7XGTZQQaqIXVBQObFzmzmqu0VrYm1ujCiKaGnEPRCK05Z5BxmgMoRpWllvIxuj_93Xn3tTehl2u3912MlCyPbYmgIKKKnFTauxC8sXLn263yB0mJPFKSkZI8UpJnStGS_bHotlfHsn1EsPnPeHcytsaY3xyALOOc8h_f1XUA
CODEN	ITREAE
CitedBy_id	crossref_primary_10_1002_aisy_202300633 crossref_primary_10_1016_j_enconman_2025_119620 crossref_primary_10_1109_TMECH_2024_3446840 crossref_primary_10_1109_LRA_2025_3588716 crossref_primary_10_1109_LRA_2023_3293749 crossref_primary_10_1109_LRA_2024_3418270 crossref_primary_10_1002_rob_22350 crossref_primary_10_1126_scirobotics_adv3604 crossref_primary_10_3390_biomimetics8080561
Cites_doi	10.1177/0278364910388677 10.1109/IROS.2012.6385548 10.1109/LRA.2021.3060437 10.1109/IROS.2018.8593888 10.1109/ICRA.2013.6630926 10.1038/s41592-019-0686-2 10.1109/ICRA40945.2020.9196673 10.15607/rss.2021.xvii.061 10.1109/LRA.2020.2979660 10.1109/ROBOT.2008.4543305 10.1109/LRA.2019.2895390 10.1109/ICRA.2013.6631372 10.1126/scirobotics.abc5986 10.1109/ICRA48506.2021.9560794 10.1109/TRO.2019.2954670 10.15607/rss.2021.xvii.021 10.1109/LRA.2019.2908502 10.1109/ICRA40945.2020.9196777 10.1109/LRA.2020.3007427 10.1007/s10514-021-10013-w 10.13180/clawar.2020.24-26.08.62 10.1109/LRA.2021.3061322 10.1109/IROS.2015.7354191 10.1109/LRA.2019.2899434 10.1109/ICRA40945.2020.9197312 10.1109/LRA.2018.2798285 10.1109/ICRA.2019.8793801 10.1109/TRO.2020.3048125 10.1109/ICRA.2018.8460731 10.1002/rob.21974 10.1002/rob.20397 10.1109/LRA.2017.2652491 10.1109/LSENS.2021.3049954 10.1109/ICRA40945.2020.9196816 10.1126/scirobotics.abk2822 10.1109/ICRA48506.2021.9561639 10.1109/LRA.2020.3007475 10.1109/IROS.2004.1389727 10.1109/IROS45743.2020.9341128 10.1109/IROS.2018.8593885 10.1109/TRO.2020.3003464 10.1126/scirobotics.abb2174 10.1016/j.neunet.2015.05.005 10.1109/ACCESS.2019.2933178 10.1109/LRA.2021.3066833 10.15607/RSS.2021.XVII.011 10.1109/ICRA.2016.7487541 10.1177/0959651811402275 10.1137/S1052623497325107 10.1109/ICRA.2019.8793865 10.1109/IROS.2009.5354701 10.1007/978-3-319-26054-9_5 10.1142/9789814525534_0056 10.1109/IROS.2016.7758092 10.1109/TRO.2015.2482061 10.1109/IROS45743.2020.9341751 10.1109/TRO.2018.2819658 10.1109/LRA.2021.3088797
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 RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D
DOI	10.1109/TRO.2022.3222958
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present 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 Xplore Digital Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0468
EndPage	20
ExternalDocumentID	10_1109_TRO_2022_3222958 9966331
Genre	orig-research
GroupedDBID	.DC 0R~ 29I 4.4 5GY 6IK 97E AAJGR AASAJ AAWTH ABQJQ ABVLG ACGFO ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS 5VS AAYXX AETIX AGSQL AIBXA CITATION EJD H~9 VJK 7SC 7SP 7TB 8FD AARMG ABAZT FR3 JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-d6609d9b5fc829f7872fc3a4bafb0fec8e5db97398d5cc3329631799a21af1f13
IEDL.DBID	RIE
ISICitedReferencesCount	19
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000912783200001&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 05:31:34 EDT 2025 Sat Nov 29 01:47:30 EST 2025 Tue Nov 18 21:32:40 EST 2025 Tue Nov 25 14:44:28 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
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-d6609d9b5fc829f7872fc3a4bafb0fec8e5db97398d5cc3329631799a21af1f13
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3034-4686 0000-0002-2822-9216 0000-0002-3134-0281 0000-0002-0892-7359
PQID	2795805195
PQPubID	27625
PageCount	20
ParticipantIDs	crossref_primary_10_1109_TRO_2022_3222958 crossref_citationtrail_10_1109_TRO_2022_3222958 proquest_journals_2795805195 ieee_primary_9966331
PublicationCentury	2000
PublicationDate	2023-04-01
PublicationDateYYYYMMDD	2023-04-01
PublicationDate_xml	– month: 04 year: 2023 text: 2023-04-01 day: 01
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 Diebel (ref69) 2006 ref15 ref59 ref14 ref58 ref53 ref52 Nocedal (ref71) 1996; 17 ref11 ref55 ref54 Fahmi (ref64) 2021 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 Maas (ref66) 2013 ref43 ref49 (ref7) 2021 ref4 Yu (ref30) 2021 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref74 ref33 ref32 Rudin (ref29) 2021 ref2 ref1 ref39 ref38 Semini (ref3) 2019 Kingma (ref68) 2015 Bishop (ref67) 2006 Paigwar (ref17) 2020 (ref8) 2021 ref73 ref72 Cun (ref65) 1989 ref24 Fahmi (ref10) 2021 ref23 ref26 ref25 ref20 ref63 ref22 ref21 ref28 ref27 Paszke (ref70) 2019 ref60 ref62 ref61 (ref9) 2021
References_xml	– ident: ref36 doi: 10.1177/0278364910388677 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. year: 2015 ident: ref68 article-title: Adam: A method for stochastic optimization – ident: ref51 doi: 10.1109/IROS.2012.6385548 – ident: ref14 doi: 10.1109/LRA.2021.3060437 – volume: 17 volume-title: Numerical Optimization year: 1996 ident: ref71 – ident: ref40 doi: 10.1109/IROS.2018.8593888 – ident: ref56 doi: 10.1109/ICRA.2013.6630926 – ident: ref73 doi: 10.1038/s41592-019-0686-2 – ident: ref23 doi: 10.1109/ICRA40945.2020.9196673 – volume-title: Spot year: 2021 ident: ref7 – year: 2021 ident: ref10 article-title: On terrain-aware locomotion for legged robots – ident: ref34 doi: 10.15607/rss.2021.xvii.061 – ident: ref35 doi: 10.1109/LRA.2020.2979660 – ident: ref42 doi: 10.1109/ROBOT.2008.4543305 – start-page: 1 volume-title: Proc. Italian Conf. Robot. Intell. Mach. year: 2019 ident: ref3 article-title: Brief introduction to the quadruped robot HyQReal – ident: ref18 doi: 10.1109/LRA.2019.2895390 – ident: ref26 doi: 10.1109/ICRA.2013.6631372 – ident: ref1 doi: 10.1126/scirobotics.abc5986 – ident: ref21 doi: 10.1109/ICRA48506.2021.9560794 – ident: ref16 doi: 10.1109/TRO.2019.2954670 – ident: ref20 doi: 10.15607/rss.2021.xvii.021 – ident: ref59 doi: 10.1109/LRA.2019.2908502 – ident: ref50 doi: 10.1109/ICRA40945.2020.9196777 – volume-title: Go1 year: 2021 ident: ref9 – ident: ref46 doi: 10.1109/LRA.2020.3007427 – ident: ref11 doi: 10.1007/s10514-021-10013-w – ident: ref49 doi: 10.13180/clawar.2020.24-26.08.62 – volume-title: Robots year: 2021 ident: ref8 – ident: ref28 doi: 10.1109/LRA.2021.3061322 – ident: ref45 doi: 10.1109/IROS.2015.7354191 – ident: ref38 doi: 10.1109/LRA.2019.2899434 – ident: ref53 doi: 10.1109/ICRA40945.2020.9197312 – ident: ref24 doi: 10.1109/LRA.2018.2798285 – start-page: 1291 volume-title: Proc. Conf. Robot Learn. year: 2021 ident: ref30 article-title: Visual-locomotion: Learning to walk on complex terrains with vision – ident: ref48 doi: 10.1109/ICRA.2019.8793801 – ident: ref22 doi: 10.1109/TRO.2020.3048125 – ident: ref37 doi: 10.1109/ICRA.2018.8460731 – ident: ref39 doi: 10.1002/rob.21974 – ident: ref44 doi: 10.1002/rob.20397 – ident: ref61 doi: 10.1109/LRA.2017.2652491 – start-page: 1 volume-title: Proc. Conf. Robot Learn. year: 2020 ident: ref17 article-title: Robust quadrupedal locomotion on sloped terrains: A linear policy approach – ident: ref12 doi: 10.1109/LSENS.2021.3049954 – start-page: 396 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. year: 1989 ident: ref65 article-title: Handwritten digit recognition with a back-propagation network – ident: ref15 doi: 10.1109/ICRA40945.2020.9196816 – ident: ref31 doi: 10.1126/scirobotics.abk2822 – ident: ref32 doi: 10.1109/ICRA48506.2021.9561639 – year: 2021 ident: ref64 article-title: ViTAL accompanying video – ident: ref27 doi: 10.1109/LRA.2020.3007475 – ident: ref74 doi: 10.1109/IROS.2004.1389727 – ident: ref54 doi: 10.1109/IROS45743.2020.9341128 – ident: ref5 doi: 10.1109/IROS.2018.8593885 – ident: ref25 doi: 10.1109/TRO.2020.3003464 – year: 2006 ident: ref69 article-title: Representing attitude: Euler angles, unit quaternions, and rotation vectors – ident: ref2 doi: 10.1126/scirobotics.abb2174 – ident: ref57 doi: 10.1016/j.neunet.2015.05.005 – volume-title: Pattern Recognition and Machine Learning year: 2006 ident: ref67 – ident: ref52 doi: 10.1109/ACCESS.2019.2933178 – ident: ref55 doi: 10.1109/LRA.2021.3066833 – ident: ref33 doi: 10.15607/RSS.2021.XVII.011 – ident: ref19 doi: 10.1109/ICRA.2016.7487541 – start-page: 91 volume-title: Proc. Conf. Robot Learn. year: 2021 ident: ref29 article-title: Learning to walk in minutes using massively parallel deep reinforcement learning – ident: ref62 doi: 10.1177/0959651811402275 – ident: ref72 doi: 10.1137/S1052623497325107 – ident: ref4 doi: 10.1109/ICRA.2019.8793865 – ident: ref43 doi: 10.1109/IROS.2009.5354701 – ident: ref63 doi: 10.1007/978-3-319-26054-9_5 – ident: ref58 doi: 10.1142/9789814525534_0056 – start-page: 1 volume-title: Proc. Int. Conf. Mach. Learn. year: 2013 ident: ref66 article-title: Rectifier non-linearities improve neural network acoustic models – ident: ref6 doi: 10.1109/IROS.2016.7758092 – ident: ref60 doi: 10.1109/TRO.2015.2482061 – ident: ref13 doi: 10.1109/IROS45743.2020.9341751 – ident: ref41 doi: 10.1109/TRO.2018.2819658 – start-page: 8026 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. year: 2019 ident: ref70 article-title: PyTorch: An imperative style, high-performance deep learning library – ident: ref47 doi: 10.1109/LRA.2021.3088797
SSID	ssj0024903
Score	2.533055
Snippet	This article focuses on vision-based planning strategies for legged robots that separate locomotion planning into foothold selection and pose adaptation....
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Adaptation Algorithms Foot Forward error correction Legged locomotion Legged robots Locomotion Optimization optimization and optimal control Planning Robot dynamics Robots Strategy Terrain Trajectory visual learning whole-body motion planning and control
Title	ViTAL: Vision-Based Terrain-Aware Locomotion for Legged Robots
URI	https://ieeexplore.ieee.org/document/9966331 https://www.proquest.com/docview/2795805195
Volume	39
WOSCitedRecordID	wos000912783200001&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 Xplore Digital Library 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/eLvHCXMwlV1LS8NAEF5q8aAHX1WsVsnBi2Da7G7a7HoQqlg8hCollt7CPktBGklT_fvubtKqKIKXkMMMhG8ymZnszHwAXATcxCGNQ1ObcHMhEPuEh9LXAkIGYcSj0tJxNBySyYQ-1cDVehZGKeWaz1Tb3rqzfJmJpf1V1rG5ObZD0xtR1CtntT736lHHgmw3ivk4oGR1JBnQTjJ6NIUgQm3syKvJtxDkOFV-fIhddBns_u-59sBOlUV6_dLs-6Cm5gdg-8tuwQa4Gc-Sfnztjd3wuH9ropX0EpVbSgi__85y5cWZyEoWH8-krl6splMjM8p4ViwOwfPgPrl78CuyBF8gCgtf9noBlZTbnixEtfFDpAVmIWeaB1oJorqS0whTIrtCYIyM59ltcAxBpqGG-AjU59lcHQMvYoQLRqWQWITcIKsJZ5IRhhUkJMRN0Fnhl4pqk7gltHhJXUUR0NQgnlrE0wrxJrhca7yWWzT-kG1YhNdyFbhN0FqZKK3cbJGiyCjYJLR78rvWKdiy_PBlq00L1It8qc7ApngrZov83L1BH1Oywfs
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5KFdSDryrWZw5eBNNmd1Oz60GooijGKhLFW9inCNJIW_Xvu7tJq6IIXkIOMxC-yWRmsjPzAexGwsYhQ2Jbmwh7oYiEVMQqNBIhjlAiktLSadLr0YcHdlOD_cksjNbaN5_plrv1Z_mqkK_uV1nb5ebEDU1PdeIYR-W01udmPeZ5kN1OsZBEjI4PJSPWzm6vbSmIcYt4-mr6LQh5VpUfn2IfX84W_vdkizBf5ZFBtzT8EtR0fxnmvmwXbMDR_VPWTQ-Dez8-Hh7beKWCTA8cKUTYfecDHaSFLEoen8Amr0GqHx-tzG0hitFwBe7OTrOT87CiSwglZmgUqoODiCkmXFcWZsZ6IjaS8FhwIyKjJdUdJVhCGFUdKQnB1vfcPjiOETfIILIK9X7R12sQJJwKyZmSishYWGQNFVxxyolGlMakCe0xfrmsdok7Sovn3NcUEcst4rlDPK8Qb8LeROOl3KPxh2zDITyRq8BtwubYRHnlaMMcJ1bBpaGd9d-1dmDmPLtK8_Sid7kBs44tvmy82YT6aPCqt2Bavo2ehoNt_zZ9AJcQxUI
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=ViTAL%3A+Vision-Based+Terrain-Aware+Locomotion+for+Legged+Robots&rft.jtitle=IEEE+transactions+on+robotics&rft.au=Fahmi%2C+Shamel&rft.au=Barasuol%2C+Victor&rft.au=Esteban%2C+Domingo&rft.au=Villarreal%2C+Octavio&rft.date=2023-04-01&rft.pub=IEEE&rft.issn=1552-3098&rft.spage=1&rft.epage=20&rft_id=info:doi/10.1109%2FTRO.2022.3222958&rft.externalDocID=9966331
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