Learning Robust Control Policies for End-to-End Autonomous Driving From Data-Driven Simulation

In this work, we present a data-driven simulation and training engine capable of learning end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging real, human-collected trajectories through an environment, we render novel training data that allows virtual agents to dri...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE robotics and automation letters Ročník 5; číslo 2; s. 1142 - 1149
Hlavní autoři:	Amini, Alexander, Gilitschenski, Igor, Phillips, Jacob, Moseyko, Julia, Banerjee, Rohan, Karaman, Sertac, Rus, Daniela
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.04.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Access control autonomous agents Autonomous vehicles data-driven simulation Deep learning in robotics and automation Machine learning Policies real world reinforcement learning Roads & highways Robust control Semantics Simulation Training
ISSN:	2377-3766, 2377-3766
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In this work, we present a data-driven simulation and training engine capable of learning end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging real, human-collected trajectories through an environment, we render novel training data that allows virtual agents to drive along a continuum of new local trajectories consistent with the road appearance and semantics, each with a different view of the scene. We demonstrate the ability of policies learned within our simulator to generalize to and navigate in previously unseen real-world roads, without access to any human control labels during training. Our results validate the learned policy onboard a full-scale autonomous vehicle, including in previously un-encountered scenarios, such as new roads and novel, complex, near-crash situations. Our methods are scalable, leverage reinforcement learning, and apply broadly to situations requiring effective perception and robust operation in the physical world.
AbstractList	In this work, we present a data-driven simulation and training engine capable of learning end-to-end autonomous vehicle control policies using only sparse rewards. By leveraging real, human-collected trajectories through an environment, we render novel training data that allows virtual agents to drive along a continuum of new local trajectories consistent with the road appearance and semantics, each with a different view of the scene. We demonstrate the ability of policies learned within our simulator to generalize to and navigate in previously unseen real-world roads, without access to any human control labels during training. Our results validate the learned policy onboard a full-scale autonomous vehicle, including in previously un-encountered scenarios, such as new roads and novel, complex, near-crash situations. Our methods are scalable, leverage reinforcement learning, and apply broadly to situations requiring effective perception and robust operation in the physical world.
Author	Amini, Alexander Karaman, Sertac Phillips, Jacob Moseyko, Julia Gilitschenski, Igor Rus, Daniela Banerjee, Rohan
Author_xml	– sequence: 1 givenname: Alexander orcidid: 0000-0002-9673-1267 surname: Amini fullname: Amini, Alexander email: amini@mit.edu organization: Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States of America – sequence: 2 givenname: Igor orcidid: 0000-0001-6426-365X surname: Gilitschenski fullname: Gilitschenski, Igor email: igilitschenski@mit.edu organization: Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States of America – sequence: 3 givenname: Jacob orcidid: 0000-0002-3276-7914 surname: Phillips fullname: Phillips, Jacob email: jdp99@mit.edu organization: Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States of America – sequence: 4 givenname: Julia orcidid: 0000-0002-4977-4918 surname: Moseyko fullname: Moseyko, Julia email: jmoseyko@mit.edu organization: Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States of America – sequence: 5 givenname: Rohan orcidid: 0000-0001-9235-0478 surname: Banerjee fullname: Banerjee, Rohan email: rohanb@mit.edu organization: Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States of America – sequence: 6 givenname: Sertac orcidid: 0000-0002-2225-7275 surname: Karaman fullname: Karaman, Sertac email: sertac@mit.edu organization: Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, United States of America – sequence: 7 givenname: Daniela orcidid: 0000-0001-5473-3566 surname: Rus fullname: Rus, Daniela email: rus@mit.edu organization: Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, United States of America
BookMark	eNp9kM1LwzAYxoNMcM7dBS8Bz535aNLmOPahwkCZerWkaSoZbTKTVPC_t3VDxIOn5-Xl-b0fzzkYWWc1AJcYzTBG4maznc8IImhGBOcpTk_AmNAsS2jG-ehXfQamIewQQpiRjAo2Bq8bLb019g1uXdmFCBfORu8a-Ogao4wOsHYermyVRJf0AudddNa1rgtw6c3HQK69a-FSRpkMHW3hk2m7Rkbj7AU4rWUT9PSoE_CyXj0v7pLNw-39Yr5JFKU0JjVOqSqZkipLecZLzqUotaipkCLHEhGJ6v4zmbMyRajkWOWaI1rluiJVWaV0Aq4Pc_fevXc6xGLnOm_7lQWhjOBciIz1Ln5wKe9C8LoulInfd0YvTVNgVAxxFn2cxRBncYyzB9EfcO9NK_3nf8jVATFa6x97LljG8pR-AfEXgcc
CODEN	IRALC6
CitedBy_id	crossref_primary_10_1016_j_patcog_2024_110532 crossref_primary_10_1109_TIV_2020_3002505 crossref_primary_10_1109_ACCESS_2020_3040896 crossref_primary_10_3390_electronics12020302 crossref_primary_10_3390_s21113606 crossref_primary_10_1109_ACCESS_2025_3539761 crossref_primary_10_1109_JSEN_2023_3280959 crossref_primary_10_1109_LRA_2024_3368234 crossref_primary_10_1109_JIOT_2024_3513642 crossref_primary_10_1038_s41598_022_14737_2 crossref_primary_10_1109_TITS_2022_3177224 crossref_primary_10_1145_3460082 crossref_primary_10_1016_j_jnca_2023_103648 crossref_primary_10_1109_TITS_2024_3368136 crossref_primary_10_1109_TPAMI_2024_3435937 crossref_primary_10_3390_s22186793 crossref_primary_10_1109_ACCESS_2024_3496578 crossref_primary_10_1016_j_tre_2024_103748 crossref_primary_10_1007_s00521_024_09732_9 crossref_primary_10_1109_ACCESS_2024_3406219 crossref_primary_10_1109_TITS_2025_3558958 crossref_primary_10_1186_s10033_025_01336_1 crossref_primary_10_3390_s22124500 crossref_primary_10_1109_TITS_2025_3532803 crossref_primary_10_3390_info14050290 crossref_primary_10_1038_s42256_020_00237_3 crossref_primary_10_1007_s42421_023_00086_7 crossref_primary_10_1016_j_trc_2021_103008 crossref_primary_10_3390_electronics14152919 crossref_primary_10_1080_15472450_2025_2559224 crossref_primary_10_1109_LRA_2020_3039730 crossref_primary_10_1145_3749992 crossref_primary_10_1016_j_conengprac_2024_105947 crossref_primary_10_1109_TITS_2024_3452480 crossref_primary_10_1016_j_engappai_2025_111285 crossref_primary_10_1016_j_jocs_2023_102119 crossref_primary_10_1109_ACCESS_2021_3098675 crossref_primary_10_1109_TC_2023_3310678 crossref_primary_10_1016_j_jksuci_2022_03_013 crossref_primary_10_3390_robotics12050133 crossref_primary_10_1109_LRA_2021_3061336 crossref_primary_10_3390_app13116700 crossref_primary_10_3390_en13112917 crossref_primary_10_3390_ai5040105 crossref_primary_10_3390_s22208055 crossref_primary_10_1109_MNET_2023_3334285 crossref_primary_10_3389_frvir_2021_721933 crossref_primary_10_1109_TITS_2021_3131303 crossref_primary_10_1109_TIV_2022_3174029 crossref_primary_10_1177_01423312231197854 crossref_primary_10_1038_s42256_022_00556_7 crossref_primary_10_1016_j_neucom_2024_127874 crossref_primary_10_1109_TPAMI_2021_3102140 crossref_primary_10_3390_app15105424 crossref_primary_10_1016_j_neucom_2024_128161 crossref_primary_10_1016_j_isatra_2024_05_010 crossref_primary_10_1049_cvi2_12074 crossref_primary_10_1109_TASE_2024_3410891 crossref_primary_10_1016_j_infsof_2025_107859 crossref_primary_10_1109_JAS_2023_123375 crossref_primary_10_1016_j_prime_2024_100810 crossref_primary_10_1287_opre_2023_2436 crossref_primary_10_3390_s23208473 crossref_primary_10_1016_j_nic_2020_08_007 crossref_primary_10_1109_LCOMM_2023_3274649 crossref_primary_10_1109_TIV_2022_3195635 crossref_primary_10_1016_j_engappai_2024_109600 crossref_primary_10_1016_j_asoc_2024_111265 crossref_primary_10_1016_j_commtr_2025_100191 crossref_primary_10_1016_j_ifacol_2023_10_1670 crossref_primary_10_1109_LRA_2025_3555938 crossref_primary_10_1109_TRO_2023_3249564 crossref_primary_10_1007_s13177_023_00356_2 crossref_primary_10_1109_LRA_2024_3387109 crossref_primary_10_1007_s11044_022_09816_1 crossref_primary_10_1109_ACCESS_2024_3385122 crossref_primary_10_1016_j_jmsy_2024_10_008 crossref_primary_10_1109_TRO_2024_3400937 crossref_primary_10_1016_j_trc_2024_104654 crossref_primary_10_1177_09544062211064797 crossref_primary_10_1007_s11370_021_00398_z crossref_primary_10_1109_TCDS_2020_3006621 crossref_primary_10_1109_TEM_2022_3201434 crossref_primary_10_3390_rs15194757 crossref_primary_10_1016_j_eswa_2023_120495
Cites_doi	10.1109/IROS40897.2019.8968116 10.1109/CVPR.2018.00945 10.1109/IROS.2017.8202133 10.1109/IVS.2017.7995835 10.1109/ICRA.2018.8460487 10.1109/ICRA.2018.8461253 10.1109/ICRA.2019.8793579 10.1109/ICRA.2019.8793742 10.1126/scirobotics.aau4984 10.1126/scirobotics.aaw0863 10.1007/978-3-319-67361-5_40 10.1109/CVPR.2017.632 10.5244/C.31.11 10.1109/ICCV.2015.312 10.1109/IROS.2018.8594386 10.1109/CVPR.2017.699 10.1109/IROS.2018.8594090 10.1007/BF00992696 10.1109/LRA.2015.2509024 10.1109/IVS.2017.7995938 10.1109/IVS.2015.7225830 10.1109/ICRA.2019.8793668 10.24963/ijcai.2018/682
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LRA.2020.2966414
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology 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 Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2377-3766
EndPage	1149
ExternalDocumentID	10_1109_LRA_2020_2966414 8957584
Genre	orig-research
GrantInformation_xml	– fundername: National Science Foundation funderid: 10.13039/100000001 – fundername: Toyota Research Institute – fundername: NVIDIA Corporation
GroupedDBID	0R~ 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD ESBDL IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c333t-f143cb5cac74676b66a9be9f39a981a02a0f966a85b400b61c8e603d8ed2dbd43
IEDL.DBID	RIE
ISICitedReferencesCount	143
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000526691200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2377-3766
IngestDate	Mon Jun 30 07:47:40 EDT 2025 Tue Nov 18 22:41:06 EST 2025 Sat Nov 29 06:03:05 EST 2025 Wed Aug 27 02:35:30 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-f143cb5cac74676b66a9be9f39a981a02a0f966a85b400b61c8e603d8ed2dbd43
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6426-365X 0000-0001-5473-3566 0000-0002-9673-1267 0000-0002-3276-7914 0000-0002-2225-7275 0000-0001-9235-0478 0000-0002-4977-4918
OpenAccessLink	https://ieeexplore.ieee.org/document/8957584
PQID	2352189975
PQPubID	4437225
PageCount	8
ParticipantIDs	ieee_primary_8957584 crossref_primary_10_1109_LRA_2020_2966414 crossref_citationtrail_10_1109_LRA_2020_2966414 proquest_journals_2352189975
PublicationCentury	2000
PublicationDate	2020-04-01
PublicationDateYYYYMMDD	2020-04-01
PublicationDate_xml	– month: 04 year: 2020 text: 2020-04-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2020
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	ref35 ref13 ref36 muller (ref38) 0 ref31 ref30 ref33 ref11 ref39 ref16 ref19 ref18 bojarski (ref2) 2016 henaff (ref17) 2019 andrychowicz (ref10) 2018 liu (ref37) 0 bansal (ref15) 2018 pomerleau (ref1) 0 dosovitskiy (ref34) 2017 xiao (ref21) 2019 amini (ref23) 2018 ref24 ref26 ref25 ref20 sadeghi (ref12) 2016 ref22 bruce (ref14) 2018 ref28 ref27 ref8 ref7 liu (ref29) 0 ref9 ref4 ref3 sutton (ref32) 0 dosovitskiy (ref5) 0 tedrake (ref6) 2019
References_xml	– year: 2018 ident: ref10 article-title: Learning dexterous in-hand manipulation publication-title: arXiv 1808 00177 – ident: ref26 doi: 10.1109/IROS40897.2019.8968116 – ident: ref25 doi: 10.1109/CVPR.2018.00945 – year: 2016 ident: ref12 article-title: Cad2rl: Real single-image flight without a single real image publication-title: arXiv 1611 04201 – ident: ref13 doi: 10.1109/IROS.2017.8202133 – year: 2019 ident: ref6 article-title: Drake: Model-based design and verification for robotics – ident: ref35 doi: 10.1109/IVS.2017.7995835 – ident: ref8 doi: 10.1109/ICRA.2018.8460487 – ident: ref22 doi: 10.1109/ICRA.2018.8461253 – ident: ref3 doi: 10.1109/ICRA.2019.8793579 – year: 2019 ident: ref21 article-title: Multimodal end-to-end autonomous driving publication-title: arXiv 1906 03199 – start-page: 739 year: 0 ident: ref38 article-title: Off-road obstacle avoidance through end-to-end learning publication-title: Proc Adv Neural Inf Process Syst – ident: ref4 doi: 10.1109/ICRA.2019.8793742 – ident: ref11 doi: 10.1126/scirobotics.aau4984 – start-page: 1057 year: 0 ident: ref32 article-title: Policy gradient methods for reinforcement learning with function approximation publication-title: Proc Adv Neural Inf Process Syst – ident: ref27 doi: 10.1126/scirobotics.aaw0863 – start-page: 85 year: 0 ident: ref29 article-title: Image inpainting for irregular holes using partial convolutions publication-title: Proc Eur Conf Comput Vision – ident: ref7 doi: 10.1007/978-3-319-67361-5_40 – start-page: 305 year: 0 ident: ref1 article-title: ALVINN: An autonomous land vehicle in a neural network publication-title: Proc Proc Adv Neural Inf Process Syst – ident: ref36 doi: 10.1109/CVPR.2017.632 – ident: ref24 doi: 10.5244/C.31.11 – ident: ref16 doi: 10.1109/ICCV.2015.312 – ident: ref19 doi: 10.1109/IROS.2018.8594386 – ident: ref28 doi: 10.1109/CVPR.2017.699 – ident: ref20 doi: 10.1109/IROS.2018.8594090 – year: 2018 ident: ref14 article-title: Learning deployable navigation policies at kilometer scale from a single traversal publication-title: arXiv 1807 05211 – ident: ref31 doi: 10.1007/BF00992696 – year: 2018 ident: ref23 article-title: Spatial uncertainty sampling for end-to-end control publication-title: arXiv 1805 04829 – start-page: 700 year: 0 ident: ref37 article-title: Unsupervised image-to-image translation networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref33 doi: 10.1109/LRA.2015.2509024 – year: 2018 ident: ref15 article-title: Chauffeurnet: Learning to drive by imitating the best and synthesizing the worst publication-title: arXiv 1812 03079 – start-page: 1 year: 0 ident: ref5 article-title: CARLA: An open urban driving simulator publication-title: Proc 1st Annu Conf Robot Learn – year: 2016 ident: ref2 article-title: End to end learning for self-driving cars publication-title: arXiv 1604 07316 [cs] – year: 2019 ident: ref17 article-title: Model-predictive policy learning with uncertainty regularization for driving in dense traffic publication-title: arXiv 1901 02705 – year: 2017 ident: ref34 article-title: Carla: An open urban driving simulator publication-title: arXiv 1711 03938 – ident: ref39 doi: 10.1109/IVS.2017.7995938 – ident: ref30 doi: 10.1109/IVS.2015.7225830 – ident: ref9 doi: 10.1109/ICRA.2019.8793668 – ident: ref18 doi: 10.24963/ijcai.2018/682
SSID	ssj0001527395
Score	2.5667899
Snippet	In this work, we present a data-driven simulation and training engine capable of learning end-to-end autonomous vehicle control policies using only sparse...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1142
SubjectTerms	Access control autonomous agents Autonomous vehicles data-driven simulation Deep learning in robotics and automation Machine learning Policies real world reinforcement learning Roads & highways Robust control Semantics Simulation Training
Title	Learning Robust Control Policies for End-to-End Autonomous Driving From Data-Driven Simulation
URI	https://ieeexplore.ieee.org/document/8957584 https://www.proquest.com/docview/2352189975
Volume	5
WOSCitedRecordID	wos000526691200001&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 customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: RIE dateStart: 20160101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: M~E dateStart: 20160101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB52xYsH3-L6WHLwIlg3fSfHRXfxoIusDzxZkjSRBW1lt_Xob3fSdldFEby0pSRQZprk-yaZbwCOtAwZEmXhaGMMEhQhHCEMXhDaIu-JUlop3txfxqMRe3jg1y04WeTCaK2rw2f61D5We_lprkobKusxjuCCBW1ox3Fc52p9xlOskhgP5zuRlPcux33kfx499RDSB27wbeWpSqn8mH-rRWW49r_PWYfVBjySfu3tDWjpbBNWvkgKbsFjI5j6RMa5LGcFOavPopNKABhpMUGUSgZZ6hS5gzfSLwub15CXM3I-ndjwAhlO8xdyLgrh2Dc6IzeTl6bK1zbcDQe3ZxdOU0PBUb7vF45BPKRkqISydUUiGUWCS82NzwVnrqCeoAbNI1gocTTLyFVMR9RPmU69VKaBvwNLWZ7pXSChwMnR4HomXR6wwBd-bDiagIo4VjLwOtCb2zdRjcC4rXPxnFREg_IEPZJYjySNRzpwvOjxWotr_NF2y3pg0a4xfgcO5i5MmtE3SzxElS4SyTjc-73XvqXn1K1zCg9gqZiW-hCW1VsxmU270L56H3Sr3-sDUxXN0Q
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1db9MwFL0qGxLbAxsUtG7d8AMvSKTNh5PYj1U_tImuQqWgPhHZjo0qsWRKE34_10laQEyT9pJEka1Y98b2Odf2uQDvtQwZEmXhaGMMEhQhHCEMXhDaIu-JUrdWvPk2jxcLtl7zzx34uD8Lo7WuN5_pgX2s1_LTXFU2VDZkHMEFo8_gMKTU95rTWn8iKlZLjIe7tUiXD-fLETJA3x34COqpR_-Ze-pkKv-NwPW0Mjt5WoNO4WULH8mo8fcr6OjsNRz_JSrYhe-tZOoPssxltS3JuNmNTmoJYCTGBHEqmWapU-YO3sioKu3JhrzakkmxsQEGMivyOzIRpXDsG52RL5u7Ns_XG_g6m67G106bRcFRQRCUjkFEpGSohLKZRSIZRYJLzU3ABWeecH3hGjSPYKHE_iwjTzEduUHKdOqnMqXBWzjI8kyfAQkFDo8GZzTpccpoIILYcDSBK-JYSer3YLizb6JaiXGb6eJnUlMNlyfokcR6JGk90oMP-xr3jbzGI2W71gP7cq3xe9DfuTBp-9828RFXekgl4_D84Vrv4MX16naezG8Wny7gyH6n2Y_Th4OyqPQlPFe_ys22uKp_st9R4s_s
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=Learning+Robust+Control+Policies+for+End-to-End+Autonomous+Driving+From+Data-Driven+Simulation&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Amini%2C+Alexander&rft.au=Gilitschenski%2C+Igor&rft.au=Phillips%2C+Jacob&rft.au=Moseyko%2C+Julia&rft.date=2020-04-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=5&rft.issue=2&rft.spage=1143&rft.epage=1150&rft_id=info:doi/10.1109%2FLRA.2020.2966414&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2020_2966414
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3766&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3766&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3766&client=summon