Deep Reinforcement Learning Robot for Search and Rescue Applications: Exploration in Unknown Cluttered Environments

Rescue robots can be used in urban search and rescue (USAR) applications to perform the important task of exploring unknown cluttered environments. Due to the unpredictable nature of these environments, deep learning techniques can be used to perform these tasks. In this letter, we present the first...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE robotics and automation letters Ročník 4; číslo 2; s. 610 - 617
Hlavní autoři:	Niroui, Farzad, Kaicheng Zhang, Kashino, Zendai, Nejat, Goldie
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 01.04.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Autonomous agents Computer architecture Deep learning deep learning in robotics and automation Exploration Layout Layouts Machine learning Microprocessors Navigation Robot sensing systems Robots Search and rescue missions search and rescue robots Task analysis Wideband communications
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	Rescue robots can be used in urban search and rescue (USAR) applications to perform the important task of exploring unknown cluttered environments. Due to the unpredictable nature of these environments, deep learning techniques can be used to perform these tasks. In this letter, we present the first use of deep learning to address the robot exploration task in USAR applications. In particular, we uniquely combine the traditional approach of frontier-based exploration with deep reinforcement learning to allow a robot to autonomously explore unknown cluttered environments. Experiments conducted with a mobile robot in unknown cluttered environments of varying sizes and layouts showed that the proposed exploration approach can effectively determine appropriate frontier locations to navigate to, while being robust to different environment layouts and sizes. Furthermore, a comparison study with other frontier exploration approaches showed that our learning-based frontier exploration technique was able to explore more of an environment earlier on, allowing for potential identification of a larger number of victims at the beginning of the time-critical exploration task.
AbstractList	Rescue robots can be used in urban search and rescue (USAR) applications to perform the important task of exploring unknown cluttered environments. Due to the unpredictable nature of these environments, deep learning techniques can be used to perform these tasks. In this letter, we present the first use of deep learning to address the robot exploration task in USAR applications. In particular, we uniquely combine the traditional approach of frontier-based exploration with deep reinforcement learning to allow a robot to autonomously explore unknown cluttered environments. Experiments conducted with a mobile robot in unknown cluttered environments of varying sizes and layouts showed that the proposed exploration approach can effectively determine appropriate frontier locations to navigate to, while being robust to different environment layouts and sizes. Furthermore, a comparison study with other frontier exploration approaches showed that our learning-based frontier exploration technique was able to explore more of an environment earlier on, allowing for potential identification of a larger number of victims at the beginning of the time-critical exploration task.
Author	Nejat, Goldie Kaicheng Zhang Niroui, Farzad Kashino, Zendai
Author_xml	– sequence: 1 givenname: Farzad surname: Niroui fullname: Niroui, Farzad email: farzad.niroui@mail.utoronto.ca organization: Dept. of Mech. & Ind. Eng., Univ. of Toronto, Toronto, ON, Canada – sequence: 2 surname: Kaicheng Zhang fullname: Kaicheng Zhang email: kc.zhang@mail.utoronto.ca organization: Dept. of Mech. & Ind. Eng., Univ. of Toronto, Toronto, ON, Canada – sequence: 3 givenname: Zendai surname: Kashino fullname: Kashino, Zendai email: zendkash@mie.utoronto.ca organization: Dept. of Mech. & Ind. Eng., Univ. of Toronto, Toronto, ON, Canada – sequence: 4 givenname: Goldie surname: Nejat fullname: Nejat, Goldie email: nejat@mie.utoronto.ca organization: Dept. of Mech. & Ind. Eng., Univ. of Toronto, Toronto, ON, Canada
BookMark	eNp9UElLAzEUDqJgrb0LXgKeW7N0ksZbqXWBglDteZjJvNHUaTImGZd_70xbRDx4etu38L4TdGidBYTOKBlRStTlYjkdMULViE0UVYoeoB7jUg65FOLwV3-MBiGsCSE0YZKrpIfCNUCNl2Bs6byGDdiIF5B5a-wzXrrcRdwe8GO70i84s0WLDboBPK3ryugsGmfDFZ5_1pXz2wkbi1f21boPi2dVEyN4KPDcvhvvbKcfTtFRmVUBBvvaR6ub-dPsbrh4uL2fTRdDzRMZh5QA6JxJmjEOLE8UF2WSywmlBU9YkWsihC7lWGWCFmM55kooJktdJAmjTGjeRxc73dq7twZCTNeu8ba1TBlTkw7PSYsiO5T2LgQPZVp7s8n8V0pJ2qWbtummXbrpPt2WIv5QtInb56PPTPUf8XxHNADw4zMRRHTXbwhNiZQ
CODEN	IRALC6
CitedBy_id	crossref_primary_10_1038_s42256_024_00859_x crossref_primary_10_1007_s13042_024_02170_y crossref_primary_10_3390_math13010173 crossref_primary_10_1109_TVT_2020_3034800 crossref_primary_10_1109_TGRS_2024_3401393 crossref_primary_10_1017_S0263574721001946 crossref_primary_10_1109_LRA_2022_3190628 crossref_primary_10_1088_1742_6596_2641_1_012003 crossref_primary_10_3390_aerospace12070642 crossref_primary_10_1016_j_anucene_2024_110398 crossref_primary_10_1214_25_AOS2501 crossref_primary_10_3389_frobt_2021_738113 crossref_primary_10_1109_LRA_2021_3093551 crossref_primary_10_1007_s43154_021_00045_6 crossref_primary_10_3389_frobt_2024_1336612 crossref_primary_10_1109_JPROC_2022_3223186 crossref_primary_10_3390_app12189249 crossref_primary_10_3390_s23041813 crossref_primary_10_1002_smb2_12008 crossref_primary_10_1109_LRA_2021_3062011 crossref_primary_10_3390_s21082577 crossref_primary_10_1016_j_jai_2022_100006 crossref_primary_10_3390_jmse12091622 crossref_primary_10_3390_s22218562 crossref_primary_10_1016_j_buildenv_2022_109806 crossref_primary_10_1016_j_eswa_2024_123202 crossref_primary_10_1002_rob_21951 crossref_primary_10_20965_jaciii_2024_p0273 crossref_primary_10_1007_s11227_023_05551_2 crossref_primary_10_1186_s40648_022_00221_z crossref_primary_10_3390_su142316151 crossref_primary_10_1007_s10846_023_01888_1 crossref_primary_10_1016_j_compag_2025_110651 crossref_primary_10_1109_TIV_2024_3369730 crossref_primary_10_1109_TASE_2024_3475735 crossref_primary_10_3390_s21248331 crossref_primary_10_1007_s43154_020_00030_5 crossref_primary_10_1109_ACCESS_2021_3108177 crossref_primary_10_1109_ACCESS_2025_3581035 crossref_primary_10_3390_s21041076 crossref_primary_10_3390_app14199127 crossref_primary_10_1007_s11432_022_3904_9 crossref_primary_10_3390_app14083215 crossref_primary_10_1109_LRA_2022_3224667 crossref_primary_10_1016_j_comcom_2019_11_031 crossref_primary_10_1109_TAFFC_2022_3221922 crossref_primary_10_1177_02783649231218720 crossref_primary_10_3390_s19163542 crossref_primary_10_1088_1757_899X_705_1_012037 crossref_primary_10_1177_10775463231161847 crossref_primary_10_1109_LRA_2021_3118078 crossref_primary_10_1088_1757_899X_912_3_032023 crossref_primary_10_1109_ACCESS_2020_3036938 crossref_primary_10_1109_ACCESS_2022_3190538 crossref_primary_10_3390_app11052408 crossref_primary_10_1109_JIOT_2022_3142274 crossref_primary_10_1109_ACCESS_2023_3308948 crossref_primary_10_1109_LRA_2024_3396059 crossref_primary_10_1109_ACCESS_2023_3293035 crossref_primary_10_3390_app10238386 crossref_primary_10_1109_TASE_2024_3483932 crossref_primary_10_1109_LRA_2022_3208349 crossref_primary_10_3390_s20226507 crossref_primary_10_1002_asmb_2723 crossref_primary_10_1007_s42452_021_04595_4 crossref_primary_10_1109_TRO_2023_3248510 crossref_primary_10_3390_app13148174 crossref_primary_10_1016_j_engappai_2024_109131 crossref_primary_10_1109_TASE_2022_3180345 crossref_primary_10_3390_app11188299 crossref_primary_10_1109_ACCESS_2021_3133567 crossref_primary_10_1109_LRA_2024_3359970 crossref_primary_10_1109_LRA_2024_3521179 crossref_primary_10_1016_j_engappai_2025_111904 crossref_primary_10_1016_j_robot_2025_105010 crossref_primary_10_1016_j_robot_2025_105131 crossref_primary_10_1109_LRA_2022_3212670 crossref_primary_10_1007_s40747_023_01144_x crossref_primary_10_1017_S026357472510221X crossref_primary_10_1109_TITS_2023_3285624 crossref_primary_10_1109_LRA_2025_3592098 crossref_primary_10_1016_j_robot_2024_104783 crossref_primary_10_1109_ACCESS_2020_3040896 crossref_primary_10_3390_drones7040246 crossref_primary_10_1038_s41598_025_97231_9 crossref_primary_10_3390_electronics10222751 crossref_primary_10_1088_1742_6596_2115_1_012009 crossref_primary_10_3390_s22114031 crossref_primary_10_1109_LRA_2023_3337593 crossref_primary_10_1007_s10489_020_01758_5 crossref_primary_10_1109_LRA_2021_3094557 crossref_primary_10_1109_TVT_2024_3390571 crossref_primary_10_3390_biomimetics10090627 crossref_primary_10_1109_TVT_2024_3489229 crossref_primary_10_1109_ACCESS_2019_2954281 crossref_primary_10_1038_s41598_021_98643_z crossref_primary_10_1109_ACCESS_2019_2929120 crossref_primary_10_1007_s10489_022_04356_9 crossref_primary_10_1007_s10846_025_02235_2 crossref_primary_10_1017_S0263574725000062 crossref_primary_10_3390_fi13100261 crossref_primary_10_1007_s40747_024_01777_6 crossref_primary_10_1109_TRO_2024_3422052 crossref_primary_10_1016_j_robot_2024_104727 crossref_primary_10_1109_LRA_2021_3116703 crossref_primary_10_1111_mice_13535 crossref_primary_10_1007_s10846_020_01262_5 crossref_primary_10_1007_s11269_020_02600_w crossref_primary_10_1016_j_asoc_2022_109482 crossref_primary_10_1109_LRA_2022_3145971 crossref_primary_10_1109_TNNLS_2023_3262956 crossref_primary_10_3389_frai_2024_1308031 crossref_primary_10_1109_TIE_2024_3370939 crossref_primary_10_1109_TRO_2024_3454572 crossref_primary_10_1049_cth2_12125 crossref_primary_10_1007_s10489_023_04959_w crossref_primary_10_1088_1742_6596_2698_1_012025 crossref_primary_10_1109_ACCESS_2020_3030963 crossref_primary_10_3390_rs13234881 crossref_primary_10_1007_s11633_024_1512_6 crossref_primary_10_1109_LRA_2025_3557233 crossref_primary_10_1109_JAS_2023_123087 crossref_primary_10_1109_LRA_2022_3157028 crossref_primary_10_1109_TNNLS_2021_3124466 crossref_primary_10_3390_s25020439 crossref_primary_10_1109_ACCESS_2020_3030190 crossref_primary_10_1016_j_mechmachtheory_2023_105476 crossref_primary_10_1109_LRA_2024_3502067 crossref_primary_10_1007_s43154_021_00048_3 crossref_primary_10_1109_LRA_2020_3001539 crossref_primary_10_1016_j_cag_2024_104091 crossref_primary_10_1109_ACCESS_2021_3076530 crossref_primary_10_3390_jmse11122258 crossref_primary_10_1049_csy2_70019 crossref_primary_10_1109_LRA_2022_3186511 crossref_primary_10_3390_s21072445 crossref_primary_10_1007_s00034_023_02581_2 crossref_primary_10_3390_drones9070490 crossref_primary_10_1016_j_swevo_2022_101171 crossref_primary_10_1177_02783649241313471 crossref_primary_10_1007_s10846_024_02167_3 crossref_primary_10_1016_j_autcon_2020_103078 crossref_primary_10_1109_TCDS_2023_3250819 crossref_primary_10_3390_s23104766 crossref_primary_10_1109_LRA_2024_3396097 crossref_primary_10_3390_electronics11040574 crossref_primary_10_3389_fnbot_2023_1205775 crossref_primary_10_3390_math13060913 crossref_primary_10_1016_j_future_2022_06_015 crossref_primary_10_1145_3550454_3555483 crossref_primary_10_1016_j_cogr_2023_07_004 crossref_primary_10_1109_ACCESS_2020_3038905 crossref_primary_10_1016_j_ymssp_2025_113029 crossref_primary_10_1109_LRA_2025_3575331
Cites_doi	10.1109/RCAR.2016.7784001 10.1109/IRIS.2017.8250126 10.1007/s10514-011-9249-9 10.1371/journal.pone.0157428 10.1371/journal.pone.0203339 10.1017/9781316671528 10.1007/s10514-012-9298-8 10.1109/SSRR.2007.4381274 10.1371/journal.pone.0198175 10.1177/0278364917734298 10.1177/0278364913495721 10.1109/TCYB.2014.2314294 10.1109/LRA.2016.2520560 10.1109/CIRA.1997.613851 10.1109/IISR.2018.8535823 10.1109/ICRA.2017.7989236 10.1016/j.compeleceng.2016.04.002 10.1109/MSP.2017.2743240 10.1007/s10846-013-9822-x 10.1038/nature14236
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LRA.2019.2891991
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 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	617
ExternalDocumentID	10_1109_LRA_2019_2891991 8606991
Genre	orig-research
GrantInformation_xml	– fundername: Natural Sciences and Engineering Council of Canada – fundername: Canada Research Chairs Program
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 IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D RIG
ID	FETCH-LOGICAL-c357t-10eecb271a23e2b5936f5b7811d352dbc066cf749a61d474396927fcd552126c3
IEDL.DBID	RIE
ISICitedReferencesCount	247
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457917800008&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	Sun Jun 29 14:09:16 EDT 2025 Sat Nov 29 06:03:02 EST 2025 Tue Nov 18 21:35:38 EST 2025 Wed Aug 27 02:47:26 EDT 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-c357t-10eecb271a23e2b5936f5b7811d352dbc066cf749a61d474396927fcd552126c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-6242-6459 0000-0002-7248-1099 0000-0002-7080-6857
PQID	2298396930
PQPubID	4437225
PageCount	8
ParticipantIDs	crossref_primary_10_1109_LRA_2019_2891991 ieee_primary_8606991 crossref_citationtrail_10_1109_LRA_2019_2891991 proquest_journals_2298396930
PublicationCentury	2000
PublicationDate	2019-04-01
PublicationDateYYYYMMDD	2019-04-01
PublicationDate_xml	– month: 04 year: 2019 text: 2019-04-01 day: 01
PublicationDecade	2010
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2019
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 sampedro (ref18) 2018 ref11 ref10 mei (ref8) 0 ref2 wang (ref3) 2018; 33 (ref5) 0 ref1 ref17 mnih (ref23) 2015; 518 ref16 ref19 (ref31) 0 gruslys (ref32) 2017 ref24 zhang (ref25) 2017 ref20 ref22 mnih (ref27) 0; 48 ref21 hausknecht (ref29) 0 (ref30) 0 ref7 garg (ref28) 0 ref9 ref4 ref6 zhang (ref26) 0
References_xml	– ident: ref24 doi: 10.1109/RCAR.2016.7784001 – ident: ref2 doi: 10.1109/IRIS.2017.8250126 – ident: ref7 doi: 10.1007/s10514-011-9249-9 – ident: ref14 doi: 10.1371/journal.pone.0157428 – volume: 48 start-page: 1928 year: 0 ident: ref27 article-title: Asynchronous methods for deep reinforcement learning publication-title: Proc Int Conf Mach Learn – ident: ref13 doi: 10.1371/journal.pone.0203339 – ident: ref4 doi: 10.1017/9781316671528 – ident: ref11 doi: 10.1007/s10514-012-9298-8 – year: 2017 ident: ref32 article-title: The reactor: A fast and sample-efficient actor-critic agent for reinforcement learning publication-title: arXiv170404651 Cs – ident: ref12 doi: 10.1109/SSRR.2007.4381274 – ident: ref15 doi: 10.1371/journal.pone.0198175 – volume: 33 start-page: 394 year: 2018 ident: ref3 article-title: Robot arm perceptive exploration based significant SLAM in publication-title: Int J Robot Automat – ident: ref20 doi: 10.1177/0278364917734298 – ident: ref21 doi: 10.1177/0278364913495721 – year: 2017 ident: ref25 article-title: Neural SLAM: Learning to explore with external memory publication-title: arXiv170609520 Cs – start-page: 740 year: 0 ident: ref28 article-title: Unsupervised CNN for single view depth estimation: Geometry to the rescue publication-title: Proc – year: 0 ident: ref31 – year: 0 ident: ref30 – ident: ref6 doi: 10.1109/TCYB.2014.2314294 – start-page: 1 year: 2018 ident: ref18 article-title: A fully-autonomous aerial robot for search and rescue applications in indoor environments using learning-based techniques publication-title: J Intell Robot Syst – start-page: 1 year: 0 ident: ref26 article-title: Robot navigation of environments with unknown rough terrain using deep reinforcement learning publication-title: Proc IEEE Int Symp Saf Secur Rescue Robot – year: 0 ident: ref5 – ident: ref9 doi: 10.1109/LRA.2016.2520560 – ident: ref10 doi: 10.1109/CIRA.1997.613851 – ident: ref17 doi: 10.1109/IISR.2018.8535823 – ident: ref19 doi: 10.1109/ICRA.2017.7989236 – ident: ref16 doi: 10.1016/j.compeleceng.2016.04.002 – ident: ref22 doi: 10.1109/MSP.2017.2743240 – start-page: 505 year: 0 ident: ref8 article-title: Energy-efficient mobile robot exploration publication-title: Proc IEEE Int Conf Robot Autom – start-page: 29 year: 0 ident: ref29 article-title: Deep Recurrent Q-learning for partially observable MDPs publication-title: Proc AAAI Fall Symp Series – ident: ref1 doi: 10.1007/s10846-013-9822-x – volume: 518 start-page: 529 year: 2015 ident: ref23 article-title: Human-level control through deep reinforcement learning publication-title: Nature doi: 10.1038/nature14236
SSID	ssj0001527395
Score	2.578931
Snippet	Rescue robots can be used in urban search and rescue (USAR) applications to perform the important task of exploring unknown cluttered environments. Due to the...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	610
SubjectTerms	Autonomous agents Computer architecture Deep learning deep learning in robotics and automation Exploration Layout Layouts Machine learning Microprocessors Navigation Robot sensing systems Robots Search and rescue missions search and rescue robots Task analysis Wideband communications
Title	Deep Reinforcement Learning Robot for Search and Rescue Applications: Exploration in Unknown Cluttered Environments
URI	https://ieeexplore.ieee.org/document/8606991 https://www.proquest.com/docview/2298396930
Volume	4
WOSCitedRecordID	wos000457917800008&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/eLvHCXMwlV3NT8IwFH8B4kEPfqERRdKDFxPHx8ZW6o0gxIMSQyThtqztmyEhG-HDo3-7fd1AjMbE25a1S7vf2r6-vvf7AdyoSGqfS8-RbRk7JLbtCG0AkRE5CHWTmyFlxSb4cNiZTMRLAe62uTCIaIPPsE6X9ixfp2pNrrJGx1jbglLVi5zzLFfry59CTGLC35xENkXjadSl0C1RN3sKCvD5tvJYKZUf869dVAZH_2vOMRzmxiPrZmifQAGTUzjYoRQsw_IBcc5GaAlRlfX9sZxD9Y2NUpmumHnAsihjFiXalF2qNbLuzkn2PctC8-wdmyZsnJDvLWG9mdW1Rs36OwlyZzAe9F97j04urOAoz-crM_UiKunyVuR66EoS9Yt9STmn2thjWipjh6iYt0UUtHSbtiyBcHmstE-ZvoHyzqGUpAleAJMGUYzdoOMrYtLTMlZBC4UXuaKjAxVVoLH56KHKWcdJ_GIW2t1HU4QGppBgCnOYKnC7rTHPGDf-KFsmWLblckQqUN3gGuZDchm6pkXUEa95-XutK9ind2dhOVUorRZrvIY99b6aLhc1KD5_9Gv2n_sEx07XXg
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD6MKagP3qY4nZoHXwS7S6-Lb2NuTJxDxgZ7K01yKoPRjV38_eak3Zwogm8tTWjSr0lOTs75PoA7GQnlBcKxhCtii8S2La40ICIiB6GqBnpIGbGJoNerj0b8LQcPm1wYRDTBZ1imS3OWr6ZyRa6ySl1b25xS1Xc817VrabbWl0eFuMS4tz6LrPJKt9-g4C1e1rsKCvH5tvYYMZUfM7BZVtpH_2vQMRxm5iNrpHifQA6TUzjYIhUswOIJccb6aChRpfH-sYxF9Z31p2K6ZPoBS-OMWZQoXXYhV8gaW2fZjywNzjN3bJywYULet4Q1J0bZGhVrbaXIncGw3Ro0O1YmrWBJxwuWevJFlMIOapHtoC1I1i_2BGWdKm2RKSG1JSLjwOWRX1MubVp8bgexVB7l-vrSOYd8Mk3wApjQmGJs-3VPEpeeErH0a8idyOZ15cuoCJX1Rw9lxjtO8heT0Ow_qjzUMIUEU5jBVIT7TY1ZyrnxR9kCwbIplyFShNIa1zAblIvQ1i2ijjjVy99r3cJeZ_DaDbvPvZcr2Kf3pEE6Jcgv5yu8hl35sRwv5jfmz_sEBsnZdA
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=Deep+Reinforcement+Learning+Robot+for+Search+and+Rescue+Applications%3A+Exploration+in+Unknown+Cluttered+Environments&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Niroui%2C+Farzad&rft.au=Zhang%2C+Kaicheng&rft.au=Kashino%2C+Zendai&rft.au=Nejat%2C+Goldie&rft.date=2019-04-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=4&rft.issue=2&rft.spage=610&rft.epage=617&rft_id=info:doi/10.1109%2FLRA.2019.2891991&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2019_2891991
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