A Lifelong Learning Approach to Mobile Robot Navigation

This letter presents a self-improving lifelong learning framework for a mobile robot navigating in different environments. Classical static navigation methods require environment-specific in-situ system adjustment, e.g., from human experts, or may repeat their mistakes regardless of how many times t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE robotics and automation letters Ročník 6; číslo 2; s. 1090 - 1096
Hlavní autoři: Liu, Bo, Xiao, Xuesu, Stone, Peter
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.04.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
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 This letter presents a self-improving lifelong learning framework for a mobile robot navigating in different environments. Classical static navigation methods require environment-specific in-situ system adjustment, e.g., from human experts, or may repeat their mistakes regardless of how many times they have navigated in the same environment. Having the potential to improve with experience, learning-based navigation is highly dependent on access to training resources, e.g., sufficient memory and fast computation, and is prone to forgetting previously learned capability, especially when facing different environments. In this work, we propose Lifelong Learning for Navigation (LLfN) which (1) improves a mobile robot's navigation behavior purely based on its own experience, and (2) retains the robot's capability to navigate in previous environments after learning in new ones. LLfN is implemented and tested entirely onboard a physical robot with a limited memory and computation budget.
AbstractList This letter presents a self-improving lifelong learning framework for a mobile robot navigating in different environments. Classical static navigation methods require environment-specific in-situ system adjustment, e.g., from human experts, or may repeat their mistakes regardless of how many times they have navigated in the same environment. Having the potential to improve with experience, learning-based navigation is highly dependent on access to training resources, e.g., sufficient memory and fast computation, and is prone to forgetting previously learned capability, especially when facing different environments. In this work, we propose Lifelong Learning for Navigation (LLfN) which (1) improves a mobile robot's navigation behavior purely based on its own experience, and (2) retains the robot's capability to navigate in previous environments after learning in new ones. LLfN is implemented and tested entirely onboard a physical robot with a limited memory and computation budget.
Author Liu, Bo
Xiao, Xuesu
Stone, Peter
Author_xml – sequence: 1
  givenname: Bo
  orcidid: 0000-0002-8158-4129
  surname: Liu
  fullname: Liu, Bo
  email: xiao@cs.utexas.edu
  organization: Department of Computer Science, The University of Texas at Austin, Austin, TX, United States of America
– sequence: 2
  givenname: Xuesu
  orcidid: 0000-0001-5151-2186
  surname: Xiao
  fullname: Xiao, Xuesu
  email: bliu@cs.utexas.edu
  organization: Department of Computer Science, The University of Texas at Austin, Austin, TX, United States of America
– sequence: 3
  givenname: Peter
  orcidid: 0000-0002-6795-420X
  surname: Stone
  fullname: Stone, Peter
  email: pstone@cs.utexas.edu
  organization: Department of Computer Science, The University of Texas at Austin, Austin, TX, United States of America
BookMark eNp9UE1Lw0AQXaSCtfYueAl4Tt3dyX4dQ_ELokLpfdkkm7olZusmFfz3bk0R8eBpHjPvzZt552jS-c4idEnwghCsbopVvqCYkgVgxkHACZpSECIFwfnkFz5D877fYowJowIUmyKRJ4VrbOu7TVJYEzoXQb7bBW-q12TwyZMvXWuTlS_9kDybD7cxg_PdBTptTNvb-bHO0Prudr18SIuX-8dlXqQVFXRISV1SawgD4KxRZSMVJ0rWtZI4i23TEB7nALimTcWsEEbWFOqMcUkslzBD1-PaeND73vaD3vp96KKjppkCpjKJIbLwyKqC7_tgG70L7s2ET02wPgSkY0D6EJA-BhQl_I-kcsP3Z0Mwrv1PeDUKnbX2x0dBxjIh4QtGqXIW
CODEN IRALC6
CitedBy_id crossref_primary_10_1016_j_eswa_2025_127856
crossref_primary_10_1016_j_robot_2022_104132
crossref_primary_10_1016_j_aej_2025_04_080
crossref_primary_10_1109_TBDATA_2021_3110862
crossref_primary_10_1109_TVT_2024_3506995
crossref_primary_10_1016_j_eswa_2025_128603
crossref_primary_10_1016_j_isatra_2024_12_048
crossref_primary_10_1007_s11370_022_00428_4
crossref_primary_10_15803_ijnc_14_2_123
crossref_primary_10_1109_TVT_2024_3382309
crossref_primary_10_1109_LRA_2021_3090023
crossref_primary_10_1007_s42235_021_00142_4
crossref_primary_10_1109_TCSVT_2022_3206865
crossref_primary_10_1007_s10514_022_10039_8
crossref_primary_10_1016_j_procs_2022_10_123
crossref_primary_10_1109_LRA_2025_3529325
crossref_primary_10_1109_TSMC_2025_3537990
crossref_primary_10_1007_s42452_025_06775_y
crossref_primary_10_1080_14620316_2025_2520366
crossref_primary_10_1142_S2301385025500438
crossref_primary_10_3390_s22207750
crossref_primary_10_1109_COMST_2024_3423319
crossref_primary_10_1007_s00521_023_09217_1
crossref_primary_10_1109_LRA_2025_3557309
crossref_primary_10_1145_3729420
crossref_primary_10_3390_s22186881
crossref_primary_10_3390_rs17071214
crossref_primary_10_1007_s40747_023_01216_y
crossref_primary_10_1109_LRA_2023_3280810
crossref_primary_10_3390_s24185925
crossref_primary_10_3390_act14060279
crossref_primary_10_1016_j_artint_2024_104238
crossref_primary_10_1016_j_compeleceng_2022_108376
crossref_primary_10_1109_TITS_2024_3524882
crossref_primary_10_1109_LRA_2021_3100940
crossref_primary_10_1109_ACCESS_2023_3247730
crossref_primary_10_1007_s11633_024_1512_6
crossref_primary_10_1145_3703838
Cites_doi 10.1109/100.580977
10.1109/ICRA.2017.7989182
10.1109/ROBOT.2000.844730
10.1109/ICRA.2017.7989381
10.1007/978-3-642-19457-3_35
10.1109/TSSC.1968.300136
10.1073/pnas.1611835114
10.1002/rob.20109
10.1016/S1364-6613(99)01294-2
10.1109/LRA.2018.2869644
10.1016/0921-8890(95)00004-Y
10.1007/BF01386390
10.3390/s19183837
10.1109/ROBOT.1993.291936
10.1007/978-3-642-13408-1_23
10.1109/IROS.2017.8206510
10.1109/TG.2018.2849942
10.1109/ICRA.2018.8461203
10.1109/70.508439
10.1109/LRA.2019.2899918
10.1109/LRA.2020.3002217
10.1109/IROS.2017.8202134
10.1109/ICRA.2018.8460655
10.1109/BigComp.2018.00030
10.1109/CVPR.2019.00679
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/LRA.2021.3056373
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2377-3766
EndPage 1096
ExternalDocumentID 10_1109_LRA_2021_3056373
9345478
Genre orig-research
GrantInformation_xml – fundername: ARO
  grantid: W911NF-19-2-0333
– fundername: ONR
  grantid: N00014-18-2243
– fundername: FLI
  grantid: RFP2-000
– fundername: Learning Agents Research Group
  grantid: CPS-1 739 964; IIS-1 724 157; NRI-1 925 082
– fundername: Lockheed Martin
  funderid: 10.13039/100002186
– fundername: Defense Advanced Research Projects Agency; DARPA
  funderid: 10.13039/100000185
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
ID FETCH-LOGICAL-c272t-1db2ea153365f9bf896198dd9804a15af162ea330d2fc5e77a8d23d45681e683
IEDL.DBID RIE
ISSN 2377-3766
IngestDate Sun Nov 30 03:46:51 EST 2025
Sat Nov 29 06:03:09 EST 2025
Tue Nov 18 21:35:38 EST 2025
Wed Aug 27 02:28:47 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-c272t-1db2ea153365f9bf896198dd9804a15af162ea330d2fc5e77a8d23d45681e683
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-6795-420X
0000-0001-5151-2186
0000-0002-8158-4129
PQID 2493594803
PQPubID 4437225
PageCount 7
ParticipantIDs crossref_primary_10_1109_LRA_2021_3056373
proquest_journals_2493594803
crossref_citationtrail_10_1109_LRA_2021_3056373
ieee_primary_9345478
PublicationCentury 2000
PublicationDate 2021-04-01
PublicationDateYYYYMMDD 2021-04-01
PublicationDate_xml – month: 04
  year: 2021
  text: 2021-04-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE robotics and automation letters
PublicationTitleAbbrev LRA
PublicationYear 2021
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
ref34
ref12
ref15
ref14
rusu (ref29) 2016
taylor (ref32) 2009; 10
zheng (ref9) 2017
ref33
ref11
yoon (ref30) 2017
ref10
gao (ref16) 2017
ref2
ref1
ref17
ref19
zenke (ref27) 0; 70
lopez-paz (ref31) 0
ref24
ring (ref25) 1994; 78712
ref23
ref26
shin (ref28) 0
ref20
ref22
ref21
ref8
ref7
wang (ref18) 2019
ref4
ref3
ref6
ref5
References_xml – ident: ref6
  doi: 10.1109/100.580977
– ident: ref19
  doi: 10.1109/ICRA.2017.7989182
– ident: ref8
  doi: 10.1109/ROBOT.2000.844730
– ident: ref17
  doi: 10.1109/ICRA.2017.7989381
– ident: ref22
  doi: 10.1007/978-3-642-19457-3_35
– ident: ref34
  doi: 10.1109/TSSC.1968.300136
– ident: ref26
  doi: 10.1073/pnas.1611835114
– ident: ref35
  doi: 10.1002/rob.20109
– ident: ref4
  doi: 10.1016/S1364-6613(99)01294-2
– year: 2017
  ident: ref30
  article-title: Lifelong learning with dynamically expandable networks
– ident: ref10
  doi: 10.1109/LRA.2018.2869644
– year: 2019
  ident: ref18
  article-title: Dual sequential monte carlo: Tunneling filtering and planning in continuous pomdps
– year: 2016
  ident: ref29
  article-title: Progressive neural networks
– ident: ref24
  doi: 10.1016/0921-8890(95)00004-Y
– ident: ref33
  doi: 10.1007/BF01386390
– ident: ref12
  doi: 10.3390/s19183837
– start-page: 2990
  year: 0
  ident: ref28
  article-title: Continual learning with deep generative replay
  publication-title: Proc Adv Neural Inf Process Syst
– volume: 78712
  year: 1994
  ident: ref25
  article-title: Continual learning in reinforcement environments
– ident: ref5
  doi: 10.1109/ROBOT.1993.291936
– year: 2017
  ident: ref9
  article-title: Ros navigation tuning guide
– ident: ref20
  doi: 10.1007/978-3-642-13408-1_23
– ident: ref1
  doi: 10.1109/IROS.2017.8206510
– ident: ref13
  doi: 10.1109/TG.2018.2849942
– ident: ref14
  doi: 10.1109/ICRA.2018.8461203
– ident: ref7
  doi: 10.1109/70.508439
– ident: ref15
  doi: 10.1109/LRA.2019.2899918
– ident: ref2
  doi: 10.1109/LRA.2020.3002217
– start-page: 6467
  year: 0
  ident: ref31
  article-title: Gradient episodic memory for continual learning
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref11
  doi: 10.1109/IROS.2017.8202134
– year: 2017
  ident: ref16
  article-title: Intention-net: Integrating planning and deep learning for goal-directed autonomous navigation
– ident: ref3
  doi: 10.1109/ICRA.2018.8460655
– volume: 10
  start-page: 1633
  year: 2009
  ident: ref32
  article-title: Transfer learning for reinforcement learning domains: A survey
  publication-title: J Mach Learn Res
– volume: 70
  year: 0
  ident: ref27
  article-title: Continual learning through synaptic intelligence
  publication-title: Mach Learn Res
– ident: ref21
  doi: 10.1109/BigComp.2018.00030
– ident: ref23
  doi: 10.1109/CVPR.2019.00679
SSID ssj0001527395
Score 2.5134065
Snippet This letter presents a self-improving lifelong learning framework for a mobile robot navigating in different environments. Classical static navigation methods...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1090
SubjectTerms autonomous vehicle navigation
Computation
imitation learning
Lifelong learning
machine learning for robot control
Mobile robots
Motion and path planning
Navigation
Optimization
Robot sensing systems
Robots
sensorimotor learning
Task analysis
Training
Tuning
Title A Lifelong Learning Approach to Mobile Robot Navigation
URI https://ieeexplore.ieee.org/document/9345478
https://www.proquest.com/docview/2493594803
Volume 6
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  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/eLvHCXMwlV3PT8IwFH4B4kEP_kIjiqQHLyYOtnVb1yMxEA9ADOHAbVl_ERKyGRgc_dttt4IajYm3ZWuX5WvX976-1-8BPEgXc9ek4hAmYicQXuqwMFJOGgQho5iqsBJxHZHJJJ7P6WsNng5nYaSUZfKZ7JrLMpYvcr41W2U9ikv5qTrUCSHVWa3P_RSjJEbDfSTSpb3RtK_5n-91jZeMCf5mecpSKj_W39KoDM_-9znncGqdR9SvRvsCajK7hJMvkoJNIH00Wiq5yrMFstqpC9S3wuGoyNE4Z3ohQNOc5QWapLtSYiPPrmA2HMyeXxxbHMHhPvELxxPMl6nx1qJQUaZiqqlQLASN3UDfTpUX6ecYu8JXPJSEpLHwsQiM4JiMYnwNjSzP5A0gTkxojxvXzQsUIYwLbdpkpDTTiERIW9Db45ZwKxxu6leskpJAuDTRSCcG6cQi3YLHQ4-3SjTjj7ZNg-yhnQW1Be390CT2r9okmipiIy_j4tvfe93BsXl3lVnThkax3sp7OOK7YrlZd6A-fh90ymnzAcywva8
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH7MKagHf01xOjUHL4Ld2qZtmmMRx8SuyNhht9LmxxiMVrZuf79J201FEbyVNqHlS5r3vryX7wHcCxMzU6fikJT7hsOtxEhdTxqJ47gpxVS6lYhrSKLIn0zoWwMet2dhhBBl8pno6ssyls9zttJbZT2KS_mpHdh1Hce2qtNanzsqWkuMuptYpEl74ShQDNC2utpPxgR_sz1lMZUfK3BpVvrH__ugEziq3UcUVON9Cg2RncHhF1HBFpAAhTMp5nk2RbV66hQFtXQ4KnI0zFO1FKBRnuYFipJ1KbKRZ-cw7j-PnwZGXR7BYDaxC8PiqS0S7a95rqSp9KkiQz7n1DcddTuRlqeeY2xyWzJXEJL43Mbc0ZJjwvPxBTSzPBOXgBjRwT2mnTfLkYSkjCvjJjypuIbHXdqG3ga3mNXS4bqCxTwuKYRJY4V0rJGOa6Tb8LDt8V7JZvzRtqWR3barQW1DZzM0cf1fLWNFFrEWmDHx1e-97mB_MB6GcfgSvV7DgX5PlWfTgWaxWIkb2GPrYrZc3JaT5wNZ87_F
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=A+Lifelong+Learning+Approach+to+Mobile+Robot+Navigation&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Liu%2C+Bo&rft.au=Xiao%2C+Xuesu&rft.au=Stone%2C+Peter&rft.date=2021-04-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=6&rft.issue=2&rft.spage=1090&rft.epage=1096&rft_id=info:doi/10.1109%2FLRA.2021.3056373&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2021_3056373
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