Zobrazit v EDS

Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data

Uloženo v:
Podrobná bibliografie
Název: Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data
Autoři: Boyi Liu, Lujia Wang, Ming Liu, Cheng-Zhong Xu
Zdroj: IEEE Robotics and Automation Letters. 5:3509-3516
Publication Status: Preprint
Informace o vydavateli: Institute of Electrical and Electronics Engineers (IEEE), 2020.
Rok vydání: 2020
Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, 0209 industrial biotechnology, Big data in robotics and automation, Computer Science - Artificial Intelligence, Computational modeling, 02 engineering and technology, Microstrip, Machine Learning (cs.LG), Computer Science - Robotics, Artificial Intelligence (cs.AI), Deep learning in robotics and automation, Motion and path planning, Robot sensing systems, Task analysis, Fuses, Cloud computing, Robotics (cs.RO)
Popis: Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue, we present a novel framework named FIL. It provides a heterogeneous knowledge fusion mechanism for cloud robotic systems. Then, a knowledge fusion algorithm in FIL is proposed. It enables the cloud to fuse heterogeneous knowledge from local robots and generate guide models for robots with service requests. After that, we introduce a knowledge transfer scheme to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and efficiency. Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a self-driving task for robots (cars). The experimental results demonstrate that the shared model generated by FIL increases imitation learning efficiency of local robots in cloud robotic systems.
arXiv admin note: substantial text overlap with arXiv:1909.00895
Druh dokumentu: Article
ISSN: 2377-3774
DOI: 10.1109/lra.2020.2976321
DOI: 10.48550/arxiv.1912.12204
Přístupová URL adresa: http://arxiv.org/pdf/1912.12204
http://arxiv.org/abs/1912.12204
http://ieeexplore.ieee.org/document/9013081/
https://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-12204
https://ieeexplore.ieee.org/document/9013081/
https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002274053393025
http://dblp.uni-trier.de/db/journals/ral/ral5.html#LiuWLX20
Rights: IEEE Copyright
arXiv Non-Exclusive Distribution
Přístupové číslo: edsair.doi.dedup.....8ef9e33390e0b51cc8cac7cf4e5f9f36
Databáze: OpenAIRE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://explore.openaire.eu/search/publication?articleId=doi_dedup___%3A%3A8ef9e33390e0b51cc8cac7cf4e5f9f36
    Name: EDS - OpenAIRE (s4221598)
    Category: fullText
    Text: View record at OpenAIRE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Liu%20B
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsair
DbLabel: OpenAIRE
An: edsair.doi.dedup.....8ef9e33390e0b51cc8cac7cf4e5f9f36
RelevancyScore: 887
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 887.180725097656
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Boyi+Liu%22">Boyi Liu</searchLink><br /><searchLink fieldCode="AR" term="%22Lujia+Wang%22">Lujia Wang</searchLink><br /><searchLink fieldCode="AR" term="%22Ming+Liu%22">Ming Liu</searchLink><br /><searchLink fieldCode="AR" term="%22Cheng-Zhong+Xu%22">Cheng-Zhong Xu</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>IEEE Robotics and Automation Letters</i>. 5:3509-3516
– Name: Publisher
  Label: Publication Status
  Group: PubInfo
  Data: Preprint
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Institute of Electrical and Electronics Engineers (IEEE), 2020.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2020
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22FOS%3A+Computer+and+information+sciences%22">FOS: Computer and information sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink><br /><searchLink fieldCode="DE" term="%220209+industrial+biotechnology%22">0209 industrial biotechnology</searchLink><br /><searchLink fieldCode="DE" term="%22Big+data+in+robotics+and+automation%22">Big data in robotics and automation</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+modeling%22">Computational modeling</searchLink><br /><searchLink fieldCode="DE" term="%2202+engineering+and+technology%22">02 engineering and technology</searchLink><br /><searchLink fieldCode="DE" term="%22Microstrip%22">Microstrip</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+Learning+%28cs%2ELG%29%22">Machine Learning (cs.LG)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Robotics%22">Computer Science - Robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence+%28cs%2EAI%29%22">Artificial Intelligence (cs.AI)</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning+in+robotics+and+automation%22">Deep learning in robotics and automation</searchLink><br /><searchLink fieldCode="DE" term="%22Motion+and+path+planning%22">Motion and path planning</searchLink><br /><searchLink fieldCode="DE" term="%22Robot+sensing+systems%22">Robot sensing systems</searchLink><br /><searchLink fieldCode="DE" term="%22Task+analysis%22">Task analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Fuses%22">Fuses</searchLink><br /><searchLink fieldCode="DE" term="%22Cloud+computing%22">Cloud computing</searchLink><br /><searchLink fieldCode="DE" term="%22Robotics+%28cs%2ERO%29%22">Robotics (cs.RO)</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Humans are capable of learning a new behavior by observing others to perform the skill. Similarly, robots can also implement this by imitation learning. Furthermore, if with external guidance, humans can master the new behavior more efficiently. So, how can robots achieve this? To address the issue, we present a novel framework named FIL. It provides a heterogeneous knowledge fusion mechanism for cloud robotic systems. Then, a knowledge fusion algorithm in FIL is proposed. It enables the cloud to fuse heterogeneous knowledge from local robots and generate guide models for robots with service requests. After that, we introduce a knowledge transfer scheme to facilitate local robots acquiring knowledge from the cloud. With FIL, a robot is capable of utilizing knowledge from other robots to increase its imitation learning in accuracy and efficiency. Compared with transfer learning and meta-learning, FIL is more suitable to be deployed in cloud robotic systems. Finally, we conduct experiments of a self-driving task for robots (cars). The experimental results demonstrate that the shared model generated by FIL increases imitation learning efficiency of local robots in cloud robotic systems.<br />arXiv admin note: substantial text overlap with arXiv:1909.00895
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Article
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2377-3774
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1109/lra.2020.2976321
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.48550/arxiv.1912.12204
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="http://arxiv.org/pdf/1912.12204" linkWindow="_blank">http://arxiv.org/pdf/1912.12204</link><br /><link linkTarget="URL" linkTerm="http://arxiv.org/abs/1912.12204" linkWindow="_blank">http://arxiv.org/abs/1912.12204</link><br /><link linkTarget="URL" linkTerm="http://ieeexplore.ieee.org/document/9013081/" linkWindow="_blank">http://ieeexplore.ieee.org/document/9013081/</link><br /><link linkTarget="URL" linkTerm="https://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-12204" linkWindow="_blank">https://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-12204</link><br /><link linkTarget="URL" linkTerm="https://ieeexplore.ieee.org/document/9013081/" linkWindow="_blank">https://ieeexplore.ieee.org/document/9013081/</link><br /><link linkTarget="URL" linkTerm="https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002274053393025" linkWindow="_blank">https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002274053393025</link><br /><link linkTarget="URL" linkTerm="http://dblp.uni-trier.de/db/journals/ral/ral5.html#LiuWLX20" linkWindow="_blank">http://dblp.uni-trier.de/db/journals/ral/ral5.html#LiuWLX20</link>
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: IEEE Copyright<br />arXiv Non-Exclusive Distribution
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsair.doi.dedup.....8ef9e33390e0b51cc8cac7cf4e5f9f36
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsair&AN=edsair.doi.dedup.....8ef9e33390e0b51cc8cac7cf4e5f9f36
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/lra.2020.2976321
    Languages:
      – Text: Undetermined
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 3509
    Subjects:
      – SubjectFull: FOS: Computer and information sciences
        Type: general
      – SubjectFull: Computer Science - Machine Learning
        Type: general
      – SubjectFull: 0209 industrial biotechnology
        Type: general
      – SubjectFull: Big data in robotics and automation
        Type: general
      – SubjectFull: Computer Science - Artificial Intelligence
        Type: general
      – SubjectFull: Computational modeling
        Type: general
      – SubjectFull: 02 engineering and technology
        Type: general
      – SubjectFull: Microstrip
        Type: general
      – SubjectFull: Machine Learning (cs.LG)
        Type: general
      – SubjectFull: Computer Science - Robotics
        Type: general
      – SubjectFull: Artificial Intelligence (cs.AI)
        Type: general
      – SubjectFull: Deep learning in robotics and automation
        Type: general
      – SubjectFull: Motion and path planning
        Type: general
      – SubjectFull: Robot sensing systems
        Type: general
      – SubjectFull: Task analysis
        Type: general
      – SubjectFull: Fuses
        Type: general
      – SubjectFull: Cloud computing
        Type: general
      – SubjectFull: Robotics (cs.RO)
        Type: general
    Titles:
      – TitleFull: Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Boyi Liu
      – PersonEntity:
          Name:
            NameFull: Lujia Wang
      – PersonEntity:
          Name:
            NameFull: Ming Liu
      – PersonEntity:
          Name:
            NameFull: Cheng-Zhong Xu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 23773774
            – Type: issn-locals
              Value: edsair
            – Type: issn-locals
              Value: edsairFT
          Numbering:
            – Type: volume
              Value: 5
          Titles:
            – TitleFull: IEEE Robotics and Automation Letters
              Type: main
ResultId 1