Academic Journal
Προβολή σε EDS

Formation planning for multiple USVs with PFCL-MADDPG deep reinforcement learning: theory and experiment.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Formation planning for multiple USVs with PFCL-MADDPG deep reinforcement learning: theory and experiment.
Συγγραφείς: Zhou, Jiahao1 (AUTHOR), Wang, Hao1,2 (AUTHOR) wanghao@mail.neu.edu.cn, Fu, Jun1 (AUTHOR), Xu, Hongli1 (AUTHOR)
Πηγή: International Journal of Systems Science. Oct2026, Vol. 57 Issue 14, p4641-4655. 15p.
Θεματικοί όροι: *Risk assessment, Robotic path planning, Reinforcement learning, Scientific experimentation, Autonomous robots, Machine learning, Maritime management
Περίληψη: In this paper, we propose a novel algorithm called Potential Field and Curriculum Learning-based Multi-Agent Deep Deterministic Policy Gradient (PFCL-MADDPG), which is based on curriculum learning and collision risk assessment model. This algorithm excels in handling complex path planning and sparse reward scenarios. By incorporating curriculum learning, we mitigate the challenges posed by sparse rewards, thereby enhancing learning efficiency. Additionally, we introduce Artificial Potential Field (APF) to establish a collision risk assessment model that computes reward values, significantly improving the safety of USVs. We conducted experiments with multiple USVs in both simulated and real-world environments. The results demonstrate that our algorithm exhibits remarkable robustness and effectiveness when executing tasks in complex maritime environments. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Systems Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Business Source Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:bsx&genre=article&issn=00207721&ISBN=&volume=57&issue=14&date=20261015&spage=4641&pages=4641-4655&title=International Journal of Systems Science&atitle=Formation%20planning%20for%20multiple%20USVs%20with%20PFCL-MADDPG%20deep%20reinforcement%20learning%3A%20theory%20and%20experiment.&aulast=Zhou%2C%20Jiahao&id=DOI:10.1080/00207721.2025.2602079
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: bsx
DbLabel: Business Source Index
An: 197136608
RelevancyScore: 1435
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1435
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Formation planning for multiple USVs with PFCL-MADDPG deep reinforcement learning: theory and experiment.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhou%2C+Jiahao%22">Zhou, Jiahao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Hao%22">Wang, Hao</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> wanghao@mail.neu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Fu%2C+Jun%22">Fu, Jun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Hongli%22">Xu, Hongli</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Systems+Science%22">International Journal of Systems Science</searchLink>. Oct2026, Vol. 57 Issue 14, p4641-4655. 15p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Risk+assessment%22">Risk assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Robotic+path+planning%22">Robotic path planning</searchLink><br /><searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Scientific+experimentation%22">Scientific experimentation</searchLink><br /><searchLink fieldCode="DE" term="%22Autonomous+robots%22">Autonomous robots</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Maritime+management%22">Maritime management</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In this paper, we propose a novel algorithm called Potential Field and Curriculum Learning-based Multi-Agent Deep Deterministic Policy Gradient (PFCL-MADDPG), which is based on curriculum learning and collision risk assessment model. This algorithm excels in handling complex path planning and sparse reward scenarios. By incorporating curriculum learning, we mitigate the challenges posed by sparse rewards, thereby enhancing learning efficiency. Additionally, we introduce Artificial Potential Field (APF) to establish a collision risk assessment model that computes reward values, significantly improving the safety of USVs. We conducted experiments with multiple USVs in both simulated and real-world environments. The results demonstrate that our algorithm exhibits remarkable robustness and effectiveness when executing tasks in complex maritime environments. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Systems Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=bsx&AN=197136608
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/00207721.2025.2602079
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 4641
    Subjects:
      – SubjectFull: Risk assessment
        Type: general
      – SubjectFull: Robotic path planning
        Type: general
      – SubjectFull: Reinforcement learning
        Type: general
      – SubjectFull: Scientific experimentation
        Type: general
      – SubjectFull: Autonomous robots
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Maritime management
        Type: general
    Titles:
      – TitleFull: Formation planning for multiple USVs with PFCL-MADDPG deep reinforcement learning: theory and experiment.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhou, Jiahao
      – PersonEntity:
          Name:
            NameFull: Wang, Hao
      – PersonEntity:
          Name:
            NameFull: Fu, Jun
      – PersonEntity:
          Name:
            NameFull: Xu, Hongli
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 10
              Text: Oct2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 00207721
          Numbering:
            – Type: volume
              Value: 57
            – Type: issue
              Value: 14
          Titles:
            – TitleFull: International Journal of Systems Science
              Type: main
ResultId 1