View in EDS

End-to-end deep reinforcement learning and control with multimodal perception for planetary robotic dual peg-in-hole assembly.

Saved in:
Bibliographic Details
Title: End-to-end deep reinforcement learning and control with multimodal perception for planetary robotic dual peg-in-hole assembly.
Authors: Li, Boxin1 (AUTHOR) libx18@mails.tsinghua.edu.cn, Wang, Zhaokui1 (AUTHOR) wangzk@tsinghua.edu.cn
Source: Advances in Space Research. Dec2024, Vol. 74 Issue 11, p5860-5873. 14p.
Subjects: Deep reinforcement learning, Robotic assembly, Planetary surfaces, Extraterrestrial resources, Space exploration, Reinforcement learning
Abstract: The planetary construction is necessary for long-term scientific deep space exploration and resource utilization in the future. The planetary robotic assembly control is a key technology that must be broken through in future planetary surface construction. The paper focuses on the most representative dual peg-in–hole assembly, which has sufficiently complex contact interaction, wide range of applications and good method portability. To address the challenges brought by the unstructured planetary environment and the features of the construction tasks, the paper proposes an end-to-end deep reinforcement learning and control method with multimodal perception for planetary robotic assembly tasks. A staged reward function based on the visual virtual target point for policy learning is designed. The effectiveness and feasibility of the proposed control method have been verified through simulation experiments and ground real robot experiments. It provides a feasible control method of robotic operations for future planetary surface construction. [ABSTRACT FROM AUTHOR]
Copyright of Advances in Space Research is the property of Pergamon Press - An Imprint of Elsevier Science 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.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 180886501
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: End-to-end deep reinforcement learning and control with multimodal perception for planetary robotic dual peg-in-hole assembly.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Li%2C+Boxin%22">Li, Boxin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> libx18@mails.tsinghua.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Zhaokui%22">Wang, Zhaokui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wangzk@tsinghua.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Advances+in+Space+Research%22">Advances in Space Research</searchLink>. Dec2024, Vol. 74 Issue 11, p5860-5873. 14p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+reinforcement+learning%22">Deep reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Robotic+assembly%22">Robotic assembly</searchLink><br /><searchLink fieldCode="DE" term="%22Planetary+surfaces%22">Planetary surfaces</searchLink><br /><searchLink fieldCode="DE" term="%22Extraterrestrial+resources%22">Extraterrestrial resources</searchLink><br /><searchLink fieldCode="DE" term="%22Space+exploration%22">Space exploration</searchLink><br /><searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The planetary construction is necessary for long-term scientific deep space exploration and resource utilization in the future. The planetary robotic assembly control is a key technology that must be broken through in future planetary surface construction. The paper focuses on the most representative dual peg-in–hole assembly, which has sufficiently complex contact interaction, wide range of applications and good method portability. To address the challenges brought by the unstructured planetary environment and the features of the construction tasks, the paper proposes an end-to-end deep reinforcement learning and control method with multimodal perception for planetary robotic assembly tasks. A staged reward function based on the visual virtual target point for policy learning is designed. The effectiveness and feasibility of the proposed control method have been verified through simulation experiments and ground real robot experiments. It provides a feasible control method of robotic operations for future planetary surface construction. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Advances in Space Research is the property of Pergamon Press - An Imprint of Elsevier Science 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=egs&AN=180886501
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.asr.2024.08.028
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 5860
    Subjects:
      – SubjectFull: Deep reinforcement learning
        Type: general
      – SubjectFull: Robotic assembly
        Type: general
      – SubjectFull: Planetary surfaces
        Type: general
      – SubjectFull: Extraterrestrial resources
        Type: general
      – SubjectFull: Space exploration
        Type: general
      – SubjectFull: Reinforcement learning
        Type: general
    Titles:
      – TitleFull: End-to-end deep reinforcement learning and control with multimodal perception for planetary robotic dual peg-in-hole assembly.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Li, Boxin
      – PersonEntity:
          Name:
            NameFull: Wang, Zhaokui
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 02731177
          Numbering:
            – Type: volume
              Value: 74
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Advances in Space Research
              Type: main
ResultId 1