• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Motor Learning for Flexible Musculoskeletal Robot Arms using Physical Constraints

Research Project

Project/Area Number 18H01410
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 20020:Robotics and intelligent system-related
Research InstitutionKyushu Institute of Technology (2019-2020)
Osaka University (2018)

Principal Investigator

Ikemoto Shuhei  九州工業大学, 大学院生命体工学研究科, 准教授 (00588353)

Co-Investigator(Kenkyū-buntansha) 細田 耕  大阪大学, 基礎工学研究科, 教授 (10252610)
Project Period (FY) 2018-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥17,550,000 (Direct Cost: ¥13,500,000、Indirect Cost: ¥4,050,000)
Fiscal Year 2020: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2019: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2018: ¥8,970,000 (Direct Cost: ¥6,900,000、Indirect Cost: ¥2,070,000)
Keywords筋骨格ロボット / 空気圧人工筋 / 筋骨格ロボットアーム / 生物規範 / 筋骨格 / 生物規範ロボット / 物理的拘束 / 運動学習
Outline of Final Research Achievements

In this study, we employ flexible musculoskeletal robot arms driven by pneumatic artificial muscles, and aim to show that trial and error under physical constraints in the early stage of learning makes it easier to achieve similar motions in the final stage without constraints. As a specific example, we focused on the motion of a flexible robot arm grasping a crank and rotating it, and addressed the problem of finding a control input that can make the crank rotate. As a result, it was found that due to the flexibility of the musculoskeletal robot arm, the physical constraint of the crank given to the hand was naturally reflected in the motion, and the search problem could be solved even in a very simple way.

Academic Significance and Societal Importance of the Research Achievements

本研究は,外から押されることで姿勢が変化する柔軟なロボットアームを用いる場合,学習初期において運動が制限されるような物理的拘束下で試行錯誤を行った方が,最終的に拘束が無い状態で同様の運動を実現することが容易になるという実例を示すことを目標とした.実際に空気圧で駆動される柔軟なロボットアームを開発し,クランクを回すというタスクを設定して検証したところ,クランクを回転させることができる制御入力を探索する問題において,ロボットアームの柔軟性により,手先に与えられたクランクの物理的な拘束が自ずと運動に表れることが確認され,非常に簡単な方法であっても問題を解くことができることが分かった.

Report

(4 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Annual Research Report
  • 2018 Annual Research Report
  • Research Products

    (13 results)

All 2021 2020 2019 2018 Other

All Int'l Joint Research (2 results) Journal Article (4 results) (of which Peer Reviewed: 2 results) Presentation (7 results) (of which Int'l Joint Research: 6 results)

  • [Int'l Joint Research] Arizona State University(米国)

    • Related Report
      2019 Annual Research Report
  • [Int'l Joint Research] Technical University of Darmstadt(ドイツ)

    • Related Report
      2019 Annual Research Report
  • [Journal Article] Neural Model Extraction for Model-Based Control of a Neural Network Forward Model2021

    • Author(s)
      Ikemoto Shuhei、Takahara Kazuma、Kumi Taiki、Hosoda Koh
    • Journal Title

      SN Computer Science

      Volume: 2 Issue: 1

    • DOI

      10.1007/s42979-021-00456-4

    • NAID

      120007186037

    • Related Report
      2020 Annual Research Report
  • [Journal Article] Noise-modulated neural networks for selectively functionalizing sub-networks by exploiting stochastic resonance2021

    • Author(s)
      Ikemoto Shuhei
    • Journal Title

      Neurocomputing

      Volume: - Pages: 1-9

    • DOI

      10.1016/j.neucom.2020.05.125

    • Related Report
      2020 Annual Research Report
  • [Journal Article] Goal-Conditioned Variational Autoencoder Trajectory Primitives with Continuous and Discrete Latent Codes2020

    • Author(s)
      Takayuki Osa, Shuhei Ikemoto
    • Journal Title

      SN Computer Science

      Volume: 1 Issue: 5

    • DOI

      10.1007/s42979-020-00324-7

    • NAID

      120007147069

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Anthropomorphic Musculoskeletal 10 degrees-of-freedom Robot Arm driven by Pneumatic Artificial Muscles2018

    • Author(s)
      Arne hitzmann, Hiroaki Masuda, Shuhei Ikemoto, and Koh Hosoda
    • Journal Title

      Advanced Robotics

      Volume: 32 Issue: 15 Pages: 865-878

    • DOI

      10.1080/01691864.2018.1494040

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed
  • [Presentation] Learning Interactive Behaviors for Musculoskeletal Robots Using Bayesian Interaction Primitives2019

    • Author(s)
      Joseph Campbell, Arne Hitzmann, Simon Stepputtis, Shuhei Ikemoto, Koh Hosoda, Heni Ben Amor
    • Organizer
      IEEE/RSJ International Conference on Intelligent Robots and Systems
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Local Online Motor Babbling: Learning Motor Abundance of a Musculoskeletal Robot Arm2019

    • Author(s)
      Zinan Liu, Arne Hitzmann, Shuhei Ikemoto, Svenja Stark, Jan Peters, Koh Hosoda
    • Organizer
      IEEE/RSJ International Conference on Intelligent Robots and Systems
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Common Dimensional Autoencoder for Learning Redundant Muscle-Posture Mappings of Complex Musculoskeletal Robots2019

    • Author(s)
      Hiroaki Masuda, Arne Hitzmann, Koh Hosoda, Shuhei Ikemoto
    • Organizer
      IEEE/RSJ International Conference on Intelligent Robots and Systems
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 状態方程式を近似するNNからの数式モデル抽出に基づくモデル予測制御2019

    • Author(s)
      池本周平,組泰樹,細田耕
    • Organizer
      日本ロボット学会学術講演会
    • Related Report
      2019 Annual Research Report
  • [Presentation] Optimal Feedback Control based on Analytical Linear Models extracted from Neural Networks trained for Nonlinear Systems2018

    • Author(s)
      Duan Yu, Shuhei Ikemoto, Koh Hosoda
    • Organizer
      IEEE/RSJ International Conference on Intelligent Robots and Systems
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Common Dimensional Autoencoder for Identifying Agonist-Antagonist Muscle Pairs in Musculoskeletal Robots2018

    • Author(s)
      Hiroaki Masuda, Shuhei Ikemoto, Koh Hosoda
    • Organizer
      Intelligent Autonomous Systems 15
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Reconstructing State-space from Movie using Convolutional Autoencoder for Robot Control2018

    • Author(s)
      Kazuma Takahara, Shuhei Ikemoto, Koh Hosoda
    • Organizer
      Intelligent Autonomous Systems 15
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2018-04-23   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi