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

A neural dynamics model for learning and generating hierarchical goal-directed behavior

Research Project

Project/Area Number 16H05878
Research Category

Grant-in-Aid for Young Scientists (A)

Allocation TypeSingle-year Grants
Research Field Intelligent robotics
Research InstitutionWaseda University

Principal Investigator

Arie Hiroaki  早稲田大学, 次世代ロボット研究機構, その他(招聘研究員) (20424814)

Project Period (FY) 2016-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥24,180,000 (Direct Cost: ¥18,600,000、Indirect Cost: ¥5,580,000)
Fiscal Year 2019: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2018: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2017: ¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
Fiscal Year 2016: ¥11,310,000 (Direct Cost: ¥8,700,000、Indirect Cost: ¥2,610,000)
Keywords認知発達ロボティクス / 目標志向行動 / 再帰型神経回路モデル / 深層学習 / ニューラルネットワーク / ディープラーニング / ロボット
Outline of Final Research Achievements

This project aims to enable robots to learn and generate goal-directed behavior. First, I worked on the development of a neural circuit model that can express the abstract information of the action goal in a self-organizing manner by learning the continuous sensorimotor information that the robot itself experiences. Furthermore, I also attempted to develop a mechanism in which the robot adaptively modifies the action plan according to the situation.
A neural circuit model constructed by integrating them was implemented in a robot. Then, I confirmed the effectiveness of the proposed method in the task of assembling with a human.

Academic Significance and Societal Importance of the Research Achievements

行動の目標という概念は自ら行動する際に必要となるだけでなく,他者の行動に意図を見いだしたり,模倣学習をしたりする際にも重要な役割を果たしていると指摘されており,社会的認知能力の礎ともなっている.しかしながら,心理学や脳科学の重要な研究課題となっているにもかかわらず,行動の目標という抽象的な概念がどのように表象されているかは未だ明らかではない.本研究の結果として得られた目標志向行動に関する神経回路モデル上での情報表現に関する知見は工学的応用のみならず,認知科学等の学術的な研究への展開も期待できる.

Report

(5 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Annual Research Report
  • 2017 Annual Research Report
  • 2016 Annual Research Report
  • Research Products

    (14 results)

All 2019 2018 2017 2016

All Journal Article (4 results) (of which Peer Reviewed: 4 results,  Open Access: 2 results) Presentation (10 results) (of which Int'l Joint Research: 4 results)

  • [Journal Article] Achieving Human-Robot Collaboration with Dynamic Goal Inference by Gradient Descent2019

    • Author(s)
      Shingo Murata, Wataru Masuda, Jiayi Chen, Hiroaki Arie, Tetsuya Ogata, Shigeki Sugano
    • Journal Title

      Neural Information Processing (Lecture Notes in Computer Science)

      Volume: Vol. 11954 Pages: 579-590

    • DOI

      10.1007/978-3-030-36711-4_49

    • ISBN
      9783030367107, 9783030367114
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Acquisition of Viewpoint Transformation and Action Mappings via Sequence to Sequence Imitative Learning by Deep Neural Networks2018

    • Author(s)
      Ryoichi Nakajo, Shingo Murata, Hiroaki Arie, Tetsuya Ogata
    • Journal Title

      Frontiers in Neurorobotics

      Volume: Vol. 12, Article 46 Pages: 1-14

    • DOI

      10.3389/fnbot.2018.00046

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Learning to Achieve Different Levels of Adaptability for Human - Robot Collaboration Utilizing a Neuro-dynamical System2018

    • Author(s)
      Shingo Murata, Yuxi Li, Hiroaki Arie, Tetsuya Ogata, and Shigeki Sugano
    • Journal Title

      IEEE Transactions on Cognitive and Developmental Systems

      Volume: 10 Issue: 3 Pages: 1-1

    • DOI

      10.1109/tcds.2018.2797260

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Representation Learning of Logic Words by an RNN: From Word Sequences to Robot Actions2017

    • Author(s)
      Tatsuro Yamada, Shingo Murata, Hiroaki Arie, Tetsuya Ogata
    • Journal Title

      Frontiers in Neurorobotics

      Volume: Vol. 11, Article 70 Pages: 1-18

    • DOI

      10.3389/fnbot.2017.00070

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] 深層学習を用いた協調ロボットのための未学習目標画像への汎化2019

    • Author(s)
      [1]左近実智隆,村田真悟,増田航,陳嘉壹,有江浩明,尾形哲也,菅野重樹
    • Organizer
      日本機械学会ロボティクス・メカトロニクス講演会2019
    • Related Report
      2019 Annual Research Report
  • [Presentation] LSTM-RNNを用いた階層的な目標計画による人間ーロボット協調組立の実現2018

    • Author(s)
      陳嘉壹,村田真悟,増田航,有江浩明,尾形哲也,菅野重樹
    • Organizer
      日本機械学会ロボティクス・メカトロニクス講演会2018
    • Related Report
      2018 Annual Research Report
  • [Presentation] Four-part Harmonization: Comparison of a Bayesian Network and a Recurrent Neural Network2017

    • Author(s)
      Tatsuro Yamada, Tetsuro Kitahara, Hiroaki Arie, and Tetsuya Ogata
    • Organizer
      The 13th International Symposium on Computer Music Multidisciplinary Research (CMMR2017)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Learning of Labeling Room Space for Mobile Robots Based on Visual Motor Experience2017

    • Author(s)
      Tatsuro Yamada, Saki Ito, Hiroaki Arie, and Tetsuya Ogata
    • Organizer
      The 26th International Conference on Artificial Neural Networks 2017 (ICANN2017)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Representation Learning of Logical Words via Seq2seq Learning from Linguistic Instructions to Robot Actions2017

    • Author(s)
      Tatsuro Yamada, Shingo Murata, Hiroaki Arie, and Tetsuya Ogata
    • Organizer
      The 5th International Conference on Human-Agent Interaction (HAI 2017)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 神経回路モデルにおける追加学習手法に関する検討2017

    • Author(s)
      張耀宇,中條亨一,山田竜郎,村田真悟,有江浩明,尾形哲也
    • Organizer
      第18回計測自動制御学会システムインテグレーション部門講演会
    • Related Report
      2017 Annual Research Report
  • [Presentation] 深層学習を用いた移動ロボットによる室内空間の状況依存的ラベリング2017

    • Author(s)
      伊藤彩貴,山田竜郎,有江浩明,尾形哲也
    • Organizer
      第35回日本ロボット学会 学術講演会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Seq2seq学習による論理語を含む言語指示の理解とロボット行動の生成2017

    • Author(s)
      山田竜郎,村田真悟,有江浩明,尾形哲也
    • Organizer
      第31回人工知能学会全国大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] LSTMを用いた四声体和声の生成2017

    • Author(s)
      山田竜郎,北原鉄朗,有江浩明,尾形哲也
    • Organizer
      第31回人工知能学会全国大会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Achieving Different Levels of Adaptability for Human-Robot Collaboration Utilizing a Neuro-Dynamical System2016

    • Author(s)
      Yuxi Li, Shingo Murata, Hiroaki Arie, Tetsuya Ogata, and Shigeki Sugano
    • Organizer
      Workshop on Bio-inspired Social Robot Learning in Home Scenarios, The 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016)
    • Place of Presentation
      Daejeon, Korea
    • Year and Date
      2016-10-09
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2016-04-21   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi