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

Self-organizational imitation learning process through unsegmented human-robot interaction

Research Project

Project/Area Number 20800060
Research Category

Grant-in-Aid for Young Scientists (Start-up)

Allocation TypeSingle-year Grants
Research Field Perception information processing/Intelligent robotics
Research InstitutionRitsumeikan University

Principal Investigator

TANIGUCHI Tadahiro  Ritsumeikan University, 情報理工学部, 助教 (80512251)

Project Period (FY) 2008 – 2009
Project Status Completed (Fiscal Year 2009)
Budget Amount *help
¥3,289,000 (Direct Cost: ¥2,530,000、Indirect Cost: ¥759,000)
Fiscal Year 2009: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2008: ¥1,729,000 (Direct Cost: ¥1,330,000、Indirect Cost: ¥399,000)
Keywords模倣学習 / 分節化 / 自己組織化型学習 / 時系列 / 統計的学習理論 / ベイズ / 情報論的学習理論 / 動作抽出 / 記号創発 / 機械学習 / 知能ロボット / パターン認識 / 自己組織化 / 自律適応系 / キーワード抽出
Research Abstract

In this research, we developed a machine learning method which enables a robot to obtain several unit motions from unsegmented human motion. In the method, the learning architecture reduces the dimensionality of observed time series data using singular vector decomposition, models the output data using Switching AR Model (SARM). After SARM encodes the data to code strings, a keyword extraction method extract unit words from the strings based on minimal description length criteria. The extracted words are revealed to be characteristic unit motions.

Report

(3 results)
  • 2009 Annual Research Report   Final Research Report ( PDF )
  • 2008 Annual Research Report
  • Research Products

    (34 results)

All 2010 2009 2008 Other

All Journal Article (7 results) (of which Peer Reviewed: 4 results) Presentation (20 results) Book (2 results) Remarks (1 results) Patent(Industrial Property Rights) (4 results)

  • [Journal Article] Adaptive Design of Role Differentiation by Division of Reward Function in Multi-agent Reinforcement Learning2010

    • Author(s)
      Tadahiro Taniguchi, Kazuma Tabuchi, Tetsuo Sawaragi
    • Journal Title

      SICE Journal of Control, Measurement, and System Integration (JCMSI) Vol.3(1)

      Pages: 26-34

    • NAID

      10031139983

    • Related Report
      2009 Final Research Report
  • [Journal Article] Adaptive Design of Role Differentiation by Division of Reward Function in Multi-agent Reinforcement Learning2010

    • Author(s)
      Tadahiro Taniguchi, Kazuma Tabuchi, Tetsuo Sawaragi
    • Journal Title

      SICE Journal of Control, Measurement, and System Integration(JCMSI) 3

    • NAID

      10031139983

    • Related Report
      2009 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 複数予測モデル遷移のN-gram統計に基づく非分節運動系列からの模倣学習手法2009

    • Author(s)
      谷口忠大, 岩橋直人
    • Journal Title

      知能と情報(日本知能情報ファジィ学会論文誌 Vol.21(6)

      Pages: 1143-1154

    • NAID

      10025996053

    • Related Report
      2009 Final Research Report
  • [Journal Article] 複数予測モデル遷移のN-gram統計に基づく非分節運動系列からの模倣学習手法2009

    • Author(s)
      谷口忠大、岩橋直人
    • Journal Title

      知能と情報(日本知能情報ファジィ学会論文誌) 21

    • NAID

      10025996053

    • Related Report
      2009 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 地産地消型電力ネットワークの為のNatural Actor-Criticを用いた自動取引エージェントの構築2009

    • Author(s)
      谷口忠大、高木圭太、榊原一紀、西川郁子
    • Journal Title

      知能と情報(日本知能情報ファジィ学会論文誌) 21

    • NAID

      10025995944

    • Related Report
      2009 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Constructive Approach to Role-Reversal Imitation Through Unsegmented Interactions2008

    • Author(s)
      T. Taniguchi, N. Iwahashi, K. Sugiura, T. Sawaragi
    • Journal Title

      Journal of Robotics and Mechatronics Vol.20(4)

      Pages: 567-577

    • Related Report
      2009 Final Research Report
  • [Journal Article] Constructive Approach to Role-Reversal Imitation Through Unsegmented Interactions2008

    • Author(s)
      T. Taniguchi, N. Iwahashi, K. Sugiura, T. Sawaragi
    • Journal Title

      Journal of Robotics and Mechatronics 20(4)

      Pages: 567-577

    • Related Report
      2008 Annual Research Report
    • Peer Reviewed
  • [Presentation] Bibliobattle : Informal community scheme based on book review sessions2009

    • Author(s)
      Tadahiro Taniguchi, Hiroshi Kawakami, Osamu Katai
    • Organizer
      The 8th International Workshop on Social Intelligence Design(SID2009)
    • Place of Presentation
      関西セミナーハウス(京都府)
    • Year and Date
      2009-11-09
    • Related Report
      2009 Annual Research Report
  • [Presentation] ビブリオバトル:書評で繋がりを生成するインタフェースの構築2009

    • Author(s)
      谷口忠大, 川上浩司, 片井修
    • Organizer
      ヒューマンインタフェースシンポジウム2009
    • Place of Presentation
      お茶の水女子大学(東京都)
    • Year and Date
      2009-09-03
    • Related Report
      2009 Annual Research Report
  • [Presentation] 複数予測モデル遷移のN-gram統計に基づく非分節運動系列からの模倣学習手法2009

    • Author(s)
      谷口忠大, 岩橋直人
    • Organizer
      第25回ファジィシステムシンポジウム
    • Place of Presentation
      筑波大学(つくば)
    • Year and Date
      2009-07-14
    • Related Report
      2009 Annual Research Report
  • [Presentation] 地産地消型電力ネットワークの為のNatural Actor-Criticを用いた自動取引エージェントの構築2009

    • Author(s)
      谷口忠大, 高木圭太, 榊原一紀, 西川郁子
    • Organizer
      第25回ファジィシステムシンポジウム
    • Place of Presentation
      筑波大学(つくば)
    • Year and Date
      2009-07-14
    • Related Report
      2009 Annual Research Report
  • [Presentation] ヒューマン・ロボットインタラクションを通した役割反転模倣に基づく実時間応答戦略獲得2009

    • Author(s)
      谷口忠大, 岩橋直人, 中西弘門, 西川郁子
    • Organizer
      第23回人工知能学会全国大会
    • Place of Presentation
      サンポートホール高松(香川)
    • Year and Date
      2009-06-17
    • Related Report
      2009 Annual Research Report
  • [Presentation] 自転車利用者の都市構造依存性に関するマルチエージェントシミュレーションによる検討2009

    • Author(s)
      谷口忠大, 村井稔也, 榊原一紀, 西川郁子
    • Organizer
      第53回システム制御情報学会研究発表講演会
    • Place of Presentation
      神戸市産業振興センター(神戸)
    • Year and Date
      2009-05-22
    • Related Report
      2009 Annual Research Report
  • [Presentation] 役割反転に基づく連続的相互作用からの応答戦略獲得2009

    • Author(s)
      中西弘門, 谷口忠大, 岩橋直人, 西川郁子
    • Organizer
      第53回システム制御情報学会研究発表講演会
    • Place of Presentation
      神戸市産業振興センター(神戸)
    • Year and Date
      2009-05-21
    • Related Report
      2009 Annual Research Report
  • [Presentation] 地産地消型電カネットワークヘの適応的取引エージェントの導入〜知能化エネルギー社会と不便益〜2009

    • Author(s)
      谷口忠大, 大仲浩司, 榊原一紀, 西川郁子
    • Organizer
      第36回知能システムシンポジウム
    • Place of Presentation
      京都
    • Year and Date
      2009-03-18
    • Related Report
      2008 Annual Research Report
  • [Presentation] 役割反転模倣に基づく実時間相互作用からの応答戦略獲得2009

    • Author(s)
      谷口忠大, 岩橋直人, 中西弘門, 西川郁子
    • Organizer
      第36回知能システムシンポジウム
    • Place of Presentation
      京都
    • Year and Date
      2009-03-17
    • Related Report
      2008 Annual Research Report
  • [Presentation] 動作低次元性とN-gram統計を用いた複数予測モデルに基づく模倣学習2009

    • Author(s)
      谷口忠大, 岩橋直人
    • Organizer
      第21回自律分散システムシンポジウム
    • Place of Presentation
      鳥取
    • Year and Date
      2009-01-22
    • Related Report
      2008 Annual Research Report
  • [Presentation] Imitation Learning from Unsegmented Human Motion using Switching Autoregressive Model and Singular Vector Decomposition2009

    • Author(s)
      T. Taniguchi, N. Iwahashi
    • Organizer
      International Conference on Neural Information Processing, (2008)
    • Place of Presentation
      Advances in Neuro-Information Processing, Springer
    • Related Report
      2009 Final Research Report
  • [Presentation] 複数予測モデル遷移のN-gram統計に基づく非分節運動系列からの模倣学習手法2009

    • Author(s)
      谷口忠大, 岩橋直人
    • Organizer
      第25回ファジィシステムシンポジウム
    • Place of Presentation
      筑波大学(つくば)(CD-ROM)
    • Related Report
      2009 Final Research Report
  • [Presentation] ヒューマン・ロボットインタラクションを通した役割反転模倣に基づく実時間応答戦略獲得2009

    • Author(s)
      谷口忠大, 岩橋直人, 中西弘門, 西川郁子
    • Organizer
      第23回人工知能学会全国大会
    • Place of Presentation
      サンポートホール高松(香川)(CD-ROM)
    • Related Report
      2009 Final Research Report
  • [Presentation] Effective integration of imitation learning and reinforcement learning by generating internal reward2008

    • Author(s)
      K. Hamahata, T. Taniguchi, K. Sakakibara, I. Nishikawa, K. Tabuchi, T. Sawaragi
    • Organizer
      Eighth International Conference on Intelligent System Design and Applications
    • Place of Presentation
      Kaohsiung Taiwan
    • Year and Date
      2008-11-28
    • Related Report
      2008 Annual Research Report
  • [Presentation] Imitation Learning from Unsegmented Human Motion using Switching Autoregressive Model and Singular Vector Decomposition2008

    • Author(s)
      T. Taniguchi, N. Iwahashi
    • Organizer
      International Conference on Neural Information Processing 2008
    • Place of Presentation
      ニュージーランドオークランド
    • Year and Date
      2008-11-27
    • Related Report
      2008 Annual Research Report
  • [Presentation] Role differentiation process by division of reward function in multi-agent reinforcement learning2008

    • Author(s)
      T. Taniguchi, K. Tabuchi, T. Sawaragi
    • Organizer
      SICE Annual Conference 2008
    • Place of Presentation
      調布(東京都)
    • Year and Date
      2008-08-20
    • Related Report
      2008 Annual Research Report
  • [Presentation] 強化学習における内部報酬生成としての模倣学習の検討2008

    • Author(s)
      濱畑慶太, 谷口忠大, 榊原一紀, 西川郁子, 田渕一真, 椹木哲夫
    • Organizer
      第14回創発システムシンポジウム「創発夏の学校2008」
    • Place of Presentation
      富山
    • Year and Date
      2008-08-17
    • Related Report
      2008 Annual Research Report
  • [Presentation] 連続的相互作用に埋め込まれた特徴的動作系列の発見的模倣学習手法2008

    • Author(s)
      谷口忠大, 岩橋直人
    • Organizer
      第22回人工知能学会全国大会
    • Place of Presentation
      旭川(北海道)
    • Year and Date
      2008-06-13
    • Related Report
      2008 Annual Research Report
  • [Presentation] ハイブリッドダイナミカルシステムによるモード誤認識の事前分析2008

    • Author(s)
      服部裕史, 谷口忠大, 椹木哲夫
    • Organizer
      第52回システム制御情報学会研究発表講演会
    • Place of Presentation
      京都
    • Year and Date
      2008-05-16
    • Related Report
      2008 Annual Research Report
  • [Presentation] 連続的相互作用に埋め込まれた特徴的動作系列の発見的模倣学習手法2008

    • Author(s)
      谷口忠大, 岩橋直人
    • Organizer
      第22回人工知能学会全国大会
    • Place of Presentation
      サンポートホール高松(香川)(CD-ROM)
    • Related Report
      2009 Final Research Report
  • [Book] コミュニケーションするロボットは創れるか~記号創発システムへの構成論的アプローチ~2010

    • Author(s)
      谷口忠大
    • Total Pages
      272
    • Publisher
      NTT出版
    • Related Report
      2009 Annual Research Report 2009 Final Research Report
  • [Book] "Implicit Estimation of Another's Intention Based on Modular Reinforcement Learning" in Machine Learning2009

    • Author(s)
      Tadahiro Taniguchi, Kenji Ogawa, Testuo Sawaragi
    • Publisher
      In-Teh
    • Related Report
      2008 Annual Research Report
  • [Remarks]

    • URL

      http://tanichu.com/?page=publication

    • Related Report
      2008 Annual Research Report
  • [Patent(Industrial Property Rights)] 応答戦略獲得装置、リアクション選択装置、コンピュータプログラム、及びロボット2009

    • Inventor(s)
      谷口忠大, 岩橋直人, 中西弘門
    • Industrial Property Rights Holder
      立命館大学・NICT
    • Industrial Property Number
      2009-181828
    • Filing Date
      2009-08-04
    • Related Report
      2009 Annual Research Report 2009 Final Research Report
  • [Patent(Industrial Property Rights)] 動作学習装置2009

    • Inventor(s)
      谷口忠大, 岩橋直人
    • Industrial Property Rights Holder
      NICT
    • Industrial Property Number
      2008-125720
    • Filing Date
      2009-05-13
    • Related Report
      2009 Final Research Report
  • [Patent(Industrial Property Rights)] 電力取引管理システム、管理装置、電力取引方法、及び電力取引用コンピュータプログラム2009

    • Inventor(s)
      谷口忠大
    • Industrial Property Rights Holder
      立命館大学
    • Industrial Property Number
      2009-168860
    • Filing Date
      2009-07-17
    • Related Report
      2009 Annual Research Report
  • [Patent(Industrial Property Rights)] 動作学習装置2008

    • Inventor(s)
      谷口忠大岩橋直人
    • Industrial Property Rights Holder
      NICT
    • Industrial Property Number
      2008-125720
    • Filing Date
      2008-05-13
    • Related Report
      2008 Annual Research Report

URL: 

Published: 2008-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi