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

Flexible Development Technology for Cyber Physical Systems Using Reinforcement Learning

Research Project

Project/Area Number 16K06424
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Control engineering/System engineering
Research InstitutionOsaka Prefecture University

Principal Investigator

Matsumoto Keinosuke  大阪府立大学, 工学(系)研究科(研究院), 客員研究員 (90285304)

Co-Investigator(Renkei-kenkyūsha) MORI Naoki  大阪府立大学, 大学院工学研究科, 准教授 (90295717)
Project Period (FY) 2016-04-01 – 2019-03-31
Project Status Completed (Fiscal Year 2018)
Budget Amount *help
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2018: ¥260,000 (Direct Cost: ¥200,000、Indirect Cost: ¥60,000)
Fiscal Year 2017: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2016: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Keywordsサイバーフィジカルシステム / 機械学習 / エージェント / モデル駆動開発 / システム情報(知識)処理
Outline of Final Research Achievements

Cyber physical systems are modeled as multi-agent systems that act autonomously. To speed up learning, we have developed a new reinforcement learning method that shares other agents' action histories. Furthermore, by placing models that are the design drawing of software at the center of development, model-driven development method enables model reuse, conversion to different types of models, and automatic generation of source code from the models. We have got the prospect that the proposed method can withstand practical use as a flexible development method if the method is applied to the real world.

Academic Significance and Societal Importance of the Research Achievements

研究代表者が開発したシステム効用の最大化を図る交渉プロトコルを適用することにより,システム評価を最大化でき,さらに実フィールド環境では不確実性や計測不能な未知パラメータが存在するため,試行錯誤を通して環境に適応する強化学習を採用した.これらによりネットワーク通信技術と組み合わせシステムを正当な状況下で運用させることができ,信頼性・安全性が大幅に向上する.またマルチエージェントによるシミュレーションを利用するため,想定外の状況が創発される可能性をもつ点で他の手法より優位性を持つ.

Report

(4 results)
  • 2018 Annual Research Report   Final Research Report ( PDF )
  • 2017 Research-status Report
  • 2016 Research-status Report
  • Research Products

    (26 results)

All 2019 2018 2017 2016

All Journal Article (7 results) (of which Peer Reviewed: 7 results,  Open Access: 3 results,  Acknowledgement Compliant: 1 results) Presentation (19 results) (of which Int'l Joint Research: 8 results)

  • [Journal Article] ストーリー解析のための文の分散表現に基づく小説の自動セグメンテーション手法の提案2019

    • Author(s)
      福田清人, 森直樹, 松本啓之亮, 岡田真
    • Journal Title

      芸術科学会論文誌

      Volume: 印刷中

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Intelligent Software Development Method Based on Model Driven Architecture2018

    • Author(s)
      K. Matsumoto, K. Nakoshi, and N. Mori
    • Journal Title

      International Journal on Advances in Software

      Volume: 11 Pages: 88-96

    • Related Report
      2018 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Learning Method by Sharing Activity Histories in Multiagent Environment2017

    • Author(s)
      K. Matsumoto, T. Gohara, and N. Mori
    • Journal Title

      International Journal on Advances in Intelligent Systems

      Volume: Vol. 10 Pages: 71-80

    • Related Report
      2017 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] 多層個体群を有する遺伝的プログラミングの提案およびBoolean問題への適用2017

    • Author(s)
      長谷川拓,森直樹,松本啓之亮
    • Journal Title

      進化計算学会論文誌

      Volume: Vol. 8 Pages: 52-60

    • NAID

      130006342387

    • Related Report
      2017 Research-status Report
    • Peer Reviewed
  • [Journal Article] 劣個体分布に基づく DII analysis の提案と応用2016

    • Author(s)
      長谷川拓,井上和之.荒木悠太,森直樹,松本啓之亮
    • Journal Title

      進化計算学会論文誌

      Volume: Vol. 7 Pages: 13-23

    • NAID

      130005420390

    • Related Report
      2016 Research-status Report
    • Peer Reviewed / Acknowledgement Compliant
  • [Journal Article] Analysis of Parameter-less Population Pyramid on the Local Distribution of Inferior Individuals2016

    • Author(s)
      T. Hasegawa, Y. Araki, N. Mori and K. Matsumoto
    • Journal Title

      Intelligent and Evolutionary Systems - Adaptation, Learning and Optimization

      Volume: 8 Pages: 149-164

    • Related Report
      2016 Research-status Report
    • Peer Reviewed
  • [Journal Article] CMA-ES with Surrogate Model Adapting to Fitness Landscape2016

    • Author(s)
      K. Tsukada, T. Hasegawa, N. Mori and K. Matsumoto
    • Journal Title

      Intelligent and Evolutionary Systems - Adaptation, Learning and Optimization

      Volume: 8 Pages: 417-429

    • Related Report
      2016 Research-status Report
    • Peer Reviewed
  • [Presentation] Development of Agent Predicting Werewolf with Deep Learning2018

    • Author(s)
      M. Kondoh, K. Matsumoto, and N. Mori
    • Organizer
      15th International Symposium on Distributed Computing and Artificial Intelligence
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] A Novel Sentence Vector Generation Method Based on Autoencoder and Bi-Directional LSTM2018

    • Author(s)
      K. Fukuda, N. Mori and K. Matsumoto
    • Organizer
      15th International Symposium on Distributed Computing and Artificial Intelligence
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Recognizing the Order of Four-Scene Comics by Evolutionary Deep Learning2018

    • Author(s)
      S. Fujino, N. Mori and K. Matsumoto
    • Organizer
      15th International Symposium on Distributed Computing and Artificial Intelligence
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Relaxation Method of Convolutional Neural Network for Natural Language Processing2018

    • Author(s)
      R. Iwasaki, T. Hasegawa, N. Mori, and K. Matsumoto
    • Organizer
      15th International Symposium on Distributed Computing and Artificial Intelligence
    • Related Report
      2018 Annual Research Report
    • Int'l Joint Research
  • [Presentation] LSTMを用いた人狼予測と人狼ゲーム分析2018

    • Author(s)
      近藤まなみ, 長谷川拓, 森直樹, 松本啓之亮
    • Organizer
      人工知能学会全国大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] U-Martシステムを基盤としたエネルギー取引シミュレータの提案2018

    • Author(s)
      中野洋志,大嶺貴晃,森 直樹,松本啓之亮,平野秀明,北村聖一,森 一之
    • Organizer
      電気学会 電子・情報・システム部門大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] LSTMを用いた人狼ゲームエージェントの戦略獲得手法の提案2018

    • Author(s)
      近藤まなみ, 森直樹, 松本啓之亮
    • Organizer
      電気学会 電子・情報・システム部門大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] 深層強化学習を用いたデイトレード戦略獲得手法の検討2018

    • Author(s)
      森大典,森直樹,松本啓之亮,渡邊順一朗
    • Organizer
      電気学会 電子・情報・システム部門大会
    • Related Report
      2018 Annual Research Report
  • [Presentation] Intelligent Software Development Method by Model Driven Architecture2017

    • Author(s)
      K. Matsumoto, K. Nakoshi, and N. Mori
    • Organizer
      6th International Conference on Intelligent Systems and Applications
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Analysis of Scaling for Fitness Landscape Learning Evolutionary Computation Based on CMA-ES2017

    • Author(s)
      T. Hasegawa, N. Mori, and K. Matsumoto
    • Organizer
      Genetic and Evolutionary Computation Conference
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] Agent of Werewolf Game Applying Deep Learning Predictions2017

    • Author(s)
      M. Kondoh, K. Fukuda, T. Hasegawa, K. Matsumoto, and N. Mori
    • Organizer
      6th Asian Conference on Information Systems
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research
  • [Presentation] パーツの組合せによる印象を考慮した自動キャラクタデザインシステム2017

    • Author(s)
      山本元気,松本啓之亮,森直樹
    • Organizer
      第61回システム制御情報学会研究発表講演会
    • Related Report
      2017 Research-status Report
  • [Presentation] 遺伝的プログラミングを用いた決定木の最適化2017

    • Author(s)
      田中良幸,松本啓之亮,森直樹
    • Organizer
      第61回システム制御情報学会研究発表講演会
    • Related Report
      2017 Research-status Report
  • [Presentation] 深層学習を用いた人狼エージェントの行動予測2017

    • Author(s)
      近藤まなみ,松本啓之亮,森直樹
    • Organizer
      第61回システム制御情報学会研究発表講演会
    • Related Report
      2017 Research-status Report
  • [Presentation] Learning Method by Sharing Activity Logs in Multiagent Environment2016

    • Author(s)
      K. Matsumoto, T. Gohara, and N. Mori
    • Organizer
      10th International Conference on Advanced Engineering Computing and Applications in Sciences
    • Place of Presentation
      Venice, Italy
    • Year and Date
      2016-10-09
    • Related Report
      2016 Research-status Report
    • Int'l Joint Research
  • [Presentation] 株式市場における人工市場と現実市場の類似度指標についての考察2016

    • Author(s)
      住田和也,松本啓之亮,森直樹
    • Organizer
      電気学会 電子・情報・システム部門大会
    • Place of Presentation
      神戸大学 (兵庫県神戸市)
    • Year and Date
      2016-08-31
    • Related Report
      2016 Research-status Report
  • [Presentation] アクティビティ図の再利用のための検索法2016

    • Author(s)
      丸本晃大,松本啓之亮,森直樹
    • Organizer
      第60回システム制御情報学会研究発表講演会
    • Place of Presentation
      京都テルサ (京都府京都市)
    • Year and Date
      2016-05-25
    • Related Report
      2016 Research-status Report
  • [Presentation] 単語と画像の印象的相関関係に基づく顔画像生成システム2016

    • Author(s)
      山本元気,松本啓之亮,森直樹
    • Organizer
      第60回システム制御情報学会研究発表講演会
    • Place of Presentation
      京都テルサ (京都府京都市)
    • Year and Date
      2016-05-25
    • Related Report
      2016 Research-status Report
  • [Presentation] 株価データの解析におけるDeep Learningの導入2016

    • Author(s)
      住田和也,松本啓之亮,森直樹
    • Organizer
      第60回システム制御情報学会研究発表講演会
    • Place of Presentation
      京都テルサ (京都府京都市)
    • Year and Date
      2016-05-25
    • Related Report
      2016 Research-status Report

URL: 

Published: 2016-04-21   Modified: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi