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

自動的な知識の抽出に基づく動物行動学に基づくソーシャルロボットの行動モデルの獲得

Research Project

Project/Area Number 19F19380
Research Category

Grant-in-Aid for JSPS Fellows

Allocation TypeSingle-year Grants
Section外国
Review Section Basic Section 61050:Intelligent robotics-related
Research InstitutionChuo University

Principal Investigator

新妻 実保子  中央大学, 理工学部, 教授 (10548118)

Co-Investigator(Kenkyū-buntansha) VINCZE DAVID  中央大学, 理工学部, 外国人特別研究員
Project Period (FY) 2019-11-08 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥2,100,000 (Direct Cost: ¥2,100,000)
Fiscal Year 2021: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 2020: ¥800,000 (Direct Cost: ¥800,000)
Fiscal Year 2019: ¥400,000 (Direct Cost: ¥400,000)
Keywordsreinforcement learning / Human-Robot Interaction / multi-agent systems / rule-base reduction / fuzzy rule interpolation / knowledge extraction / fuzzy control / antecedent redundancy / fuzzy rule clustering
Outline of Research at the Start

本研究では,犬の愛着行動のモデル化及び人-ロボットコミュニケーションにおける有用性について取り組むものである。
このアプローチの最大の課題は,行動のモデル化には動物行動学者による観察と知識が不可欠な点である。ヴィンツェ博士と共同して行う研究は,Q-learningによる強化学習のメカニズムとファジィルール補間を統合することにより,動物行動学者の知識も大量の学習データも必要とせず,自動的にゼロからルールベースを構築し,環境からのフィードバックに基づいてルールベースを構築,収束させ,動物行動学的に抽出されるような行動モデルを自動的に抽出しようとするものである。

Outline of Annual Research Achievements

In this period the possibility of using multiple agents in the Fuzzy Rule Interpolation-based Reinforcement Learning (FRI-RL) and running them distributed in parallel was investigated. As the FRI-RL knowledge extraction method is inherently sequential, some sub-results can be different in the parallel version, but still providing a sufficient solution. This way the knowledge extraction can be performed much faster, therefore using the method on problems with a high dimension count becomes practical. Also, a possible bridging interface between the behaviour simulation model (Strange Situation Test (SST) realized with an FRI-based fuzzy automaton) and real physical robots have been partly designed and implemented. Experimenting with real physical robots is underway. Furthermore a suitable indoor localization system was constructed and adapted to the needs of the planned Human-Robot Interaction (HRI) scenario. This system is able to easily calibrate the indoor localization system’s virtual coordinate system to the real-world physical coordinate system, which makes our planned HRI experiments possible with real humans and mobile robots. A customized robot behaviour engine and a motion control system was developed to support the proposed artificial Strange Situation Test experiments.

Research Progress Status

令和3年度が最終年度であるため、記入しない。

Strategy for Future Research Activity

令和3年度が最終年度であるため、記入しない。

Report

(3 results)
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • 2019 Annual Research Report
  • Research Products

    (5 results)

All 2021 2020

All Presentation (5 results) (of which Int'l Joint Research: 5 results)

  • [Presentation] Towards the automatic observation and evaluation of ethologically inspired Human-Robot Interaction2021

    • Author(s)
      D. Vincze, M. Gacsi, S. Kovacs, P. Korondi, A. Miklosi and M. Niitsuma
    • Organizer
      2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Demonstration of expert knowledge injection in Fuzzy Rule Interpolation based Q-learning2021

    • Author(s)
      Tompa, T., Kovacs, S., Vincze, D., Niitsuma, M.
    • Organizer
      2021 IEEE/SICE International Symposium on System Integration
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Towards the automatic observation and coding of simple behaviours in ethological experiments2021

    • Author(s)
      Vincze, D., Gacsi, M., Kovacs, S., Niitsuma, M., Korondi, P., Miklosi, A.
    • Organizer
      2021 IEEE/SICE International Symposium on System Integration
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Antecedent redundancy exploitation in fuzzy rule interpolation-based reinforcement learning2020

    • Author(s)
      Vincze, D., Toth, A., Niitsuma, M.
    • Organizer
      2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Football Simulation Modeling with Fuzzy Rule Interpolation-based Fuzzy Automaton2020

    • Author(s)
      Vincze, D., Toth, A., Niitsuma, M.
    • Organizer
      2020 17th International Conference on Ubiquitous Robots
    • Related Report
      2020 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2019-11-29   Modified: 2024-03-26  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi