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

2022 Fiscal Year Final Research Report

Construction of a comprehensive cognitive architecture based on the POMDP theory and its application to physical RPA

Research Project

  • PDF
Project/Area Number 19K12157
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61040:Soft computing-related
Research InstitutionSaga University

Principal Investigator

Itoh Hideaki  佐賀大学, 理工学部, 教授 (20345375)

Project Period (FY) 2019-04-01 – 2023-03-31
Keywords確率的情報処理 / POMDP / 認知アーキテクチャ / Physical RPA / 行動最適化
Outline of Final Research Achievements

In this study, we have constructed a novel cognitive architecture that can comprehensively realize cognitive abilities (i.e., "thinking" abilities), has a solid theoretical foundation, and is easy to apply to real problems, by reformulating a fundamental cognitive architecture, the blackboard model, based on the Partially Observable Markov Decision Process (POMDP) theory. Furthermore, we have applied the proposed architecture to a real problem called physical Robotic Process Automation (physical RPA) and showed its effectiveness. Additionally, we have developed an electroadhesive pad and an electroadhesion sensor to realize physical RPA systems for handling paper.

Free Research Field

ソフトコンピューティング

Academic Significance and Societal Importance of the Research Achievements

本研究で構築した新たな認知アーキテクチャは、認知能力を包括的に実現でき、理論的基盤がしっかりしていて工学的に応用しやすいため、本研究において開発したロボットシステム以外にも様々な応用に役立つと考えられる。また、本研究では黒板モデルを定式化し直したが、同様のアプローチは他の様々な認知アーキテクチャの再定式化にも用いることができると考えられる。さらに、本研究で開発した静電吸着パッドや吸着センサは、今後、紙を用いる作業を自動化することのできるフィジカルRPAを実現する際に有用であると考えられる。

URL: 

Published: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi