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

2023 Fiscal Year Final Research Report

Development of exoskeleton robot control guiding user to appropriate motion according to situation

Research Project

  • PDF
Project/Area Number 21K17836
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61050:Intelligent robotics-related
Research InstitutionInstitute of Physical and Chemical Research

Principal Investigator

Furukawa Jun-ichiro  国立研究開発法人理化学研究所, 情報統合本部, 研究員 (50721619)

Project Period (FY) 2021-04-01 – 2024-03-31
Keywords運動アシストロボット / 生体信号 / 機械学習
Outline of Final Research Achievements

This study developed a control strategy for an exoskeleton robot that physically assists human motions, allowing it to perform appropriate movements according to the situation. Generally, exoskeleton robots are designed to reduce the physical burden in pre-determined situations, so the user’s motions are often limited. In this study, we proposed a control method based on human intention estimation that expands the allowable range of motion conditions. We also investigated a method to evaluate human motions widely based on muscle activity. It was confirmed that this resulted in a robot that accurately reflects the wearer’s intentions and guides them to appropriate movements.

Free Research Field

ロボティクス

Academic Significance and Societal Importance of the Research Achievements

従来、外骨格型ロボット制御の多くでは、予め支援対象なる動作を想定しラベル付けしたデータを用いて設計された支援方策が利用される。そのため、装着者はその想定された動作を行うことが前提となっており、部分的な身体負荷軽減が着目されている。本研究では、ラベルの無いデータを利活用した機械学習手法を援用した制御アルゴリズムの提案と身体動作を筋活動から大局的に評価する方法を検討し、装着者が想定外の動作を行う状況下でも動作意図を精度よく推定し適切にロボットを駆動できるようになった。本成果により、外骨格型ロボットの活用範囲の拡張が期待できる。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi