Development of a motion estimation method based on tempo-spacial information and its applications

2021 Fiscal Year Final Research Report

• Project/Area Number: 19H04192
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 61050:Intelligent robotics-related
• Research Institution: Meiji University
• Principal Investigator: Ozawa Ryuta 明治大学, 理工学部, 専任教授 (40368006)
• Co-Investigator(Kenkyū-buntansha): 岡田 志麻 立命館大学, 理工学部, 教授 (40551560) ; 福永 修一 東京都立産業技術高等専門学校, ものづくり工学科, 准教授 (70402518)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 筋電モーメント / ロボットハンド / 筋電計測装置 / 運動識別

Outline of Final Research Achievements

This study proposed new features for estimating hand and wrist motion with multi-point surface muscle electrodes. The features, named "myoelectric moments," are based on the position of the myoelectric electrodes weighted by the potential. We analyzed the features with the electrodes attached around the forearm during multiple hand postures and wrist movements. Then, we found that the myoelectric moments intuitively interpret the relationship between the features and the motions. We also employed machine learning methods to discriminate motion from these features. In addition, we developed a wearable multi-point muscle electrode to facilitate myoelectric measurement at multiple points. Furthermore, we developed prosthetic and robotic hands for the applications of myoelectric moments.

Free Research Field

ロボティクス

Academic Significance and Societal Importance of the Research Achievements

本研究では、前腕などに取り付けた複数の筋電極から運動を推定するための新しい特徴量を提案した。この手法は、筋電義手や新しい入力デバイスを構成する際に重要な基礎技術となる。ここでは、この新しい特徴量が運動の識別を行うために、直観的でわかりやすい特徴を示し、機械学習などで動作識別が行えることを示した。また、計測するための筋電計測システムと応用先の義手などの開発も合わせて行った。