A Study on Perception-Assist to Modify Human Motion Using Mechanical Vibration Stimulation

2018 Fiscal Year Final Research Report

• Project/Area Number: 16H04305
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Intelligent mechanics/Mechanical systems
• Research Institution: Kyushu University
• Principal Investigator: Kiguchi Kazuo 九州大学, 工学研究院, 教授 (90269548)
• Co-Investigator(Kenkyū-buntansha): 荒田 純平 九州大学, 工学研究院, 准教授 (40377586)
• Research Collaborator: Honda Koki
• Project Period (FY): 2016-04-01 – 2019-03-31
• Keywords: 知能機械学 / 人間工学 / ロボット工学

Outline of Final Research Achievements

The research results show that the conditions of the mechanical vibration stimulation affect the amount of motion change of the human joint such as elbow or knee joint while the daily motion is performed. Furthermore, a method to change the human motion from his/her intended motion to the previously defined motion by adjusting the amount of motion change based on the frequency control of the mechanical vibration stimulation was successfully proposed. The proposed control method results in realization of automatic human motion modification to avoid the possible accident in Perception-Assist.
In this research, machine learning was applied for the real-time estimation of the dangerous motion which causes the serious accident. In addition, a method to estimate interaction between a person and the other person was proposed for Perception-Assist.

Free Research Field

知能機械学

Academic Significance and Societal Importance of the Research Achievements

近年，筋力弱者の日常生活動作補助等を目的とした動作支援ロボット（パワーアシストロボット等）の研究が盛んである．しかし，動作支援を必要とする高齢者等の筋力弱者は，運動能力のみならず環境認知能力も衰え，外部刺激に対する反応時間も長くなるなど，動作支援のみでは対応できない問題が多いため，危険な動作を自動的に安全な動作に補正する認知アシストの研究が進めていた．本研究により，動作中の人の筋肉に加える機械的振動刺激を調整することにより動作を変更することが可能となり，環境認知機能の衰えた人の動作を自動的に補正し，事故を未然に防ぐ認知アシストの実現可能性が高まった．