Development of Haptic Sensing System for Control of Hand Proetheses

2022 Fiscal Year Final Research Report

• Project/Area Number: 20K11906
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61020:Human interface and interaction-related
• Research Institution: Maebashi Institute of Technology
• Principal Investigator: Wang Feng 前橋工科大学, 工学部, 教授 (80323046)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Keywords: ヒューマン-マシンイン・タフェース / 義手 / 触覚 / センシング / 運動意思識別 / 機械学習

Outline of Final Research Achievements

Aiming at improvement of the QoL of upper-extremity amputees, this study was about development of a new human-machine interface for the real-time control of a powered prosthetic hand.
In this study, a tactile sensor was first developed using Polyvinylidene Difluoride (PVDF) film to detect the tactile feature on human body surface. Two tactile sensors were used to detect the tactile feature on the forearm caused by intended hand motions. Machine learning was applied to classify hand motion intentions using detected tactile feature patterns. Motion intention classification methods were further compared and studied, and support vector machine was chosen for real-time classification of motion intention. The experimental results showed that average classification accuracy for the 6 types of motion was over 80% for experiment participants who were with simple training lasting for only minutes. This verified the efficacy of the proposed system.

Free Research Field

生体医工学

Academic Significance and Societal Importance of the Research Achievements

上肢切断者の QOL を向上するために、様々な義手は開発された。特に近年様々な高性能電動義手が開発され、巧妙な動作の実現が可能となっている。しかしながら、国内に上肢切断者の約８割が電動義手の使用を希望しているにも関わらず、実際の普及率は１割未満で極めて低い。経済的などの原因以外に、義手使用者の運動意思の読み取りは、電動義手普及の技術的なボトルネックとなり、便利有効な方法は求められている。
本研究ではごく少数のセンサを利用することで複数種類の運動意図を識別でき、義手使用者の意思通り自由自在に能動義手を動作させることが期待でき、電動義手の普及におけるボトルネックを突破することが期待できる。