On methods to assist manipulation of intelligent machines considering human sensory-motor characteristics

2014 Fiscal Year Final Research Report

• Project/Area Number: 24560308
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Intelligent mechanics/Mechanical systems
• Research Institution: Tokyo University of Technology
• Principal Investigator: MATSUO Yoshiki 東京工科大学, コンピュータサイエンス学部, 教授 (90173806)
• Co-Investigator(Kenkyū-buntansha): URAGAMI Daisuke 日本大学, 生産工学部, 助教 (40458196) ; SEKIGUCHI Akinori 東京工科大学, コンピュータサイエンス学部, 講師 (80344612)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 人間機械協調 / 操作運動支援 / 知覚運動特性 / 生体信号計測 / 力操作 / 歩行運動 / 認知バイアス / 学習アルゴリズム

Outline of Final Research Achievements

In order to establish foundations for the development of methods that enables non-professional persons to maneuver intelligent machines such as robots, human characteristics of cognitive and sensory-motor functions are analyzed. Basic assistive methods are examined which are expected to be effective in developing human-oriented, easily-operated intelligent machines. Specifically, relationships between machine properties and human sensory-motor characteristics are investigated through experiments employing measurements of bio-signals such as EEG, EMG, and motion variables. Results show feasibility of building and evaluating manipulation systems using such bio-signals and effectiveness of a learning algorithm inspired by human cognitive biases.

Free Research Field

制御工学，メカトロニクス，人間中心システム