Feature extraction based on sensor topology on localized Human Robot Interaction

2014 Fiscal Year Final Research Report

• Project/Area Number: 24700203
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Advanced Telecommunications Research Institute International
• Principal Investigator: NODA Tomoyuki 株式会社国際電気通信基礎技術研究所, 脳情報通信総合研究所, 専任研究員 (30588661)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 外骨格型ロボット / 生体信号 / ヒトロボットインタラクション

Outline of Final Research Achievements

In this project, for assured safety in controlling an exoskeleton robot as an assistive device, machine learning methods based on hypocrisies involving a problem of human-robot-interaction were developed. The result of this research would provide exoskeleton assistive systems with assured safety or continuously functioning during assistive situations. For example, in the problem of joint torque estimation using electromyography, utilizing learned intermediate structures of distributed sensors, the estimation of the motor intention of the user can be continuously functioning, even one sensor channel or its wire is broken.

Free Research Field

外骨格型ロボット