Arm motion estimation based on distributed representations and neurodynamics

Research Project

Project/Area Number	24760213
Research Category	Grant-in-Aid for Young Scientists (B)
Allocation Type	Multi-year Fund
Research Field	Intelligent mechanics/Mechanical systems
Research Institution	Teikyo University
Principal Investigator	YAMANE Ken 帝京大学, 理工学部, 助教 (30581235)
Project Period (FY)	2012-04-01 – 2015-03-31
Project Status	Completed (Fiscal Year 2014)
Budget Amount *help	¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000) Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000) Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000) Fiscal Year 2012: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Keywords	軌道アトラクタ / 選択的不感化 / 分散表現 / 神経力学系 / 表面筋電位 / 運動推定 / 人支援 / 動作推定 / リカレントニューラルネット / 人支援システム
Outline of Final Research Achievements	From this study, we propose a method of processing sequences of motions based only on distributed representations and neurodynamics. To assess the method’s applicability, we constructed a motion estimation system using a trajectory attractor model: a recurrent neural network with continuous-time dynamics. Experimentally obtained results from surface myoelectric signals from an arm show that the system estimated 15 complex hand motions with average accuracy of about 86%, demonstrating the great potential of this system.