2015 Fiscal Year Annual Research Report
最低センサー数を用いた人間の動さ計測と認識とその応用
Project/Area Number |
14F04768
|
Research Institution | Tokyo University of Agriculture and Technology |
Principal Investigator |
Venture Gentiane 東京農工大学, 工学(系)研究科(研究院), 准教授 (30538278)
|
Co-Investigator(Kenkyū-buntansha) |
BONNET VINCENT 東京農工大学, 工学(系)研究科(研究院), 外国人特別研究員
|
Project Period (FY) |
2014-04-25 – 2017-03-31
|
Keywords | inverse kinematics / inverse dynamics / Extended Kalman filter / motion analysis |
Outline of Annual Research Achievements |
The candidate has managed to fulfill most of his ambitious goals. We have developed a new algorithm that allows for solving both kinematics and dynamics at the same time using extended Kalman filters. It gives an estimate in real time. The method has been tested on real human data with a very high accuracy for simple human models.
|
Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
The research has progressed according to the research plan and no delay has been noticed. The new algorithm that allows for solving both kinematics and dynamics at the same time using extended Kalman filters. It gives an estimate in real time. The method has then been tested on data collected on real humans.Our algorithm performs much better than other algorithm for simple human models.
|
Strategy for Future Research Activity |
The candidate research will continue in implementing the algorithm for more complex 3D human models and a variety of tasks and situations. Work on dynamic quantities is also scheduled. For example estimating the ground reaction forces frmo the data obtained by the previous algorithm.
|