Learning system of wearable robot for cooperative gait assistance with user
| Project/Area Number |
15K05894
|
|---|
| 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 | Aichi Institute of Technology (2017)
Nagoya University (2015-2016) |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
宇野 洋二 名古屋大学, 工学研究科, 教授 (10203572)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
|
|---|
| Keywords | 装着型ロボット / 学習制御 / 歩行補助 |
|---|
| Outline of Final Research Achievements |
In this study, we developed an on-line learning system of gait pattern for a wearable robot to assist walking. A cost function of our learning system was defined by the sum of the measured arm loading force of a user and the power consumption of the motors during walking. Via-points of the joint trajectories were optimized so as to reduce the cost function by Newton-like method. We propose an on-line learning algorithm of the via-point parameters by RLS algorithm which achieves less number of iteration than a conventional method. We confirmed that the arm loading force of a user decreased while walking with a wearable robot with little change of power consumption by using the proposed algorithm.
|
Report
(4 results)
Research Products
(13 results)
