Development of Robot Control Interface based Mutual Learning of Users and Machines.
| Project/Area Number |
15K05884
|
|---|
| 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 | Hokkaido University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
飯塚 博幸 北海道大学, 情報科学研究科, 准教授 (30396832)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | インタフェース / 相互学習 / ニューラルネットワーク / ロボット操縦 / つもり制御 / LSTM / リカレント |
|---|
| Outline of Final Research Achievements |
In this research, we have proposed a mutual learning interface between human and machine where the machine exploits the prediction errors to read user’s intention. To do this, we extracted human intention from body movements, especially hand movements, and associate with movements of multi-degree of freedom spider robot, thereby constructing interface to operate robot only from hand movements. Since the hand movements reacts the intention that varies depending on the individual user, the correspondence between the hand movements and the operation of the controlled object is built using machine learning. It is shown that the proposed interface can adapt to multiple behaviors of the robot.
|
Report
(4 results)
Research Products
(18 results)
