| Project/Area Number |
15K20850
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent mechanics/Mechanical systems
Intelligent robotics
|
|---|
| Research Institution | Iwate University |
|---|
Principal Investigator |
Kim Chyon Hae 岩手大学, 理工学部, 准教授 (30424815)
|
|---|
| Research Collaborator |
SASAKI Yoshihisa
TOMISAAW Takeya
NAKAJIMA Hisayoshi
FUNATO Shuichi
OYAMA Hirokuni
AKASHI Takuya
MIYOSHI Tasuku
OGASAWARA Toshiki
MATSUBAYASHI Yuriko
|
|---|
| Project Period (FY) |
2015-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2016: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2015: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 知能ロボット / 定点制御 / 船体制御 / 学習アルゴリズム / 動力学 / ブラックボックスモデル / 逐次学習 / 外乱 / 水上ロボット / 力学系学習木 / 水底画像処理 / 安定化制御 / 予測制御 |
|---|
| Outline of Final Research Achievements |
In this research, we developed two aquatic robots and an image processing system based on optical flow in order to estimate the position of the aquatic robots. We also developed an acceleration predictor of the robots that is based on dynamics learning tree (DLT) and FAD learning. We improved the effectiveness of DLT against noise. As a result of the control experiments using these robots, we could confirm the three facts, the robots are able to come back around a goal position when there is no wave, the robots are able to cancel the affection from wave, and the robots are able to go back around goal position and azimuth even when there is wave. The learning and control methods that are developed by this research were also effective for the control of humanoid robots and vehicles.
|
