Learning controlof object manipulation with unknown environmental interaction based on machine learning
| Project/Area Number |
22700198
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Shizuoka University (2012)
Tokyo University of Agriculture and Technology (2010-2011) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2010 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2010: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
|
|---|
| Keywords | ロボット行動学習 / 物体操作 / 機械学習 / 最適制御 / ロボット / 学習 / 接触モード切り替り / 最適制御・強化学習 / モデル予測制御 / 物体抱え上げ操作 / 接触モードの切り替り |
|---|
| Research Abstract |
We proposed a learning control method of object manipulation, where physical interaction between the robot and its environment is unknown. Pattern classification method was integrated with control methods such as reinforcement learning and model predictive control. It was verified in experiment using physical simulation that the proposed method can realize appropriate robot control based on information obtained by off-line trial and errors.
|
Report
(4 results)
Research Products
(22 results)
