Automatic acquisition of knowledge representation and manipulation by active manipulation of cloth products
| Project/Area Number |
26700024
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (A)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Research Field |
Intelligent robotics
|
|---|
| Research Institution | Shinshu University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥24,440,000 (Direct Cost: ¥18,800,000、Indirect Cost: ¥5,640,000)
Fiscal Year 2017: ¥5,460,000 (Direct Cost: ¥4,200,000、Indirect Cost: ¥1,260,000)
Fiscal Year 2016: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2015: ¥8,320,000 (Direct Cost: ¥6,400,000、Indirect Cost: ¥1,920,000)
Fiscal Year 2014: ¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
|
|---|
| Keywords | 布の知識表現 / 布の認識 / 布の操作 / 自律型ロボット / マニピュレーション / 布の形状予測 / 知能ロボット / 柔軟物認識・操作 / 感覚行動システム / 柔軟物認識 / 柔軟物操作 / 知能ロボティクス |
|---|
| Outline of Final Research Achievements |
There are two main results of this study. One is to propose a mechanism to predict shape change of cloth accompanying operation. Conventionally, it was difficult to define a general model capable of predicting the behavior of cloth, but in this study, we showed an example of solutions, although it was targeted on cloth products of comparatively simple shape. Another achievement is to build a mechanism that allows robots to acquire manipulation methods of cloth products automatically. In order to realize this, we propose a novel movement acquisition framework combining a motion planning method and a reinforcement learning method. The manipulation trajectory suitable for the configuration of the robot arm can be generated automatically by referring to how the human being folds the cloth.
|
Report
(5 results)
Research Products
(44 results)
