Prediction Object Dynamics and Tool Handling based on Active Perception of Humanoid Robot
Project/Area Number |
21300076
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | Waseda University (2012) Kyoto University (2009-2011) |
Principal Investigator |
OGATA Tetsuya 早稲田大学, 理工学術院, 教授 (00318768)
|
Co-Investigator(Kenkyū-buntansha) |
NISHIDE Shun 京都大学, 学内共同利用施設等, 助教 (30613400)
|
Project Period (FY) |
2009 – 2012
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥12,740,000 (Direct Cost: ¥9,800,000、Indirect Cost: ¥2,940,000)
Fiscal Year 2012: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2011: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2010: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2009: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
|
Keywords | 再帰型神経回路モデル / 道具身体化 / 予測信頼性 / アフォーダンス / 能動知覚 / 神経力学モデル / 予測可能性 / 身体モデル / 環境音 / アフォダンス |
Research Abstract |
The approach is based on the embodied/active perception of robot and prediction of object dynamics. Concretely the project completed the following three themes by utilizing recurrent neural network models and humanoid robots, such as (1) prediction and recognition of environmental sounds associated with object dynamics, (2) selective learning of self-body and other object based on predictability, and (3) tool-body assimilation model. The achievements of the project could be applied not only to engineering techniques but also to academic studies on cognitive science etc.
|
Report
(5 results)
Research Products
(35 results)