Project/Area Number |
18K18133
|
Research Category |
Grant-in-Aid for Early-Career Scientists
|
Allocation Type | Multi-year Fund |
Review Section |
Basic Section 61050:Intelligent robotics-related
|
Research Institution | Tokyo Polytechnic University |
Principal Investigator |
Kono Hitoshi 東京工芸大学, 工学部, 助教 (70758367)
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2020: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
Keywords | 強化学習 / 転移学習 / 身体図式 / ボディキャリブレーション / 多脚型ロボット / 物理演算シミュレーション / 身体マッピング / 身体表象 / 自己身体表象 / 自律ロボット |
Outline of Final Research Achievements |
The aim of this research is to develop a method which is automatically calculation the difference among heterogeneous robots' body structure based on body representation. Transfer the knowledge is needed the mapping description method between robots’ heterogeneity. In this research, a body calibration is proposed and developed in which the robot automatically learns the own body structure. The proposed method evaluated using virtual multi-legged robot constructed in the physics simulation and two types of real multi-legged robots. Reinforcement learning and transfer learning were performed between developed robots, and the usefulness of the proposed method was evaluated.
|
Academic Significance and Societal Importance of the Research Achievements |
本研究の学術的意義は,ヒトの脳内で動作していると考えられる身体表象や身体図式の理論をロボットに応用することにより,ロボット間における異なる身体的構造を自動的に記述できることにある.これにより社会的意義としては,様々な学習ロボット間での知識の再利用,すなわち転移学習の際に身体性や構造の違いをヒトが定義する必要がなく,より転移学習の実世界応用を支援する技術である.
|