New development of statistical control theory and its application to aerospace engineering
| Project/Area Number |
17K06492
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Control engineering/System engineering
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 制御工学 / 宇宙機の制御 / 統計的学習 / ガウス過程回帰 / 軌道追従制御 / ロバスト軌道計画 / スライディングモード制御 / 最適制御 / 機械学習 / 航空宇宙 / 非線形制御 / システム同定 / 航空宇宙工学 |
|---|
| Outline of Final Research Achievements |
The objective of this research is to apply some techniques of machine learning to control engineering and provide a novel useful tools for control problems in aerospace engineering. To this end, we have provided research results in two different directions. One is to find data-driven algorithms of control theory to cope with data and statistics. The other is to develop practical control methods for aerospace engineering to use such data-driven algorithms. Concerning the former objective, we have proposed modeling and control methods based on Gaussian process regression which is an efficient data-driven estimation tool in machine learning. For the latter objective, we have obtained a robust trajectory planning method for spacecraft and a robust feedback control method for the attitude. Combining those results, we can obtain data-driven control methods for spacecraft.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究では、近年注目を集めているAIやビッグデータを扱える方法を、制御工学の分野にも応用し、さらに航空宇宙の諸問題に適用することにある。これにより、過去に蓄積された多くの制御データを利用して信頼性の高い制御が可能になるほか、従来は計算の難しかった宇宙機の軌道計画においても、コンピュータによる大規模計算を行うことでより短時間で高精度な計算結果が得られる可能性がある。本研究により、このような新しい制御手法の技術的な基盤を作ることができた。
|
Report
(5 results)
Research Products
(22 results)
