Learning efficient navigation in vortical flow fields
Navigation and trajectory planning in environments with background flow, relevant for robotics, are challenging provided information only on local surrounding. The authors propose a reinforcement learning approach for time-efficient navigation of a swimmer through unsteady two-dimensional flows.
保存先:
| 主要な著者: | , , , , |
|---|---|
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
Nature Portfolio
2021-12-01
|
| シリーズ: | Nature Communications |
| オンライン･アクセス: | https://doi.org/10.1038/s41467-021-27015-y |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|