Low-level autonomous control and tracking of quadrotor using reinforcement learning
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
0 | en_US |
dc.citation.spage |
0 | en_US |
dc.citation.volume |
95 | en_US |
dc.citation.woscount |
0 | en_US |
dc.contributor.author |
Pi, Chen-Huan | en_US |
dc.contributor.author |
Hu, Kai-Chun | en_US |
dc.contributor.author |
Cheng, Stone | en_US |
dc.contributor.author |
Wu, I-Chen | en_US |
dc.contributor.department |
機械工程學系 | zh_TW |
dc.contributor.department |
應用數學系 | zh_TW |
dc.contributor.department |
資訊工程學系 | zh_TW |
dc.contributor.department |
Department of Mechanical Engineering | en_US |
dc.contributor.department |
Department of Applied Mathematics | en_US |
dc.contributor.department |
Department of Computer Science | en_US |
dc.date.accessioned |
2020-03-02T03:23:32Z | |
dc.date.available |
2020-03-02T03:23:32Z | |
dc.date.issued |
2020-02-01 | en_US |
dc.description.abstract |
This paper proposes a low-level quadrotor control algorithm using neural networks with model-free reinforcement learning, then explores the algorithm's capabilities on quadrotor hover and tracking tasks. We provide a new point of view by examining the well-known policy gradient algorithm from reinforcement learning, then relaxing its requirements to improve training efficiency. Without requiring expert demonstrations, the improved algorithm is then applied to train a quadrotor controller with its output directly mapped to four actuators in a simulator, which is a technique used to control any linear or nonlinear system under unknown dynamic parameters and disturbances. We show two experimental tasks both in simulation and real-world quadrotors to verify our method and demonstrate performance: 1) hovering at a fixed position, and 2) tracking along a specific trajectory. | en_US |
dc.identifier.doi |
10.1016/j.conengprac.2019.104222 | en_US |
dc.identifier.issn |
0967-0661 | en_US |
dc.identifier.journal |
CONTROL ENGINEERING PRACTICE | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1016/j.conengprac.2019.104222 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/153802 | |
dc.identifier.wosnumber |
WOS:000510526900020 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
Reinforcement learning | en_US |
dc.subject |
Policy gradient | en_US |
dc.subject |
Quadrotor | en_US |
dc.title |
Low-level autonomous control and tracking of quadrotor using reinforcement learning | en_US |
dc.type |
Article | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 期刊論文
引用此條目
Pi, C.-H., Hu, K.-C., Cheng, S., & Wu, I.-C. (2020). Low-level autonomous control and tracking of quadrotor using reinforcement learning. CONTROL ENGINEERING PRACTICE, 95, 0. https://doi.org/10.1016/j.conengprac.2019.104222
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/153802