arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.02147eess.SYcs.LGcs.SY
收藏

航空应用中的强化学习综述

A Survey on Reinforcement Learning in Aviation Applications

George Washington University(乔治·华盛顿大学);Ecole Nationale de l’Aviation Civile(法国国立民用航空学院);Rochester Institute of Technology(罗切斯特理工学院)

Pouria Razzaghi, Amin Tabrizian, Wei Guo, Shulu Chen, Abenezer Taye, Ellis Thompson, Alexis Bregeon, Ali Baheri, Peng Wei

AI总结:

本文综述了强化学习在航空领域的应用,介绍了标准RL表述与求解方法,调查了现有基于RL的航空应用,并指出了技术差距与未来研究方向。

摘要:

与基于模型的控制和优化方法相比,强化学习(RL)提供了一个数据驱动、基于学习的框架来表述和求解序贯决策问题。由于航空业数据可用性和计算能力的大幅提升,RL框架变得极具前景。许多基于航空的应用可以被表述或视为序贯决策问题。其中一些是离线规划问题,而另一些则需要在线求解且具有安全关键性。在这篇综述论文中,我们首先描述了标准的RL表述和求解方法。然后我们调查了航空领域现有基于RL应用的概况。最后,我们对论文进行了总结,识别了技术差距,并提出了航空领域RL研究的未来方向。

英文摘要:

Compared with model-based control and optimization methods, reinforcement learning (RL) provides a data-driven, learning-based framework to formulate and solve sequential decision-making problems. The RL framework has become promising due to largely improved data availability and computing power in the aviation industry. Many aviation-based applications can be formulated or treated as sequential decision-making problems. Some of them are offline planning problems, while others need to be solved online and are safety-critical. In this survey paper, we first describe standard RL formulations and solutions. Then we survey the landscape of existing RL-based applications in aviation. Finally, we summarize the paper, identify the technical gaps, and suggest future directions of RL research in aviation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑