Reinforcement Learning for a Cellular Internet of UAVs: Protocol Design, Trajectory Control, and Resource Management
Reinforcement Learning for a Cellular Internet of UAVs: Protocol Design, Trajectory Control, and Resource Management
复制标题
DOI：
10.1109/mwc.001.1900262
复制
发表时间：
2020-02-01
影响因子：
12.9
通讯作者：
Poor, H. Vincent
中科院分区：
文献类型：
--
作者：
Hu, Jingzhi;Zhang, Hongliang;Poor, H. Vincent
无人驾驶飞机（UAV）可以是功能强大的物联网组件，可以在下一代蜂窝网络上执行传感任务，这些蜂窝网络通常称为无人机的蜂窝互联网。但是，由于无人机的流动性高和空气地面通道中的阴影，无人机在动态和不确定的环境中运行。因此，无人机需要在没有完整信息的情况下提高感应和交流的服务质量，这使得加强学习适合在无人机的蜂窝互联网中使用。在本文中，我们提出了一个分布式的感官和日期协议，以协调无人机进行感应和传输。然后，我们在无人机的蜂窝互联网中应用强化学习来解决关键问题，例如轨迹控制和资源管理。最后，我们指出了一些潜在的未来研究方向。
Unmanned aerial vehicles (UAVs) can be powerful Internet of Things components to execute sensing tasks over the next-generation cellular networks, which are generally referred to as the cellular Internet of UAVs. However, due to the high mobility of UAVs and shadowing in airto- ground channels, UAVs operate in a dynamic and uncertain environment. Therefore, UAVs need to improve the quality of service of sensing and communication without complete information, which makes reinforcement learning suitable for use in the cellular Internet of UAVs. In this article, we propose a distributed sense-and-send protocol to coordinate UAVs for sensing and transmission. Then we apply reinforcement learning in the cellular Internet of UAVs to solve key problems such as trajectory control and resource management. Finally, we point out several potential future research directions.