Open AccessTrajectory Design and Mode Selection for a Cellular-based UAV Traffic Monitoring System
Author(s) -
Kai Wang,
Fuchao Wu,
Kaiming Xu,
Jianjun Wu
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/719/1/012073
Subject(s) - trajectory , computer science , base station , mode (computer interface) , real time computing , transmission (telecommunications) , selection (genetic algorithm) , cellular network , sleep mode , computer network , artificial intelligence , telecommunications , power (physics) , power consumption , quantum mechanics , operating system , physics , astronomy
In this paper, we propose to enable cellular networks to support a UAV traffic monitoring system, in which multiple UAVs are required to record videos from the target roads, and then transmit their video data back to the ground stations over the cellular spectrum. In this system, the video data can be transmitted directly to the ground stations bypassing the base station (BS), or via the traditional cellular links. Each UAV should select its transmission mode from the direct mode and the cellular mode as it preforms traffic monitoring tasks. Since the mode selections are influenced by the trajectories of UAVs, we study the trajectory design problem for UAVs in consideration of their transmission modes under a reinforcement learning (RL) framework. Then, we propose a trajectory design algorithm to solve this problem. Simulation results show that our proposed algorithm outperforms the single-agent one.