FANETs in Low-Altitude Space: A Q-Learning Enabled Routing Algorithm with Visual Information

Flying ad hoc Networks (FANETs) have drawn people’s attention these years due to their wide range of civil and military applications. Due to the high mobility and limited battery capacity of unmanned aerial vehicles (UAVs), it is difficult to exploit existing ad hoc network routing algorithms protocols in espe-cially low-altitude complex environments with dense obstacles for FANETs. Therefore, this paper proposes a Q-learning-based visual information assisted routing (QVIR) algorithm for FANETs in low altitude complex environments, which could make use of the imaged data collected by the onboard camera to reduce the influence of flight environment on the network. Simulation results show that compared with the classical FANETs routing algorithm, the QVIR algorithm has better performance in terms of lower delay, packet delivery ratio, and energy efficiency.