Learning from the sky: autonomous flying access networks for beyond 5G

The use of flying robots (drones) carrying radio transceiver equipment is the new promising frontier in our quest towards ever more flexible, adaptable and spectrally efficient wireless networks. Beyond obvious challenges within regulatory, control, navigation, and operational domains, the deployment of autonomous flying radio access network (Fly-RANs) also comes with a number of exciting new research problems such as the issue of autonomous real-time placement of the drones in a way that can guarantee user and network performance. We present several different scenarios of interest such as IoT monitoring and mobile broadband access. The approaches lie at the cross-roads between machine learning, signal processing and optimization. Some approaches exploit the reconstruction of 3D map from sampled radio measurements which can have application beyond the realm of communications. Early-stage practical realizations are demonstrated.