Autonomous Driving From the Sky: Design and End-to-End Performance Evaluation

For autonomous vehicles to operate without human intervention, information sharing from local sensors plays a fundamental role. This can be challenging to handle with bandwidth-constrained communication systems, which calls for the adoption of new wireless technologies, such as the use of the millimeter wave (mmWave) bands, to solve capacity issues. Another approach is to exploit Unmanned Aerial Vehicles (UAVs), able to provide human users and their cars with an aerial bird’seye view of the scene otherwise unavailable, thus offering broader and more centralized observations. To do so, we use the ns-3 simulator to conduct an end-to-end simulation campaign with applications that model the transmission of information from a UAV to vehicles based on real data extracted from the Stanford Drone Dataset. We design a novel framework to study four scenarios representing different UAV-to-ground communication strategies. In each scenario, a UAV, operating at mmWaves, broadcasts realistic sensory data to the ground as a means to extend the (local) perception range of vehicles. This paper provides the first evaluation of the trade-offs between centralized data processing in the sky and distributed local processing on the ground, with considerations related to the throughput, latency and reliability of the communication process.