Deep Learning-Based Joint Communication and Sensing for 6G Cellular-Connected UAVs
José Rodríguez-Piñeiro, Wenjing Liu, Yu Wang, Xuefeng Yin, Juyul Lee, Myung-Don Kim
Abstract
Unmanned Aerial Vehicles (UAVs) have been widely used in military and civilian fields in the recent years, being many of their applications dependent on some strategy for sensing the environment. With full Joint Communication And Sensing (JCAS) support, increased bandwidth and higher frequency bands expected for sixth generation (6G) communication systems, a new horizon on the usage of cellular radio frequency (RF) signals for joint air-to-ground (A2G) communications and precise environment sensing is open. In this short paper, the basics of a Deep Learning (DL)-based approach for environment sensing from a UAV by using RF signals from terrestrial cellular deployments is presented. Preliminary results prove that the achieved accuracy of the location of scatterers on the environment is currently around 1 m. The proposed approach constitutes a totally autonomous JCAS solution for environment sensing whose accuracy could be even further improved by learning from previously captured data.