Navigation Methods for UAVs in GNSS-Denied Environments Using Artificial Intelligence
With the rapid advancement of autonomous flight technology, there is an increasing demand for higher precision and advanced navigation techniques, with permissible distance errors often restricted to a few meters. Furthermore, the ubiquitous deployment of Unmanned Aerial Vehicles (UAVs) necessitates the integration of novel technologies to ensure operational continuity under adverse conditions, such as environmental signal interference, hostile attacks, or traversal through zones of complete signal loss. This study presents a methodology to address these challenges, enabling themaintenance of coordinates and navigation for UAVs to traverse jammed or completely out-of-coverage zones, thereby avoiding the need for emergency landings or Return-to-Home (RTH) protocols common in current UAV systems. The proposed approach leverages the TransGAN model, a framework typically employed for data analysis comprising a Generator and a Discriminator. In this context, the model processes sequential real-world coordinate data. Under normal GNSS operation, TransGAN is trained as a high-precision prediction model utilizing velocity and coordinate data as inputs. Conversely, during GNSS outages or interference, the trained TransGAN model is utilized to generate coordinates, thereby maintaining navigation capabilities for the UAV.