Research Information System
JOURNAL OF SUPERCOMPUTING, vol.81, no.1, 2025 (SCI-Expanded)
Real-time aircraft tracking is a critical component of aircraft flight testing. The data flowing from the aircraft to the ground control center must be real-time and uninterrupted. However, ground control systems often can cause disconnection with the aircraft, leading to tracking challenges. This study first presents a brief survey of real-time aircraft tracking systems (ATS) and then proposes DeepAT, a deep learning-based ATS for real-time three-dimensional prediction of the aircraft's next location. The proposed DeepAT model provides uninterrupted real-time data tracking by employing an encoder-decoder GRU model to predict the next location of the aircraft. Thus, in case of any disconnection, the tracking of the aircraft is ensured. DeepAT model is evaluated using real flight test sensor data collected through a telemetry system. Experimental evaluations are performed for two structurally different aircraft models, one being a highly maneuverable fixed-wing aerobatic/training aircraft and the other a tactical unmanned aerial vehicle. The efficiency and superiority of the proposed method are demonstrated by comparing it with state-of-the-art methods. The results show that DeepAT outperforms existing methods by providing more accurate predictions of the next location of the aircraft.