TY  - JOUR
T1  - Real-Time Trajectory Prediction for Urban Low-Altitude Unmanned Aerial Vehicles Based on Deep Learning Model
AU  - Jang, Da-hyun 
AU  - Yoon, Seung-won 
AU  - Park, Tae-won 
AU  - Yoon, Hye-won 
AU  - Lee, Kyu-chul 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2025
DA  - 2025/1/1
DO  - 10.7840/kics.2025.50.2.224
KW  - UAV(Unmanned Aerial Vehicle)
KW  - Autonomous aircraft
KW  - Trajectory Prediction
KW  - Deep Learning
AB  - The continuous increase in global air traffic and autonomous aircraft development have made accurate trajectory prediction crucial for safe air traffic management. This study proposes a method for predicting UAV trajectories based on a deep learning model. Specifically, we propose a prediction model based on the GRU (Gated Recurrent Unit) architecture, which is well-suited for time series prediction. We applied look_back and forward_length to assess model performance across different ranges. Furthermore, to validate the performance of the proposed model, we conducted comparative experiments with RNN (Recurrent Neural Network) and LSTM (Long Short-Term Memory) models. The experimental results showed that our model achieved the best prediction performance with an RMSE of 0.0037 and demonstrated real-time prediction capability.