@article{M093D38E5,
title = "Real-Time Trajectory Prediction for Urban Low-Altitude Unmanned Aerial Vehicles Based on Deep Learning Model",
journal = "The Journal of Korean Institute of Communications and Information Sciences",
year = "2025",
issn = "1226-4717",
doi = "10.7840/kics.2025.50.2.224",
author = "Da-hyun Jang, Seung-won Yoon, Tae-won Park, Hye-won Yoon, Kyu-chul Lee",
keywords = "UAV(Unmanned Aerial Vehicle), Autonomous aircraft, Trajectory Prediction, Deep Learning",
abstract = "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."
}