Deep Learning-Assisted Unmanned Aerial Vehicle Flight Data Anomaly Detection: A Review

Flight data anomaly detection is crucial for ensuring the flight safety of unmanned aerial vehicles (UAVs). By monitoring and analyzing flight data, anomalies can be detected in time to avoid potential risks. Deep learning can automatically extract complex patterns and features from data and has been widely used in UAV flight data anomaly detection in recent years. Given the lack of a comprehensive survey of research related to deep learning in UAV flight data anomaly detection, this article conducts a systematic and in-depth literature review. First, the basic concepts of UAV flight data are briefly introduced, followed by an analysis and summary of the applications of deep learning methods based on prediction and reconstruction in UAV flight data anomaly detection. Emphasis is placed on the research progress of deep learning methods based on recurrent neural network (RNN), convolutional neural network (CNN), auto-encoder (AE), and variational AE (VAE) for UAV flight data anomaly detection. Second, an in-depth analysis of the threshold calculation methods utilized in existing research is conducted and the advantages and limitations of these thresholds in practical applications are discussed. Finally, some insightful research directions are given based on the shortcomings of existing research. This work aims to provide a reference and insight for future research, inspire further studies, and jointly promote the development of this promising field.