EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An improved transformer‐based model for long‐term 4D trajectory prediction in civil aviation

Aofeng Luo, Yuxing Luo, Hong Liu, Wenchao Du, Xiping Wu, Hu Chen, Hongyu Yang

IET Intelligent Transport Systems · 2024-09 · 18 (9) · 1588-1598

DOI: 10.1049/itr2.12530 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Intelligent Transport Systems, online erschienen am 24.06.2024. Verfasst von Aofeng Luo und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Four‐dimensional trajectory prediction is a crucial component of air traffic management, and its accuracy is closely related to the efficiency and safety of air transportation. Although long short‐term memory (LSTM) or its variants have been widely used in recent studies, they may produce unacceptable results in long‐term prediction due to the iterative output that accumulates error. To address this issue, a transformer‐based long‐term trajectory prediction model is proposed here, which utilizes the self‐attention mechanism to extract time series features from historical trajectory data. For long‐term prediction scenarios, we a trajectory stabilization module is introduced to ensure the stationarity of the time series for better predictability. Additionally, the transformer output strategy is improved to generate the prediction sequence by a single step instead of serial dynamic decoding, thus effectively enhancing the precision and inference speed. The proposed model is validated using real data obtained from China's Southwest Air Traffic Management Bureau. The experimental results demonstrate that this model outperforms the benchmark model. Further ablation experiments and visualizations are performed to analyze the impact of trajectory stabilization and one‐step inference strategy.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Luo, A., Luo, Y., Liu, H., Du, W., Wu, X., Chen, H., & Yang, H. (2024). An improved transformer‐based model for long‐term 4D trajectory prediction in civil aviation. IET Intelligent Transport Systems, 18(9), 1588-1598. https://doi.org/10.1049/itr2.12530

Vancouver

Luo A, Luo Y, Liu H, Du W, Wu X, Chen H, et al. An improved transformer‐based model for long‐term 4D trajectory prediction in civil aviation. IET Intelligent Transport Systems. 2024;18(9):1588-1598. doi:10.1049/itr2.12530

BibTeX
@article{Luo2024,
  author = {Luo, Aofeng and Luo, Yuxing and Liu, Hong and Du, Wenchao and Wu, Xiping and Chen, Hu and Yang, Hongyu},
  title = {An improved transformer‐based model for long‐term 4D trajectory prediction in civil aviation},
  journal = {IET Intelligent Transport Systems},
  year = {2024},
  volume = {18},
  number = {9},
  pages = {1588--1598},
  doi = {10.1049/itr2.12530}
}
Kostenlos starten →