EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Balancing Fairness and Efficiency in Airport Surface Trajectory Joint Optimization: An Asynchronous Guided Hierarchical Multi-Agent Reinforcement Learning Approach

Jianan Yin, Jing Shan, Peiran Qiao, Yuanyuan Ma, Wenjing Zhou

Aerospace · 06.11.2026 · 13 (11) · 1034

DOI: 10.3390/aerospace13111034 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Aerospace, online erschienen am 06.11.2026. Verfasst von Jianan Yin und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Research Program of Jiangsu, Fundamental Research Funds for the Central Universities, the Postgraduate Research & Practice Innovation Program of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the continuous increase in airport operational pressure, frequent conflicts and declining efficiency in aircraft surface taxiing have become increasingly prominent. This paper addresses the problem of aircraft conflict resolution and taxi trajectory optimization in airport surface operations by constructing a surface trajectory optimization model that incorporates airline fairness and designing a corresponding Markov decision process. On this basis, an asynchronous guided hierarchical multi-agent reinforcement learning method is proposed to achieve the joint optimization of conflict-priority determination and aircraft taxi trajectory planning through upper- and lower-level coordinated decision-making. Simulation results under the selected peak-hour scenario show that, compared with the first-come, first-served (FCFS) method, the proposed approach improves the departure sequence, waiting time, and number of turns by 40%, 23.61%, and 7.52%, respectively, while also taking into account the interests of different airlines. Further sensitivity analysis indicates that, under disturbances such as increased flight volume and random stand changes, the model still maintains a certain degree of optimization capability and robustness within the same simulation framework, although the optimization performance declines as the disturbance level increases. Algorithm comparison and ablation experiments show that the proposed method has advantages over common baseline methods in convergence speed, training stability, and final optimization performance under the reported experimental settings. The results provide preliminary evidence for the feasibility of introducing fairness constraints into airport surface trajectory optimization under peak-hour operating conditions and offer a useful reference for airport surface conflict resolution and operational optimization.

Förderung

  • Basic Research Program of Jiangsu
  • Fundamental Research Funds for the Central Universities
  • the Postgraduate Research & Practice Innovation Program of Jiangsu Province

Zitieren

APA

Yin, J., Shan, J., Qiao, P., Ma, Y., & Zhou, W. (2026). Balancing Fairness and Efficiency in Airport Surface Trajectory Joint Optimization: An Asynchronous Guided Hierarchical Multi-Agent Reinforcement Learning Approach. Aerospace, 13(11), 1034. https://doi.org/10.3390/aerospace13111034

Vancouver

Yin J, Shan J, Qiao P, Ma Y, Zhou W. Balancing Fairness and Efficiency in Airport Surface Trajectory Joint Optimization: An Asynchronous Guided Hierarchical Multi-Agent Reinforcement Learning Approach. Aerospace. 2026;13(11):1034. doi:10.3390/aerospace13111034

BibTeX
@article{Yin2026,
  author = {Yin, Jianan and Shan, Jing and Qiao, Peiran and Ma, Yuanyuan and Zhou, Wenjing},
  title = {Balancing Fairness and Efficiency in Airport Surface Trajectory Joint Optimization: An Asynchronous Guided Hierarchical Multi-Agent Reinforcement Learning Approach},
  journal = {Aerospace},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {1034},
  doi = {10.3390/aerospace13111034}
}
Kostenlos starten →