Pan Weijun, Liang Ruihan, Wang Yuhao, Song Dajiang, Yin Zirui
Flight Technology and Flight Safety Research Base of the Civil Aviation Administration of China, Civil Aviation Flight University of China, Guanghan 618307, China.
College of Air Traffic Management, Civil Aviation Flight University of China, Guanghan 618307, China.
Sensors (Basel). 2025 Mar 25;25(7):2052. doi: 10.3390/s25072052.
Remote tower technology is an important development direction for air traffic control to reduce the construction and operation costs of small or remote airports. However, its digital and virtualized working environment poses new challenges to controllers' situational awareness (SA). In this study, a dataset is constructed by collecting eye-tracking (ET) and heart rate variability (HRV) data from participants in a remote tower simulation control experiment. At the same time, probe questions are designed that correspond to the SA hierarchy in conjunction with the remote tower control task flow, and the dataset is annotated using the scenario presentation assessment method (SPAM). The annotated dataset containing 25 ET and HRV features is trained using the LightGBM model optimized by a Tree-structured Parzen Estimator, and feature selection and model interpretation are performed using the SHapley Additive exPlanations (SHAP) analysis. The results show that the TPE-LightGBM model exhibits excellent prediction capability, obtaining an RMSE, MAE and adjusted R of 0.0909, 0.0730 and 0.7845, respectively. This study presents an effective method for assessing and predicting controllers' SA in remote tower environments. It further provides a theoretical basis for understanding the effect of the physiological state of remote tower controllers on their SA.
远程塔台技术是空中交通管制的一个重要发展方向，旨在降低小型或偏远机场的建设和运营成本。然而，其数字化和虚拟化的工作环境给管制员的态势感知（SA）带来了新的挑战。在本研究中，通过收集远程塔台模拟控制实验参与者的眼动追踪（ET）和心率变异性（HRV）数据构建了一个数据集。同时，结合远程塔台控制任务流程设计了与SA层次结构相对应的探测问题，并使用情景呈现评估方法（SPAM）对数据集进行标注。使用由树结构帕曾估计器优化的LightGBM模型对包含25个ET和HRV特征的标注数据集进行训练，并使用夏普利值加法解释（SHAP）分析进行特征选择和模型解释。结果表明，TPE-LightGBM模型具有出色的预测能力，RMSE、MAE和调整后的R分别为0.0909、0.0730和0.7845。本研究提出了一种评估和预测远程塔台环境中管制员SA的有效方法。它进一步为理解远程塔台管制员的生理状态对其SA的影响提供了理论依据。
