Haiyan Zhang

The increasing density and complexity of airport surface operations have intensified the risk of crossing conflicts between ground service vehicles and taxiing aircraft. Such interactions are characterized by strong spatiotemporal coupling, asymmetric right-of-way relationships, and stringent safety requirements, making conventional human-driven conflict avoidance highly dependent on drivers’ perception and judgment. To address this problem, this study proposes a spatiotemporal prediction-driven model predictive control (MPC) framework for autonomous ground vehicles on airport surfaces. First, the spatial interaction between the aircraft safety boundary and the vehicle service road is modeled to define the vehicle–aircraft conflict zone. Aircraft motion information is then used to predict the temporal occupancy of the conflict zone, based on which a dynamic time-window constraint is constructed to characterize the time-varying safe passage conditions for autonomous vehicles. The predicted spatiotemporal constraints are embedded into a rolling MPC framework that continuously optimizes vehicle motion while jointly considering safety, traffic efficiency, and energy consumption. Simulation results show that, compared with human-driven vehicles, the proposed method reduces average energy consumption from 1200.16 kJ to 866.67 kJ and shortens average arrival time from 43.63 s to 41.27 s. In addition, the method demonstrates effective disturbance compensation under aircraft-state uncertainty and adaptability to sequential multi-aircraft crossing scenarios.

Dynamic evaluation of airport terminal capacity is critical for efficient operations, yet it remains challenging due to the complex interplay of spatial and temporal factors. Existing approaches often handle spatial connectivity and temporal fluctuations separately, limiting their predictive power under rapidly changing conditions. Here the ST-GTNet (Spatio-Temporal Graph Transformer Network) is presented, a novel deep learning model that integrates Graph Convolutional Networks (GCNs) with a Transformer architecture to simultaneously capture spatial interdependencies among airport gates and temporal patterns in operational data. To ensure interpretability and efficiency, a feature selection mechanism guided by XGBoost and SHAP (Shapley Additive Explanations) is incorporated to identify the most influential features. This unified spatio-temporal framework overcomes the limitations of conventional methods by learning spatial and temporal dynamics jointly, thereby enhancing the accuracy of dynamic capacity predictions. In a case study at a large international airport with a U-shaped corridor terminal, the ST-GTNet delivered robust and reliable capacity forecasts, validating its effectiveness in a complex real-world scenario. These findings highlight the potential of the ST-GTNet as a powerful tool for dynamic airport capacity evaluation and management.