Over a century has passed since humans took to commercial flying and the pursuit of safe operations continues today. The need to better understand the human factor as part of sociotechnical systems has become clear in recent times. In this paper, we focus on human coordination through a case study of a runway collision at Tenerife airport in 1977. We formalize coordination using theoretical frameworks and mathematically model it using agent-based techniques. For validation, we use LEADSTO simulations and perform a variability analysis. We identify coordination mechanisms that play an important role in identifying and repairing loss of common ground. Ultimately, we aim to add to the growing body of knowledge pertaining to the understanding of human cognition in complex sociotechnical systems in order to support resilient system operations.

AbstractCoordinating the movements of aircraft along the surface of busy airports is a complex task, involving both humans and machines. In response to the interrelated challenges of ever-increasing demand, emission reduction, and sustaining safety levels, technological advances are emerging which, in turn, necessitate novel concepts of operations (ConOps). To this end, diverse operational concepts with varying technological aspects, level of automation, and degree of control centralisation could potentially offer a solution. However, before such innovative ConOps are matured to be deployable at real-world airports, extensive evaluation based on computational modelling is necessary. To enable such detailed modelling and analysis of the large variety of concepts for next-generation airport surface movement operations, this paper proposes a generalised architecture based on the hierarchical-distributed multi-agent system modelling paradigm. We illustrate the generalised architecture by providing a specific model instance for a ConOps based on centralised planning and distributed, fully-automated control. As essential part of this model, we introduce the novel Multi-Agent Motion Planning on Airport Surfaces (AS-MAMP) algorithm to represent the decision-logic for coordinating all ground movements. The two-level solver builds on prominent prioritised planners such as Priority-Based Search (PBS) and its variant Greedy PBS. As current low-level solvers were insufficient to plan realistic 4D trajectories for ground movements, we developed the new Safe Interval Motion Planning (SIMP) algorithm. By defining activity sequences per agent, SIMP plans trajectories across the operational processes during taxiing such as pushback, tug coupling/decoupling, and engine-start. The motions of aircraft and ground vehicles are based on finite acceleration, and avoid dynamic obstacles in continuous space and time, necessitating to define states with feasible motion intervals. We benchmark AS-MAMP by varying its high-level prioritisation scheme, and exchanging SIMP with two existing low-level solvers, namely the Safe Interval Path Planning (SIPP) and A* algorithms. Based on scenarios on both a synthetic and a real-world airport layout, we demonstrate the efficacy of AS-MAMP to plan safe and efficient 4D trajectories. Moreover, we show that the model is able to handle runway throughput levels that match or exceed those of large European airports.

Flight diversions are rare but high-impact events in aviation, making their reliable prediction vital for both safety and operational efficiency. However, their scarcity in historical records impedes the training of machine learning models used to predict them. This study addresses this challenge by proposing a generative augmentation framework for imbalanced aviation tabular records. The principal contribution lies in the design of a composite optimisation objective specifically tailored to flight data, which integrates four complementary quality dimensions into a single score used to guide automated hyperparameter search via the Tree-structured Parzen Estimator (TPE) algorithm: realism, statistical similarity, fidelity, and predictive utility. These dimensions were selected and defined to reflect the operational and statistical requirements specific to aviation records, and were complemented by two descriptive evaluation dimensions, diversity and operational validity, forming a six-stage assessment framework. The composite objective was then used to tune three deep generative models, namely Tabular Variational Autoencoder (TVAE), Conditional Tabular Generative Adversarial Network (CTGAN), and CopulaGAN, with Gaussian Copula (GC) serving as a statistical baseline. Results show that optimised models substantially outperform their default counterparts across all six assessment dimensions, and that augmentation with the resulting synthetic data improves diversion prediction compared to training on real data alone. These findings demonstrate that domain-adapted multi-objective optimisation is an effective strategy for generative augmentation of rare events in aviation, with applicability to other imbalanced tabular prediction tasks.

This paper discusses SESAR’s Auto-Steer Taxi at Airport (ASTAIR) project, which seeks to advance airport ground operations including engine-off taxiing to move towards sustainable airports. The ASTAIR concept integrates human–AI teaming to optimize aircraft movement from gates to runways, with the primary objectives of improving predictability, efficiency, and environmental sustainability at large airports. Building on previous initiatives such as SESAR’s AEON, ASTAIR brings high-level automation to tasks like autonomous taxiing and vehicle routing. The system assists operators by calculating conflict-free routes for vehicles and dynamically adjusting operations based on real-time data. Based on workshops with several stakeholders, we describe the operational challenges involved in implementing ASTAIR, including managing parking stand availability and adapting to unforeseen events. A significant challenge highlighted is the human–automation partnership, where AI plays a supportive role but humans retain control over critical decisions, particularly in cases of system failure. The need for clear and consistent collaboration between AI and human operators is emphasized to ensure safety, efficiency, and improved compliance with take-off schedules, which in turn facilitates in-flight optimization.

Both EASA and SESAR JU define a vision and roadmap towards an autonomous air traffic management system. Furthermore, past and ongoing SESAR JU projects investigate how to increase the efficiency and predictability of current operations by means of automation. In this paper, we explore the operational implications that result from fully-automated airport surface movement operations modelled with high realism. A hierarchical multi-agent system model was developed to coordinate and control all movements on the airport surface. It comprises the Airport Operations Agent to handle the flight schedule and runway configuration, the Routing Agent to compute conflict-free trajectories, and the Guidance Agents to instruct and monitor the Aircraft Agents while these execute the planned routes. The model incorporates the decisive processes and elements of airport surface movement operations such as pushback, engine-start, inbound and outbound holding, compliance to CTOT-slots, and wake turbulence separation for takeoffs. To compute conflict-free trajectories for all taxiing agents, we tailored and extended state-of-the-art multi-agent motion planning algorithms: the two-level routing algorithm combines Priority-Based Search (PBS) with Safe Interval Path Planning (SIPP). We defined different sizes of aircraft, accounted for a minimal safety distance between them, and calibrated their speed limits in curves with historic ADS-B data. Using the real-world flight schedules of two of the busiest days at Amsterdam Airport Schiphol, including different runway configurations, we examine the performance of the autonomous taxiing system with respect to the historic operations. For the considered simulation conditions, we show that the MAS yields 30% lower taxi times that vary less and are more predictable and increases runway capacity.

The increasing adoption of synthetic data in aviation research offers a promising solution to data scarcity and confidentiality challenges. This study investigates the potential of generative models to produce realistic synthetic flight data and evaluates their quality through a comprehensive four-stage assessment framework. The need for synthetic flight data arises from their potential to serve as an alternative to confidential real-world records and to augment rare events in historical datasets. These enhanced datasets can then be used to train machine learning models that predict critical events, such as flight delays, cancellations, diversions, and turnaround times. Two generative models, Tabular Variational Autoencoder (TVAE) and Gaussian Copula (GC), are adapted to generate synthetic flight information and compared based on their ability to preserve statistical similarity, fidelity, diversity, and predictive utility. Results indicate that while GC achieves higher statistical similarity and fidelity, its computational cost hinders its applicability to large datasets. In contrast, TVAE efficiently handles large datasets and enables scalable synthetic data generation. The findings demonstrate that synthetic data can support flight delay prediction models with accuracy comparable to those trained on real data. These results pave the way for leveraging synthetic flight data to enhance predictive modeling in air transportation.

Both EASA and SESAR JU have outlined roadmaps towards an autonomous air traffic management system. Their long-term vision aligns with our previous work in which we studied the operational consequences of fully automated airport surface movement operations (ASM Ops) using a multi-agent system model that conducts multi-agent motion planning. However, such an automated system needs to be placed in a sociotechnical context, in which human operators and system users would be able to interact with automation in a seamless way. In the context of the SESAR JU project”ASTAIR - Auto-Steer Taxi at Airport”, workshops and interviews were conducted with human operators to identify operational requirements and preferred interactions with automated systems. In this paper, we explore how the requirements can be modelled and implemented in the multi-agent system for automated planning of ASM Ops to enable interactions with human operators. To this end, we present a conceptual agent-based framework for human-automation teaming in ASM Ops, introduce interactive tools for ATCOs to engage with the system, and showcase these interactions through a series of use cases derived from the workshops as well as historic data. Illustrated through the interactions of a fictitious Air Traffic Controller at Amsterdam Airport Schiphol, we demonstrate their practical implementation and broader aspects of such interactions in next-generation ASM Ops.

The increasing demand and complexity of air traffic management (ATM) systems necessitate significant advancements in automation to ensure safety and efficiency. Artificial intelligence (AI) and machine learning (ML) are emerging as promising solutions to manage this growing complexity, offering enhanced decision-making and predictive capabilities. However, the effectiveness of ML models in ATM heavily relies on the availability of extensive, high-quality data. In many cases, such data is scarce or incomplete, which presents a major barrier for training robust models. Synthetic data generation (SDG) is a viable solution to address this, enabling the creation of realistic datasets that unlock the ML value proposition. The Terminal Maneuvering Area (TMA) is a crucial segment of airspace characterized by high traffic density and diverse trajectory types, necessitating granular data to model these scenarios accurately. The main research objective of this work was to investigate the applicability of TimeGAN in generating synthetic 4-dimensional aircraft landing trajectories capable of capturing traffic patterns in this airspace, helping to analyze airspace constraints and delay propagation. The resulting synthetic trajectories were evaluated in terms of data diversity, fidelity and usefulness. The main challenge identified during the research was the imbalance in data classes, which affected the models’ ability to accurately capture data patterns, particularly in less frequent scenarios. Generating synthetic data based on separate groupings showed promise in addressing these imbalances, although this approach was sensitive to the designation of groups. This work proves the capability of TimeGAN in generating diverse, realistic trajectories that are difficult to differentiate from real historical data.

Airport terminals are complex sociotechnical systems, in which humans interact with diverse technical systems. A natural way to represent them is through agent-based modeling. However, this method has two drawbacks: it entails a heavy computational burden and the emergent properties are often difficult to analyze. The purpose of our research is therefore to accurately abstract and explain the dynamics of airport terminal operations by means of computationally efficient and interpretable surrogate models, based on an existing detailed agent-based simulation model. We propose a methodology consisting of two stages. Stage I involves the development of faithful surrogates. A sample is collected according to an active learning strategy, upon which Gaussian process regression, higher-order polynomials, gradient boosting, and random forests are fitted. Stage II then applies state-of-the-art techniques from the emerging field of explainable artificial intelligence to interpret and understand these models. Both model-agnostic and model-specific methods are considered, and their results are synthesized in order to explain the emergent properties. We prove the efficacy of this approach by conducting two case studies on AATOM, an existing Agent-based Airport Terminal Operations Model. The first case study examines the total expenditure on discretionary activities, such as shopping and dining. A combination of poor staffing strategies and high occupancy rates on certain flights was found to disrupt the terminal journey of passengers on subsequent flights. As a result of these knock-on phenomena, less free time is left for discretionary activities, which has a negative effect on the total expenditure. The second case study examines the throughput of security checkpoints. While throughput increases with passenger numbers, a clear point was observed where the checkpoint reaches its maximum capacity. This leads to longer queues and therefore higher waiting times. It even goes so far as to put passengers at risk of missing their flight, especially with poor staffing strategies. Altogether, we clearly observed the preservation of emergent phenomena in surrogate models, and conclude that their combination with interpretable machine learning is an effective way to explain the dynamics of complex sociotechnical systems.