Publiée le 16 juin
Mission du poste
L’ENAC, École Nationale de l’Aviation Civile, est la plus importante des Grandes Écoles ou universités aéronautiques en Europe. Elle forme à un spectre large de métiers : des ingénieurs ou des professionnels de haut niveau capables de concevoir et faire évoluer les systèmes aéronautiques et plus largement ceux du transport aérien ainsi que des pilotes de ligne, des contrôleurs aériens ou encore des techniciens aéronautiques.
Ses laboratoires de recherche sont à la pointe de l’innovation et travaillent activement en coopération avec des universités internationales de haut niveau pour un transport aérien toujours plus sûr, efficace et durable.
L’ENAC est un établissement public à caractère scientifique, culturel et professionnel – grand établissement (EPSCP-GE), sous tutelle de la DGAC (Direction Générale de l’Aviation Civile), Direction du Ministère de la Transition Écologique et Solidaire. L’ENAC comprend une direction générale localisée à Toulouse et 8 sites en France.
Pour soutenir sa dynamique en faveur de la promotion de la diversité, l’ENAC facilite l’accueil et l’intégration des travailleurs en situation de handicap.
This PhD will investigate how quantum-AI trajectory optimisation outputs can be made understandable, trustworthy, and operationally useful for air traffic controllers. Embedded in the NEXT-QCM project at ENAC, the research will focus on explainable quantum machine learning, hybrid quantum-classical simulation, and human-centred validation for conflict resolution and trajectory optimisation in Air Traffic Management. The work will begin by identifying controller information needs through interviews and operational scenario analysis. It will then develop visual explanation methods for quantum-generated trajectory sets, including density maps, uncertainty indicators, candidate trajectory clusters, and trade-off visualisations. These explanations will be integrated into a hybrid quantum-classical simulation loop where quantum-generated solutions are evaluated and filtered through classical ATM simulation. The resulting prototype will be assessed with ATM experts using human-in-the-loop methods, measuring trust, usability, workload, transparency, and operational acceptance. The PhD will contribute a methodological framework and design guidelines for explainable quantum-AI decision support in safety-critical ATM contexts, directly supporting ENAC’s role in NEXT-QCM on operational data collection, explainable QML, simulation, ethics, and validation.
Research objectives
Quantum and quantum-inspired methods may offer new ways to explore large trajectory solution spaces, but their operational usefulness in ATM depends on whether their outputs can be translated into understandable, actionable, and trustworthy decision support for human operators. The PhD will address the following problem: How can outputs from quantum or hybrid quantum-classical trajectory optimisation models be represented, explained, and validated so that air traffic controllers can understand candidate solutions, assess trade-offs, and maintain effective human oversight in safety-critical ATM operations?
The PhD will follow a human-centred and iterative methodology combining ATM scenario analysis, explainable quantum-AI modelling, hybrid simulation, and expert validation. First, representative conflict-resolution and trajectory-optimisation scenarios will be defined through controller interviews, analysis of operational conflict cases, simulated trajectory generation, and the use of authentic trajectory data when available, in line with ENAC’s role in NEXT-QCM data collection. Second, the research will develop explanation methods for quantum-generated candidate trajectories, focusing on visual representations such as trajectory density maps, conflict-risk indicators, uncertainty displays, trade-off comparisons, and counterfactual explanations. Third, these explanations will be integrated into a hybrid quantum-classical simulation loop, where classical ATM simulation defines constraints, quantum or quantum-inspired models generate candidate solutions, and classical evaluation filters the results for operational relevance. Finally, the approach will be assessed with ATM experts through interviews, workshops, questionnaires, and human-in-the-loop experiments, using ENAC’s ACHIL platform where appropriate to evaluate transparency, trust, workload, usability, safety perception, and acceptance.
