NEXT-QCM · TOWARDS EXPLAINABLE QUANTUM AI SOLUTIONS FOR NEXT -GENERATION TRAJECTORY OPTIMISATION

Quantum computing has emerged as a disruptive paradigm with transformative potential for Air Traffic Management (ATM), where safe separation of aircraft, fuel efficiency, and real-time adaptability present highly complex, NP-hard optimisation challenges. Even a small number of aircraft can generate vast decision spaces that are unsolvable in polynomial time. Building on the SESAR JU–funded ARTIMATION project, which applied explainable AI and genetic algorithms for pairwise conflict resolution, this study explores the role of quantum computing in enabling scalable, real-time trajectory optimisation. The NEXT-QCM framework integrates quantum optimisation and Quantum Machine Learning (QML) to evaluate exponentially large sets of routing alternatives in parallel, offering conflict-free, fuel-efficient, and sustainable solutions. Four core innovations underpin the approach: (1) global optimisation across entire sectors or networks, balancing safety, efficiency, and environmental impact; (2) real-time adaptability, using quantum simulators such as ColibrITD’s MPQP to reconfigure trajectories as new data arrive; (3) quantum-enhanced optimisation via QML to accelerate model learning and improve computational efficiency; and (4) explainable QML (XQML) to enhance interpretability and build controller trust. By leveraging advanced encoding, noise mitigation, and error-correction techniques, NEXT-QCM aims to deliver a proof-of-concept system validated through realistic field cases. This exploratory research demonstrates how quantum computing can move ATM from sequential, rule-based conflict resolution toward massively parallel, bias-aware, and sustainable airspace management.