Richard Alligier

Richard Alligier is a lecturer and researcher at Ecole Nationale de l'Aviation Civile (ENAC) specializing in artificial intelligence applications for air traffic management. His work bridges machine learning, optimization algorithms, and trajectory prediction to address critical challenges in conflict detection and resolution for both manned and unmanned aerial systems.

• Research Focus: Trajectory prediction, conflict resolution, UAV collision avoidance, mass/thrust estimation, and uncertainty modeling
• Key Collaborations: Nicolas Durand, David Gianazza, Xavier Olive, Kim Gaume, Sarah Degaugue

His publications (2011–2024) analyze trajectory uncertainty quantification, 3D maneuver visualization, and human-aligned deconfliction strategies using ADS-B data. Notable contributions include:

• Dual-horizon collision avoidance algorithms integrating human factors
• High-confidence interval prediction frameworks
• Wind parameter extraction from flight paths
• Machine learning models for climb/descent phase optimization

Awarded the 2019 best paper in trajectory prediction, his work emphasizes operational alignment between automated systems and air traffic controller decision-making. He employs GPU acceleration, metaheuristics, and deep learning architectures while maintaining a focus on practical implementation through partnerships with ONERA and ISAE-SUPAERO.