Online Learning for Ground Trajectory Prediction

Areski Hadjaz (1) , Gaétan Marceau (1, 2) , Pierre Savéant (3) , Marc Schoenauer (2, 4)

1 Thales Air Systems
2 TAO - Machine Learning and Optimisation
3 Thales Research and Technology [Palaiseau]
4 MSR - INRIA - Microsoft Research - Inria Joint Centre

This paper presents a model based on an hybrid system to numerically simulate the climbing phase of an aircraft. This model is then used within a trajectory prediction tool. Finally, the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) optimization algorithm is used to tune five selected parameters, and thus improve the accuracy of the model. Incor- porated within a trajectory prediction tool, this model can be used to derive the order of magnitude of the prediction error over time, and thus the domain of validity of the trajectory prediction. A first validation experiment of the proposed model is based on the errors along time for a one-time trajectory prediction at the take off of the flight with respect to the default values of the theoretical BADA model. This experiment, assuming complete information, also shows the limit of the model. A second experiment part presents an on-line trajectory prediction, in which the prediction is continuously updated based on the current aircraft position. This approach raises several issues, for which improvements of the basic model are proposed, and the resulting trajectory prediction tool shows statistically significantly more accurate results than those of the default model.

Mots clés: Air Traffic Control; Trajectory Prediction; Hybrid System; Total-Energy Model; Black-Box Optimization; Machine Learning

Domaines: Intelligence artificielle [cs.AI]

Areski Hadjaz, Gaétan Marceau, Pierre Savéant, Marc Schoenauer. Online Learning for Ground Trajectory Prediction. SESAR 2nd Innovation Days, Nov 2012, Braunschweig, Germany. ⟨hal-00766049⟩