Learning Probabilistic Trajectory Models of Aircraft in Terminal Airspace from Position Data
This addresses the need for improved collision avoidance and safety analysis in aeronautical systems, though it is incremental as it builds on existing trajectory modeling approaches.
The paper tackled the problem of predicting aircraft motion in terminal airspace by developing a probabilistic generative model from historical radar data, resulting in realistic trajectories, accurate predictions, and efficient training and inference.
Models for predicting aircraft motion are an important component of modern aeronautical systems. These models help aircraft plan collision avoidance maneuvers and help conduct offline performance and safety analyses. In this article, we develop a method for learning a probabilistic generative model of aircraft motion in terminal airspace, the controlled airspace surrounding a given airport. The method fits the model based on a historical dataset of radar-based position measurements of aircraft landings and takeoffs at that airport. We find that the model generates realistic trajectories, provides accurate predictions, and captures the statistical properties of aircraft trajectories. Furthermore, the model trains quickly, is compact, and allows for efficient real-time inference.