Objectives

In air traffic flow management (ATFM), measures are issued when traffic demand exceeds capacity usually in advance of take-off. Controllers then give different aircraft instructions to separate them when airborne. The challenges facing ATFM and air traffic control may differ and solutions to them are often developed in isolation of one another. The project aims to develop a “hyper solver” based on an advanced artificial intelligent reinforcement learning method with continuous reassessment and dynamic updates. The tool is a holistic solver from end-to-end, covering the whole process to manage density of aircraft, complexity of trajectories, interactions (potential conflict in dynamic capacity balancing timeframe) of trajectories, conflict of trajectories at medium-term and conflict of trajectories at short-term.