Artificial Intelligence and Human-Machine Interactions for Stream-based Air Traffic Flow Management

Considerable growth in air traffic has led to airspace congestion in certain regions, with the consequent need of introducing new decision support systems and flexible schemes to optimally manage the available resources, towards maximising efficiency and safety of air operations. This evolution has elicited the introduction of higher levels of automation, which can support en-route Air Traffic Flow Management (ATFM) systems to deliver a more efficient route planning and balancing demand and capacity of airspace sectors. The stream-based management paradigm has been proposed as a promising strategy to improve the efficiency of ATFM, which is selected for this study as it can also enhance the intuitiveness and interpretability of system resolutions. A clustering algorithm is proposed in this paper to automatically identify the traffic streams, addressing the need for an optimal method in stream identification. In addition, a hybrid Artificial Intelligence (AI) approach is implemented for the autonomous determination of Traffic Flow Management Initiatives (TFMI) for each stream, and thus to demonstrate the potential use of the stream-based traffic. Lastly, custom Human-Machine Interactions (HMI) are designed and prototyped to improve the ATFM operator's situational awareness and overall human-machine teaming.