Air Traffic Flow Management (ATFM) is the problem of adjusting the traffic demand in each traffic volume using ATFM measures so that aircraft can be safely separated during the subsequent Air Traffic Control (ATC) process. On the other hand, ATC officers (ATCOs) give different aircraft heading, speed, and flight level change instructions to separate them in flight. Both ATFM and ATC problems have been subject of research during decades, however, all previous works addressed the ATFM and ATC problems independently. The project aims to develop an HyperSolver based on advanced Artificial Intelligent Reinforcement Learning method with continuous reassessment and dynamic updates, i.e. an 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.

MAHALO asks a simple but profound question: in the emerging age of Machine Learning (ML), should we be developing automation that matches human behavior (i.e., conformal), or automation that is understandable to the human (i.e., transparent)? Further, what tradeoffs exist, in terms of controller trust, acceptance, and performance? To answer these questions, MAHALO will: • Develop an individually-tuned ML system comprised of layered deep learning and reinforcement models, trained on controller performance (context-specific solutions), strategies (eye tracking), and physiological data, which learns to solve ATC conflicts; • Couple this to an enhanced en-route CD&R prototype display to present machine rationale with regards to ML output; • Evaluate in realtime simulations the relative impact of ML conformance, transparency, and traffic complexity, on controller understanding, trust, acceptance, workload, and performance; and • Define a framework to guide design of future AI systems, including guidance on the effects of conformance, transparency, complexity, and non-nominal conditions. Building on the collective experience within the team, past research, and recent advances in the areas of ML and ecological interface design (EID), MAHALO will take a bold step forward: to create a system that learns from the individual operator, but also provides the operator insight into what the machine has learnt. Several models will be trained and evaluated to reflect a continuum from individually-matched to group-average. Most recent work in areas of automation transparency, Explainable AI (XAI) and ML interpretability will be explored to afford understanding of ML advisories. The user interface will present ML outputs, in terms of: current and future (what-if) traffic patterns; intended resolution maneuvers; and rule-based rationale. The project’s output will add knowledge and design principles on how AI and transparency can be used to improve ATM performance, capacity, and safety.

Facing the air traffic growth and the challenges in balancing air traffic between geographical sectors, the air traffic control paradigm is shifting from local sector-based solutions to cross-border flow-based approaches. Such flow-centric approaches can be promising to overcome the scalability limits of geographical sectors and optimize the traffic at a regional level. Under this paradigm, this project proposes to develop a dynamic air traffic flow configuration method to assess, predict, manage, and optimize the evolving air traffic flows to enable more efficient flow-centric ATFCM and airspace management. To realize this, first, a flow-pattern extraction module will be developed to identify the major air traffic flows and to characterize the traffic flow structure. Second, with the identified traffic flow pattern, a flow monitor module will be developed to observe the evolution of major traffic flows, such as flow density, flow rate, and flow interactions, integrating as well weather and environmental impact key performance indicators. Third, with the monitored traffic flow data, a traffic flow assessment module will be designed to measure the congestion and flow/capacity imbalance in the airspace, followed by a flow prediction module to provide forecasts of the future air traffic flow features. The fifth module, traffic flow configuration, will investigate the dynamic flow management strategies, such as flow merge and split and flow regulation, based on the flow assessment/prediction outcome. This last module will allow for installation of Flow Regulation Gates to monitor flow interactions and to regulate flights according to flow capacity. An integration of these modules into a flow-centric airspace management framework can pave the way to the dynamic airspace management. Finally, all the developments will be integrated into an innovative platform to validate the concept and methods proposed by the project.

The project aims to continue the research work done in SESAR 2020 PJ 13 ERICA. It will finalize the effort for the ATM infrastructure and services and DAA regarding IFR RPAS integration in Airspace Class A to C. Also it will in an additional working package newly address the ATM infrastructure and services and DAA regarding IFR RPAS accommodation in Airspace Class D to G. Both Work Packages aim to support the full integration of RPAS into European Airspace and to address the transition between ATM and UTM airspaces.

The SEC-AIRSPACE project aims to enable a more resilient ATM, by focusing on reducing the risks of virtualization and increased data-sharing between all components of the ATM infrastructure and the relevant stakeholders. The project will enhance the state-of-the-art security risk assessment methodology(ies) currently adopted in ATM with prominent cyber security components. Further, the project will investigate the potential of applying the concept of People Analytics (PA) to increase cyber security awareness in ATM organizations. The project results will be validated and demonstrated through two realistic use cases, involving relevant stakeholders.