ORCI will explore innovative AI-based solutions to help increase runway throughput using advanced automation support tools in the TMA domain. Specifically, the objective is to provide key information to Air Traffic Controllers in final approach sectors, to support informed decisions on when to issue vectoring instructions to aircraft for optimal spacing between consecutive arrivals during medium, high, very high-density and increasingly complex TMA airspace operations. To achieve this objective, the project will develop an AI model that is trained using radar surveillance data and ATC voice communications between pilots and controllers. During the project, Barcelona and Lisbon approach operations will be assessed. This will include interviews with ATCO experts from the respective ANSP partners, as well as in-depth analysis of local arrival characteristics (e.g. geometries, procedures, etc.). In addition, high amounts of radar surveillance and voice communications data will be collected and processed, to support and guide the training and testing of the AI models. The validation of the AI model will be supported by Human in the loop and Fast Time simulation techniques (using the RAMS Plus tool) to ensure that the performance of the AI model is evaluated in a realistic and controlled environment, and to get some initial human performance and safety related feedback. The successful implementation of the AI model is anticipated to optimize delivery of vectoring instructions, leading to enhanced capacity, efficiency, environmental performance, and overall improvements to arrival air traffic management that are consistent with SESAR performance targets. Additional benefits also extend to optimization of the runway throughput by reducing both ATC workload and the potential for human error. The expected solution could also be extended to incorporate the use of time-based separation for arrivals and digitally shared trajectory information coming from the flight-deck

SALSA is an exploratory research project relating to multi-source ADS-B system. A multi-source ADS-B system that combines the benefit of all possible type of relays (space, maritime, air or ground based) of ADS-B messages could provide a global surveillance system to overcome the prevailing continuous surveillance constraints in the non-radar airspace (NRA). By bringing Space based ADS-B with other sources of surveillance based on ground, air and oceanic relays, a system of system architecture is conceived; upon its benefits, new separation standards are validated through analysis using theoretical modelling for separation standard and airspace capacity, in the context of NRA. Reduction in separation minimum and in the number of standards will bring significant benefits to ATC/ATM operations with improved aircraft surveillance and airspace management. These two aspects, namely, a system-of-system concept for multi-source ADS-B architecture and analytical modelling for enhanced separation minima and airspace capacity in the context of NRA define the scope of SALSA. The analysis will also consider different scenarios of separation minima Vs. ADS-B message update rate. The study will assess the impact of performance of such a system of systems approach in the context of separation standards; it will provide an assessment of the procedural impact and impact to flight safety due to the revised minima and the system configuration. A set of recommendations to SESAR JU and other stake-holders and industry partners will be provided in order to purse the outcome of the study towards higher technology readiness level (TRL) and eventual implementation.

The scope of AI4REALNET covers the perspective of AI-based solutions addressing critical systems (electricity, railway, and air traffic management) modelled by networks that can be simulated, and are traditionally operated by humans, and where AI systems complement and augment human abilities. It has two main strategic goals: 1) to develop the next generation of decision-making methods powered by supervised and reinforcement learning, which aim at trustworthiness in AI-assisted human control with augmented cognition, hybrid human-AI co-learning and autonomous AI, with the resilience, safety, and security of critical infrastructures as core requirements, and 2) to boost the development and validation of novel AI algorithms, by the consortium and AI community, through existing open-source digital environments capable of emulating realistic scenarios of physical systems operation and human decision-making. The core elements are: a) AI algorithms mainly composed by supervised and reinforcement learning, unifying the benefits of existing heuristics, physical modelling of these complex systems and learning methods, as well as, a set of complementary techniques to enhance transparency, safety, explainability and human acceptance; b) human-in-the-loop decision making for co-learning between AI and humans, considering integration of model uncertainty, human cognitive load and trust; c) autonomous AI systems relying on human supervision, embedded with human domain knowledge and safety rules. The AI4REALNET framework will be validated in 6 uses cases driven by industry requirements, across 3 network infrastructures with common properties. The use cases are focused on critical challenges and tasks of network operators, considering strategic long-term goals, such as decarbonisation, digitalisation, and resilience to disturbances, and are formulated in a unified sequential decision problem where many AI and non-AI algorithms can be applied and benchmarked.

PEARL project aims at carrying out the SESAR performance management process, under the leadership of SESAR 3 JU. This implies to reconcile and map the performance assessments and results delivered by the R&I projects with the SESAR performance ambitions in the ATM Master Plan. To achieve this goal, PEARL Project will conduct the following activities: -A priori estimation of performance contributions from SESAR Solutions -Consolidation of performance assessments coming from SESAR Solutions to deliver PAGAR report -Provision support and guidance to Solutions through Communities of Practice (in performance domains as Operational Performance, Safety, (cyber) Security, Human Performance, Environment, CBA, Digitalisation and U-Space), as part of a Quality Assurance process -Conduct multi-SESAR Solution network impact simulations, looking for indications of cross-effects of joint deployment Complementarily, on specific request from SESAR 3 JU, PEARL project will maintain SESAR Performance Framework and related material, as well as providing support to Maturity Gates. It will also be flexible for the provision of additional ad-hoc activities, to be agreed with SESAR 3 JU.