This proposal describes a series of activities that will support the successful delivery of the TRA conference in Dublin in 2024. A consortium has been assembled that addresses all the key requirements of the call: • They represent the key transport modes with at least 2 partners active in road, rail, waterborne, aviation and cross-modal. • The partners are all active in European research and have the reach to promote the conference across Europe. • The partners have a long history of delivering high quality researcher competitions where Europe’s research leaders are recognised. The partners will work with key stakeholders to ensure the conference themes support European policies. The proposal also has the full support of the Irish Minister for Transport and this will ensure the full support of relevant Irish agencies. The partners will work together to deliver a conference that builds on the success of previous TRA conferences and provide a forum that will allow the key actors in the transport sector come together to develop solutions for society’s needs.

BEST will determine how semantic technologies can be used effectively to maximise the benefits of adopting SWIM, one of the major results of SESAR. SWIM offers an “information sharing” approach to ATM information management and its adoption offers advantages for better situational awareness and information management. But the full benefits of SWIM can only be achieved if advanced support can be provided for developing smart SWIM-based applications that manage information effectively, and semantic technologies offer a promising way to do that. BEST identifies a set of focused research questions about how to exploit semantic technologies in a practical way in an ATM setting, and will produce concrete results that help address these. The project will experiment with use of semantic technologies with several use cases, and build on that experience to produce guidelines (aimed at practitioners) about how to use ontologies in flexible ways to describe meta-data, and how these can be used in innovative yet scalable ways. BEST envisages use of multiple modular ontologies to maximise flexibility and applicability to specific application scenarios, but within a framework where compliance with the wider requirements of SWIM and the SESAR AIRM can be assured. This involves both technical compliance testing and governance aspects. While BEST is primarily a research-oriented project, it is also designed to ensure relevance to and suitability for ATM operations, through project activities and the involvement of a Reference Group of key stakeholders. The consortium includes a mixture of research and industrial partners (including one SME), all with extensive ATM experience. Several project partners have had leading roles in AIRM and SWIM work in SESAR, but some partners are new to SESAR and offer “new blood”. The consortium also provides leading expertise on semantic technologies. The project duration will be 24 months, with a requested funding of just under 600 K€.

Aviation is a vital industrial sector of Europe’s society and economy. For several historical reasons the economic activities in this field are unevenly distributed across Europe. Statistics show that also the R&D effort, which always comes along with the aviation, mirrors this allocation. On one hand, there are countries and regions featuring low involvement in aviation research and also low participation in the EU Framework Programmes; on the other – some regions are heavily involved in aviation R&D and are origin of wealth and prosperity. RADIAN is a multi-step project which intends to overcome this misbalance by identification of barriers for international collaboration in aviation research at EU level and by subsequent development and verification of solutions and measures on level of the European regions. The initial step is to assess the impact of regional, national and international environment on aviation actors. An impact is considered to become a “barrier” in case it has a detrimental nature or significantly differs from the pan-European average. By systematically comparing single impact scenarios for various actors located in different European regions, barriers for cooperation will be identified. Having this verified knowledge, 12 target regions are identified to derive, verify and execute tailored activity plans aiming at the enhancement of the actor’s ability to cooperate by reducing the disadvantageous impact or by the advancement of actor’s own assets, knowledge and abilities. Another field of work of RADIAN is a self-sustaining collaboration platform which acts as a host for transnational exchange. The platform aims at becoming a live portal, for providing personalised information related to the users’ interests such as open calls, available funding schemes, recent advancements etc.

The goal of the project is to enable human-machine collaboration by using an artificial situational awareness system which is enabling AI to anticipate and respond to human needs by understanding human intent and goals. While humans are extensively trained to understand the capabilities, limitations, and functionality of the machines they are using, further improvements in human-machine collaboration are currently hindered by lack of awareness of human's intent on the side of machines. The project will develop and test an AI Assistant Application providing adaptable human-centric support to enhance air traffic controller's (ATCO) performance and to reduce ATCO’s workload despite high task complexity. This will be achieved by development of human-machine collaboration environment that relies on recognition of ATCO intent, ATCO situation awareness (compared to machine situation awareness) and ATCO mental load. ATCO's intent will be analysed by tracking their attention and human-machine interactions and comparing them to the tasks that need solving as assessed by the artificial situational awareness system. Adaptable support will then be provided either in solving the task they are currently focused on or solving an unrelated task autonomously. This will allow ATCOs to maintain their skills and expertise while preventing a shift towards supervisory control that has been demonstrated to undermine human capability to take-over in situations with degraded automation. A goal of the adaptable and human-aware system is to maintain ATCOs in an active role, to train their skills and expertise on the job while selectively using higher levels of automation to augment capacity. ATCOs are supported in their tasks rather than substituted by automation. It is expected that ATCOs can handle high-complexity scenarios when assisted by an attention-aware support system. ATCO workload is expected to decrease with the use of support functions.

This proposal addresses the topic “Digitalisation and Automation principles for ATM”. Automation is one of the most promising solutions for the capacity problem, however, to implement advanced automation concepts it is required that the AI and human are able to share the situational awareness. Exploring the effect of, and opportunities for, distributed human-machine situational awareness in en-route ATC operations is one of the main objectives of this project. Instead of automating isolated individual tasks, such as conflict detection or coordination, we propose building a foundation for automation by developing an intelligent situationally-aware system. Sharing the same team situational awareness among ATCO team members and AI will enable the automated system to reach the same conclusions as ATCOs when confronted with the same problem and to be able to explain the reasoning behind those conclusions. The challenges of transparency and generalization will be solved by combining machine learning with reasoning engine (including domain-specific knowledge graphs) in a way that emphasizes their advantages. Machine learning will be used for prediction, estimation and filtering at the level of individual probabilistic events, an area where it has so far shown great prowess, whereas reasoning engine will be used to represent knowledge and draw conclusions based on all the available data and explain the reasoning behind those conclusions. We will explore to what extent it is possible to deduce machine learning false estimates and how resilient such system is to failure. In this way, the artificial situational awareness system will be the enabler of future advanced automation based on machine learning.