ATM application-oriented Research for Artificial Intelligence (AI) for aviation

Topic description

ExpectedOutcome:

Project results are expected to contribute to the following expected outcomes.

• Environment. Project results are expected to demonstrate the positive impact of AI-based solutions on operational mitigation of aviation’s environmental impact.
• Capacity. Project results are expected to contribute to capacity by addressing AI-based human operator support tools to ensure the integration of new entrant aircraft types.
• Operational efficiency. Project results are expected to improve the operational efficiency by enabling better traffic predictions and forecasts, thus contributing to punctuality.
• Safety. Project results are expected to maintain at least the same level of safety as the current ATM system.
• Security. Project results are expected to maintain at least the same level of security as the current ATM system.

The SESAR 3 JU has identified the following innovative research elements that could be used to achieve the expected outcomes. The list is not intended to be prescriptive; proposals for work on areas other than those listed below are welcome, provided they include adequate background and justification to ensure clear traceability with the R&I needs set out in the SRIA for the AI for aviation flagship.

• Aviation/ATM AI infrastructure. AI is largely dependent on data, which is required to develop AI algorithms and to validate them. Thus, the challenge is to develop an appropriate aviation/ATM AI infrastructure and/or exploit existing ones that can capture the current and future information required to support AI-enabled applications, with the required software development processes, using robust architectures for ATC systems to provide ATCOs and pilots with a good level of confidence in automated decision-aiding tools. This includes capability development, trustworthiness, safety and airworthiness. Furthermore, there is a need to foster access to and sharing of data while looking at aspects related to data quality, data integrity, data ownership, data security, the trust framework and data governance. This element also includes the creation of an exploitation plan detailing future steps after the end of the project (R&I need: trustworthy AI powered ATM environment).
• AI-powered human–machine interactions. Moving beyond the state of the art, this element covers research on how human–machine interactions can be boosted to the highest level of automation, including through branches of AI such as reinforcement learning, explainable AI and natural language processing. The research results should demonstrate how the technology can support ATCOs in carrying out their tasks, not redefine the role of the human (e.g. demonstrate an increase in human capabilities during the execution of complex scenarios or a reduction in human workload in the execution of standard tasks (R&I need: human–AI collaboration: digital assistants).
• AI-powered co-piloting. Similarly to the research described in the previous bullet point, this element aims to investigate how AI can support pilots and reduce their workload. Research should focus, for example, on how to exploit high levels of automation to perform non-critical tasks and how the HMI should work during such operations (R&I need: human–AI collaboration: digital assistants).
• AI for complex operations. This research is about the development of AI-based human operator support tools to ensure the safe integration of new entrant aircraft types into an increasingly busy, heterogeneous and complex traffic mix (i.e. UAVs, supersonic aircraft, hybrid and fully electric aircraft) This should also cover the wider implications for other organisations and the impact on the network (R&I need: human–AI collaboration: digital assistants).
• Sustainable trajectory. This element will involve developing AI-based solutions for operational mitigation of aviation’s environmental impact, such as near-real-time network optimisation (airspace/route availability) and use (on-the-fly flight planning), in conjunction with meteorological data now-casting, which could be made possible through AI (R&I need: AI Improved datasets for better airborne operations).