Project TAPAS
“The main ATM future performance need is Capacity” – this statement seems to be valid no matter when you read it. However, this has been particularly true in the last two years 2018 and 2019, where ATFM delays almost doubled with respect to those observed in previous years, due not only to a lack of capacity but to an unprecedented traffic demand which was also expected to keep rising in the future (mid-term, after COVID-19 impact).
There are great expectations in Artificial Intelligence (AI) and Machine Learning (ML) technologies bringing a major breakthrough to ATM, enabling a highly automated system, which is able to deliver higher capacity. There is global interest on this matter, as clearly shown by Fly AI Report or EASA AI Roadmap, among other initiatives.
There are, however, some natural questions immediately arising, for both users and operators: Are these systems reliable? How do I know if their decision can be trusted? Is it safe? Eventually, people could ask themselves if they would fly in an aircraft controlled by an AI system. As humans, some with direct responsibility in the ANS provision and some as users, we need to understand –at different levels- an AI system to be able to trust them.
This explainability issue is a fundamental barrier for the adoption of AI/ML technologies in any domain, and in ATM in particular, due to the focus on Safety. It is also the main objective of TAPAS project: to be able to provide a set of principles and criteria which pave the way for the deployment of these technologies in ATM in a safe and trustworthy manner, bringing benefits in ATM performance. Objective that remains affordable, taking into account that COVID-19 has not had any impact in the work of the project.
