Toward the certification of safety-related systems using ML techniques: the ACAS-Xu experience

Overview & Synopsis

In the context of the use of Machine Learning (ML) techniques in the development of safety-critical applications for both airborne and ground aeronautical products, this paper proposes elements of reasoning for a conformity to the future industrial standard. Indeed, this contribution is based on the EUROCAE WG-114/SAE G-34 ongoing standardization work that will produce the guidance to support the future certification/approval objectives. The proposed argumentation is structured using assurance case patterns that will support the demonstration of compliance with assurance objectives of the new standard. At last, these patterns are applied to the ACAS-Xu use case to contribute to a future conformity demonstration using evidences from ML development process outputs. Disclaimer: This paper is based on the EUROCAE WG-114/SAE G-34 standardization results at the time of the writing. Though some of the authors are active members of the working group, it is a free interpretation of the current draft work and only reflects the authors' view. As the working group has not published any released outcomes yet, some parts of the described argumentation may have to be modified in the future to conform to the final standard objectives.