AUTHOR=Luettig Bastian , Akhiat Yassine , Daw Zamira 

TITLE=ML meets aerospace: challenges of certifying airborne AI

JOURNAL=Frontiers in Aerospace Engineering

VOLUME=Volume 3 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/aerospace-engineering/articles/10.3389/fpace.2024.1475139

DOI=10.3389/fpace.2024.1475139

ISSN=2813-2831

ABSTRACT=Artificial Intelligence (AI) technologies can potentially revolutionize the aerospace industry with applications such as remote sensing data refinement, autonomous landing, and dronebased agriculture. However, safety concerns have prevented the widespread adoption of AI in commercial aviation. Currently, commercial airplanes do not incorporate AI components, even in entertainment or ground systems. This paper explores the intersection of AI and aerospace, focusing on the challenges of certifying AI for airborne use, which may require a new certification approach. We identify common AI methods for aerospace applications and address the issue from a certification standpoint, highlighting where existing standards fall short and from a machine learning perspective, outlining required methods and open research questions. Additionally, we review current efforts to certify AI, applying the proposed development processes by the EASA and Overarching Properties to a case study of a system for automated peripheral detection (ADIMA).