Towards certifiable AI in aviation: landscape, challenges, and opportunities
Machine Learning
2024-09-16 v1 Artificial Intelligence
Abstract
Artificial Intelligence (AI) methods are powerful tools for various domains, including critical fields such as avionics, where certification is required to achieve and maintain an acceptable level of safety. General solutions for safety-critical systems must address three main questions: Is it suitable? What drives the system's decisions? Is it robust to errors/attacks? This is more complex in AI than in traditional methods. In this context, this paper presents a comprehensive mind map of formal AI certification in avionics. It highlights the challenges of certifying AI development with an example to emphasize the need for qualification beyond performance metrics.
Keywords
Cite
@article{arxiv.2409.08666,
title = {Towards certifiable AI in aviation: landscape, challenges, and opportunities},
author = {Hymalai Bello and Daniel Geißler and Lala Ray and Stefan Müller-Divéky and Peter Müller and Shannon Kittrell and Mengxi Liu and Bo Zhou and Paul Lukowicz},
journal= {arXiv preprint arXiv:2409.08666},
year = {2024}
}