Thinking the Certification Process of Embedded ML-Based Aeronautical Components Using AIDGE, a French Open and Sovereign AI Platform

Filipo Perotto, Anthony Pires, Jean-Loup Farges, Youcef Bouchebaba, Mohammed Belcaid, Eric Bonnafous, Claire Pagetti, Frédéric Boniol, Xavier Pucel, Adrien Chan-Hon-tong, Stéphane Herbin, Mario Cassaro, Sofiane Kraiem

2024

Abstract

AIDGE is a novel software development platform for embedded Artificial Intelligence (AI). It is designed to import or even learn Deep Neural Networks (DNN) and generate optimized code for target hardware architectures, in a completely open, transparent, and traceable manner. The purpose is to avoid dependence on opaque and non-sovereign tools or elements, ensuring competitive performance and favoring the certification of embedded Machine Learning (ML) components. In this paper, we present the preliminary analysis on the potential benefits of using this platform in light of the rising aeronautical certification standards concerning the use of ML into critical aeronautical systems, pointing possible steps toward certification, based on the artifacts that can be automatically generated by AIDGE.

Paper Citation

in Harvard Style

Perotto F., Pires A., Farges J., Bouchebaba Y., Belcaid M., Bonnafous E., Pagetti C., Boniol F., Pucel X., Chan-Hon-tong A., Herbin S., Cassaro M. and Kraiem S. (2024). Thinking the Certification Process of Embedded ML-Based Aeronautical Components Using AIDGE, a French Open and Sovereign AI Platform. In Proceedings of the 2nd International Conference on Cognitive Aircraft Systems - Volume 1: ICCAS; ISBN 978-989-758-724-5, SciTePress, pages 64-71. DOI: 10.5220/0012965100004562

in Bibtex Style

@conference{iccas24,
author={Filipo Perotto and Anthony Pires and Jean-Loup Farges and Youcef Bouchebaba and Mohammed Belcaid and Eric Bonnafous and Claire Pagetti and Frédéric Boniol and Xavier Pucel and Adrien Chan-Hon-tong and Stéphane Herbin and Mario Cassaro and Sofiane Kraiem},
title={Thinking the Certification Process of Embedded ML-Based Aeronautical Components Using AIDGE, a French Open and Sovereign AI Platform},
booktitle={Proceedings of the 2nd International Conference on Cognitive Aircraft Systems - Volume 1: ICCAS},
year={2024},
pages={64-71},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012965100004562},
isbn={978-989-758-724-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Cognitive Aircraft Systems - Volume 1: ICCAS
TI - Thinking the Certification Process of Embedded ML-Based Aeronautical Components Using AIDGE, a French Open and Sovereign AI Platform
SN - 978-989-758-724-5
AU - Perotto F.
AU - Pires A.
AU - Farges J.
AU - Bouchebaba Y.
AU - Belcaid M.
AU - Bonnafous E.
AU - Pagetti C.
AU - Boniol F.
AU - Pucel X.
AU - Chan-Hon-tong A.
AU - Herbin S.
AU - Cassaro M.
AU - Kraiem S.
PY - 2024
SP - 64
EP - 71
DO - 10.5220/0012965100004562
PB - SciTePress