White Paper Machine Learning in Certified Systems

Delseny, Hervé; Gabreau, Christophe; Gauffriau, Adrien; Beaudouin, Bernard; Ponsolle, Ludovic; Aleçu, Lucian; Bonnin, Hugues; Beltran, Brice; Duchel, Didier; Ginestet, Jean-Brice; Hervieu, Alexandre; Ghilaine, Martinez,; Pasquet, Sylvain; Delmas, Kévin; Pagetti, Claire; Gabriel, Jean-Marc; Chapdelaine, Camille; Picard, Sylvaine; Damour, Mathieu; Cappi, Cyril; Gardès, Laurent; Grancey, Florence De; Jenn, Éric; Lefevre, Baptiste; Flandin, G.; Gerchinovitz, Sébastien; Mamalet, Franck; Albore, Alexandre

doi:10.48550/arxiv.2103.10529

Cited by 5 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Last but not least, an important aspect of planning is its interpretability, which relates to whether the method can be certified. Further investigation on the interpretation and certification [ 41 ] of machine learning based planning is needed for large-scale adoption.…”

Section: Experiments and Datamentioning

confidence: 99%

Conditional Generative Models for Dynamic Trajectory Generation and Urban Driving

Paz,

Zhang,

Xiang

et al. 2023

Sensors

View full text Add to dashboard Cite

This work explores methodologies for dynamic trajectory generation for urban driving environments by utilizing coarse global plan representations. In contrast to state-of-the-art architectures for autonomous driving that often leverage lane-level high-definition (HD) maps, we focus on minimizing required map priors that are needed to navigate in dynamic environments that may change over time. To incorporate high-level instructions (i.e., turn right vs. turn left at intersections), we compare various representations provided by lightweight and open-source OpenStreetMaps (OSM) and formulate a conditional generative model strategy to explicitly capture the multimodal characteristics of urban driving. To evaluate the performance of the models introduced, a data collection phase is performed using multiple full-scale vehicles with ground truth labels. Our results show potential use cases in dynamic urban driving scenarios with real-time constraints. The dataset is released publicly as part of this work in combination with code and benchmarks.

show abstract

Section: Experiments and Datamentioning

confidence: 99%

Conditional Generative Models for Dynamic Trajectory Generation and Urban Driving

Paz,

Zhang,

Xiang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…We chose to build our review/discussion of the literature around distinct categories of research in ML certification. These categories are identified from our examination of the content of the retrieved papers, as well as considerations brought about by the DEEL project [49]. Hence, the following categories were considered:…”

Section: Selected Taxonomymentioning

confidence: 99%

“…To help tackle scientific challenges related to the certification of ML based safety-critical systems, the DEEL (DEpendable & Explainable Learning) project 13 , which is born from the international collaboration between the Technological Research Institutes (IRT) Saint Exupéry in Toulouse (France), the Institute for Data Valorisation (IVADO) in Montreal (Canada) and the Consortium for Research and Innovation in Aerospace of Québec (CRIAQ) in Montreal (Canada), aims to develop novel theories, techniques, and tools to help ensure the Robustness of ML based systems (i.e., their efficiency even outside usual conditions of operation), their Interpretability (i.e., making their decisions understandable and explainable), Privacy by Design (i.e., ensuring data privacy and confidentiality during design and operation), and finally, their Certifiability. A white paper [49] released in 2021 introduces the challenges of certification in machine learning, to contribute to this global research effort on the certification of ML based safety-critical systems.…”

Section: Introductionmentioning

confidence: 99%

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Tambon,

Laberge,

et al. 2021

Preprint

View full text Add to dashboard Cite

Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called "safety-critical" systems such as automotive or aeronautic has proven to be very challenging, since the shift in paradigm that ML brings completely changes traditional certification approaches.Objective: This paper aims to elucidate challenges related to the certification of ML-based safety-critical systems, as well as the solutions that are proposed in the literature to tackle them, answering the question "How to Certify Machine Learning Based Safety-critical Systems?".Method: We conduct a Systematic Literature Review (SLR) of research papers published between 2015 to 2020, covering topics related to the certification of ML systems. In total, we identified 217 papers covering topics considered to be the main pillars of ML certification: Robustness, Uncertainty, Explainability, Verification, Safe Reinforcement Learning, and Direct Certification. We analyzed the main trends and problems of each sub-field and provided summaries of the papers extracted.Results: The SLR results highlighted the enthusiasm of the community for this subject, as well as the lack of diversity in term of datasets and type of ML models. It also emphasized the need to further develop connections between academia and industries to deepen the domain study. Finally, it also illustrated This work is supported by the DEEL project CRDPJ 537462-18 funded by the National Science and Engineering Research Council of Canada (NSERC) and the Consortium for Research and Innovation in Aerospace in Québec (CRIAQ), together with its industrial partners Thales Canada inc, Bell Textron Canada Limited, CAE inc and Bombardier inc.

show abstract

“…The technical report [18] published by EUROCAE and SAE joint committee in 2021 identifies gaps in the existing certification standards with respect to ML technology and discusses potential approaches to address the gaps, but without detailed information on specific standards' objectives. Another recent work [19] includes a detailed analysis of ML-based system certification challenges without proposing solutions.…”

Section: ML Overview and Related Workmentioning

confidence: 99%

“…As a result, the DO-178C traceability objectives are not achievable for an ML model. This traceability issue is one aspect of the more general ML explainability challenge [19].…”

Section: B Development Processesmentioning

confidence: 99%

Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications

Dmitriev

Schumann

Holzapfel

2021

2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC)

View full text Add to dashboard Cite

The exceptional progress in the field of machine learning (ML) in recent years has attracted a lot of interest in using this technology in aviation. Possible airborne applications of ML include safety-critical functions, which must be developed in compliance with rigorous certification standards of the aviation industry. Current certification standards for the aviation industry were developed prior to the ML renaissance without taking specifics of ML technology into account. There are some fundamental incompatibilities between traditional design assurance approaches and certain aspects of ML-based systems. In this paper, we analyze the current airborne certification standards and show that all objectives of the standards can be achieved for a low-criticality ML-based system if certain assumptions about ML development workflow are applied.

show abstract

White Paper Machine Learning in Certified Systems

Cited by 5 publications

References 0 publications

Conditional Generative Models for Dynamic Trajectory Generation and Urban Driving

Conditional Generative Models for Dynamic Trajectory Generation and Urban Driving

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications

Contact Info

Product

Resources

About