Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive IndustryShow others and affiliations
2019 (English)In: Journal of Automotive Software Engineering, ISSN 2589-2258, Vol. 1, no 1, p. 1-19Article in journal (Refereed) Published
Abstract [en]
Deep neural networks (DNNs) will emerge as a cornerstone in automotive software engineering. However, developing systems with DNNs introduces novel challenges for safety assessments. This paper reviews the state-of-the-art in verification and validation of safety-critical systems that rely on machine learning. Furthermore, we report from a workshop series on DNNs for perception with automotive experts in Sweden, confirming that ISO 26262 largely contravenes the nature of DNNs. We recommend aerospace-to-automotive knowledge transfer and systems-based safety approaches, for example, safety cage architectures and simulated system test cases.© 2019 The Authors.
Place, publisher, year, edition, pages
Paris: Atlantis Press, 2019. Vol. 1, no 1, p. 1-19
Keywords [en]
Deep learning, Safety-critical systems, Machine learning, Verification and validation, ISO 26262
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:hh:diva-41108DOI: 10.2991/jase.d.190131.001OAI: oai:DiVA.org:hh-41108DiVA, id: diva2:1375200
Funder
VinnovaKnowledge Foundation
Note
Funding details: Thanks go to all participants in the SMILE workshops, in particular Carl Zandén, Michaël Simoen, and Konstantin Lindström. This work was carried out within the SMILE and SMILE II projects financed by Vinnova, FFI, Fordonsstrategisk forskning och innovation under the grant numbers: 2016-04255 and 2017-03066. We would like to acknowledge that this work was supported by the KKS foundation through the S.E.R.T. Research Profile project at Blekinge Institute of Technology.
2019-12-042019-12-042019-12-04Bibliographically approved