Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry
- 10.2991/jase.d.190131.001How to use a DOI?
- Deep learning; Safety-critical systems; Machine learning; Verification and validation; ISO 26262
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. Published by Atlantis Press SARL.
- Open Access
- This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - JOUR AU - Markus Borg AU - Cristofer Englund AU - Krzysztof Wnuk AU - Boris Duran AU - Christoffer Levandowski AU - Shenjian Gao AU - Yanwen Tan AU - Henrik Kaijser AU - Henrik Lönn AU - Jonas Törnqvist PY - 2019 DA - 2019/01/31 TI - Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry JO - Journal of Automotive Software Engineering SP - 1 EP - 19 VL - 1 IS - 1 SN - 2589-2258 UR - https://doi.org/10.2991/jase.d.190131.001 DO - 10.2991/jase.d.190131.001 ID - Borg2019 ER -