Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry

2018/12/13 by Borg, Markus, Englund, Cristofer, Wnuk, Krzysztof +7 · 2 citations
#FOS: Computer and information sciences #Software Engineering (cs.SE)

paper · doi:10.48550/arxiv.1812.05389

Abstract

Deep Neural Networks (DNN) 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, e.g., safety cage architectures and simulated system test cases.

Cited by

• RE for AI in Practice: Managing Data Annotation Requirements for AI Autonomous Driving Systems
• The DevSafeOps Dilemma: A Systematic Literature Review on Rapidity in Safe Autonomous Driving Development and Operation

Related

• Deep Learning Safety Concerns in Automated Driving Perception
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Continuous Safety Verification of Neural Networks
• Practical Solutions for Machine Learning Safety in Autonomous Vehicles
• Strategy to Increase the Safety of a DNN-based Perception for HAD Systems