An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software
Addresses safety certification challenges for ML in automotive systems, which is incremental as it builds on existing standards.
The paper analyzes how machine learning affects the ISO 26262 safety lifecycle in automotive software and provides recommendations to adapt the standard for ML use.
Machine learning (ML) plays an ever-increasing role in advanced automotive functionality for driver assistance and autonomous operation; however, its adequacy from the perspective of safety certification remains controversial. In this paper, we analyze the impacts that the use of ML as an implementation approach has on ISO 26262 safety lifecycle and ask what could be done to address them. We then provide a set of recommendations on how to adapt the standard to accommodate ML.