An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software

TL;DR

This paper examines how machine learning impacts automotive safety standards, specifically ISO 26262, and proposes adaptations to ensure safe implementation in driver assistance and autonomous systems.

Contribution

It analyzes the challenges ML introduces to ISO 26262 compliance and offers recommendations for standard adaptation to support safe ML integration.

Findings

ML complicates ISO 26262 safety certification

Recommendations for standard modifications to accommodate ML

Guidelines for safe ML deployment in automotive systems

Abstract

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.