Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262

By Rick Salay, Krzysztof Czarnecki. 2018

75 citations recorded by the source corpus.

The use of machine learning (ML) is on the rise in many sectors of software development, and automotive software development is no different. In particular, Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) are two areas where ML plays a significant role. In automotive development, safety is a critical objective, and the emergence of standards such as ISO 26262 has helped focus industry practices to address safety in a systematic and consistent way. Unfortunately, these standards were not designed to accommodate technologies such as ML or the type of functionality that is provided by an ADS and this has created a conflict between the need to innovate and the need to improve safety. In this report, we take steps to address this conflict by doing a detailed assessment and adaption of ISO 26262 for ML, specifically in the context of supervised learning. First we analyze the key factors that are the source of the conflict. Then we assess each software development process requirement (Part 6 of ISO 26262) for applicability to ML. Where there are gaps, we propose new requirements to address the gaps. Finally we discuss the application of this adapted and extended variant of Part 6 to ML development scenarios.

Subfields: Artificial Intelligence, Safety, Risk, Reliability and Quality, Software

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiaowei Huang
2. Wenjie Ruan
3. Daniel Kroening
4. Youcheng Sun
5. Min Wu
6. James Sharp
7. David Flynn
8. Valentin Robu

In Safety, Risk, Reliability and Quality

1. James Sharp
2. Xiaowei Huang

In Software

1. Daniel Kroening
2. Xinping Yi
3. James Sharp
4. Xiaowei Huang
5. Youcheng Sun
6. Min Wu
7. Emese Thamo
8. Wenjie Ruan

Citations in the corpus

• A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability (2018, methodology): “Particularly, as discussed in [Salay and Czarnecki, 2018], when considering the use of machine models in safety critical applications like automotive software, DNN structural coverage criteria can be applied in a similar manner as their traditional software counterparts (e.g., statement coverage or…”
• A Safety Framework for Critical Systems Utilising Deep Neural Networks (2020, methodology): “Regarding the safety of automated driving, [54,50,53] discuss the extension and adaptation of ISO-26262, and [13] considers functional insufficiencies in the perception functions based on DL.”
• Software Engineering for AI-Based Systems: A Survey (2021, methodology): “Specific approaches include the application of agile development principles to AI model and system development [176], the integration of development and runtime methods known from DevOps [9, 132] or the adaptation of acknowledged process standards such as ISO 26262 [168].”