Safety Case Templates for Autonomous Systems

Abstract

This report documents safety assurance argument templates to support the deployment and operation of autonomous systems that include machine learning (ML) components. The document presents example safety argument templates covering: the development of safety requirements, hazard analysis, a safety monitor architecture for an autonomous system including at least one ML element, a component with ML and the adaptation and change of the system over time. The report also presents generic templates for argument defeaters and evidence confidence that can be used to strengthen, review, and adapt the templates as necessary. This report is made available to get feedback on the approach and on the templates. This work was sponsored by the UK Dstl under the R-cloud framework.

arXiv comment136 pages, 57 figures

References in corpus (9)

• A tutorial on conformal prediction
• On a Formal Model of Safe and Scalable Self-driving Cars
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection
• Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars
• A Safety Framework for Critical Systems Utilising Deep Neural Networks
• Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262
• Assurance 2.0: A Manifesto
• Positive Trust Balance for Self-Driving Car Deployment