Safety Case Templates for Autonomous Systems
It addresses safety assurance for autonomous systems, particularly those using ML, by providing structured templates, but it is incremental as it builds on existing safety engineering practices.
The report presents safety assurance argument templates for autonomous systems with machine learning components, covering safety requirements, hazard analysis, and monitoring architectures to support deployment and operation.
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.