Assurance of Machine Learning for use in Autonomous Systems (AMLAS)

Here we present a methodology for the Assurance of Machine Learning for use in Autonomous Systems (AMLAS).

AMLAS comprises a set of safety case patterns and a process for systematically integrating safety assurance into the development of ML components. This provides a compelling argument about your ML model to feed into your system safety case.

Please enter your details below to download the report (this is done on a voluntary basis to help support our understanding of the reach of our work, not to contact you in the future. Click 'view report' if you would prefer not to enter your details).

AMLAS has been reviewed a wide range of experts across industry and academia. In the coming months, we will validate the process by applying it to a number of case studies in different domains.

We welcome your feedback on AMLAS. In particular, we encourage you to apply this guidance to the development of systems and share those experiences with us.