Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)
This methodology aims to establish justified confidence in machine learning components for safety-critical autonomous systems, addressing a key challenge for developers and regulators.
This paper introduces the Assurance of Machine Learning for use in Autonomous Systems (AMLAS) methodology, which integrates safety assurance into ML component development and generates an evidence base to justify the safety of these components in autonomous systems.
Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high degrees of autonomy and are safety critical. Establishing justified confidence in ML forms a core part of the safety case for these systems. In this document we introduce 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 (1) systematically integrating safety assurance into the development of ML components and (2) for generating the evidence base for explicitly justifying the acceptable safety of these components when integrated into autonomous system applications.