Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

TL;DR

This paper introduces AMLAS, a methodology combining safety case patterns and processes to systematically assure machine learning components in autonomous, safety-critical systems like healthcare and automotive.

Contribution

It presents a novel safety assurance methodology specifically designed for ML in autonomous systems, integrating assurance into development and evidence generation.

Findings

Provides a structured safety assurance process for ML in autonomous systems

Defines safety case patterns for ML component justification

Facilitates systematic safety evidence collection and validation

Abstract

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.