Architecting Systems for Assured Autonomy

Abstract

The promise of autonomous systems can positively impact many facets of human endeavors. This new future does come with significant risks and challenges. There exists a good amount of literature and news about autonomous systems failures that are comic but also tragic. A driving principle for autonomous systems must be that they will cause no harm, that they will operate in a reliable manner and that they can be ultimately trusted. A key item is to develop assurance of a system throughout its architecture. This article provides an overview of the development of assurance architectures as part of the Defense Advanced Research Project Agency Assured Autonomy program.