Towards a Framework for Certification of Reliable Autonomous Systems

Abstract

A computational system is called autonomous if it is able to make its own decisions, or take its own actions, without human supervision or control. The capability and spread of such systems have reached the point where they are beginning to touch much of everyday life. However, regulators grapple with how to deal with autonomous systems, for example how could we certify an Unmanned Aerial System for autonomous use in civilian airspace? We here analyse what is needed in order to provide verified reliable behaviour of an autonomous system, analyse what can be done as the state-of-the-art in automated verification, and propose a roadmap towards developing regulatory guidelines, including articulating challenges to researchers, to engineers, and to regulators. Case studies in seven distinct domains illustrate the article.

A formal toolchain for offline and run-time verification of robotic systems

“…These recipes do not all translate in the proposed formalism, yet they clarify where the efforts should be focused. In [Fisher et al, 2021] the authors address the certification aspect, which may involve formal models and approaches. Still the survey is quite extensive and is illustrated with seven use cases.…”

Toward a Holistic Approach to Verification and Validation of Autonomous Cognitive Systems

“…As observed by Fisher, Mascardi, et al in their recent paper on certification of reliable autonomous systems [52], formal methods are a suitable technique for design, specification, validation, and verification of a wide variety of systems, including autonomous and robotic ones. This opinion is shared by many authors [30,61,93].…”