Fisher2020_Article_TowardsAFrameworkForCertificat.pdf (2 MB)

Towards a framework for certification of reliable autonomous systems

Download (2 MB)
journal contribution
posted on 28.12.2020, 10:40 by Michael Fisher, Viviana Mascardi, Kristin Yvonne Rozier, Bernd-Holger Schlingloff, Michael Winikoff, Neil Yorke-Smith
AbstractA 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.

History

Preferred citation

Fisher, M., Mascardi, V., Rozier, K. Y., Schlingloff, B. -H., Winikoff, M. & Yorke-Smith, N. (2021). Towards a framework for certification of reliable autonomous systems. Autonomous Agents and Multi-Agent Systems, 35(1), 8-. https://doi.org/10.1007/s10458-020-09487-2

Journal title

Autonomous Agents and Multi-Agent Systems

Volume

35

Issue

1

Publication date

01/04/2021

Pagination

8

Publisher

Springer Science and Business Media LLC

Publication status

Published online

Online publication date

23/12/2020

ISSN

1387-2532

eISSN

1573-7454

Article number

8

Language

en