Towards a Framework for Certification of Reliable Autonomous Systems

Fisher, Michael; Mascardi, Viviana; Rozier, Kristin Yvonne; Schlingloff, Bernd-Holger; Winikof, Michael; Yorke-Smith, N.

doi:10.1007/s10458-020-09487-2

Towards a Framework for Certification of Reliable Autonomous Systems

Title

Towards a Framework for Certification of Reliable Autonomous Systems

Author

Fisher, Michael (The University of Manchester)
Mascardi, Viviana (University of Genova)
Rozier, Kristin Yvonne (Iowa State University)
Schlingloff, Bernd-Holger (Humboldt-Universitat zu Berlin; Fraunhofer FOKUS)
Winikof, Michael (Victoria University of Wellington)
Yorke-Smith, N. (TU Delft Algorithmics)

Date

2021

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.

Subject

Artificial intelligence
Autonomous systems
Certification
Verification

To reference this document use:

http://resolver.tudelft.nl/uuid:5ad2715b-afa6-410b-9c6f-9c9f9376ba23

DOI

https://doi.org/10.1007/s10458-020-09487-2

ISSN

1387-2532

Source

Autonomous Agents and Multi-Agent Systems, 35 (1), 1-65

Part of collection

Institutional Repository