Verifiable self-certifying autonomous systems

Michael Fisher, Emily C. Collins, Louise A. Dennis, Matt Luckcuck, Matt Webster, Michael Jump, Vincent Page, Charles Patchett, Fateme Dinmohammadi, David Flynn, Valentin Robu, Xingyu Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Citations (Scopus)
85 Downloads (Pure)


Autonomous systems are increasingly being used in safety-and mission-critical domains, including aviation, manufacturing, healthcare and the automotive industry. Systems for such domains are often verified with respect to essential requirements set by a regulator, as part of a process called certification. In principle, autonomous systems can be deployed if they can be certified for use. However, certification is especially challenging as the condition of both the system and its environment will surely change, limiting the effective use of the system. In this paper we discuss the technological and regulatory background for such systems, and introduce an architectural framework that supports verifiably-correct dynamic self-certification by the system, potentially allowing deployed systems to operate more safely and effectively.
Original languageEnglish
Title of host publication2018 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW)
Number of pages8
ISBN (Electronic)9781538694435
Publication statusPublished - 19 Nov 2018


  • autonomy
  • verification
  • certification


Dive into the research topics of 'Verifiable self-certifying autonomous systems'. Together they form a unique fingerprint.

Cite this