​Validating Non-trivial Semantic Properties of Autonomous Robots

Jiri Wiedermann*, Jan van Leeuwen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

A semantic property of autonomous robots is called non-trivial if some robots satisfy it and some do not, like adherence to rules of ethics or compliance with legal regulations. In order to study the validation problem for these properties, we model robots as cyber-physical systems with programmable control. Their behaviour is modelled by the infinite streams of interactions that they generate. We show that, under mild conditions, there can be no algorithmic method for deciding from a robot’s program whether it satisfies a given non-trivial semantic property or not. The result provides a compelling analogue to Rice’s theorem from classical computability theory, now for autonomous robots. We also show that no interactive verifiers of any kind whatsoever can exist for the problem. The results are fundamental to understanding the difficulty of validations in artificial intelligence.
Original languageEnglish
Title of host publicationPhilosophy and Theory of Artificial Intelligence 2021
EditorsVincent C. Muller
Place of PublicationCham
PublisherSpringer
Pages91-104
Number of pages14
Edition1
ISBN (Electronic)978-3-031-09153-7
ISBN (Print)978-3-031-09152-0, 978-3-031-09155-1
DOIs
Publication statusPublished - 15 Nov 2022

Publication series

NameStudies in Applied Philosophy, Epistemology and Rational Ethics (SAPERE)
PublisherSpringer
Volume63
ISSN (Print)2192-6255
ISSN (Electronic)2192-6263

Bibliographical note

Funding Information:
Version dated: May 21, 2022. This work was partially supported by ICS CAS fund RVO 67985807, CAS Programme Strategy 21, and the Karel Cˇ apek Center for Values in Science and Technology (Prague, Czech Republic).

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

  • Autonomous robots
  • Cyber-physical systems
  • Ethics of AI
  • Rice’s theorem
  • Robot modelling
  • Semantic properties
  • Turing machines
  • Verification

Fingerprint

Dive into the research topics of '​Validating Non-trivial Semantic Properties of Autonomous Robots'. Together they form a unique fingerprint.

Cite this