Picture of a black hole

Strathclyde Open Access research that creates ripples...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of research papers by University of Strathclyde researchers, including by Strathclyde physicists involved in observing gravitational waves and black hole mergers as part of the Laser Interferometer Gravitational-Wave Observatory (LIGO) - but also other internationally significant research from the Department of Physics. Discover why Strathclyde's physics research is making ripples...

Strathprints also exposes world leading research from the Faculties of Science, Engineering, Humanities & Social Sciences, and from the Strathclyde Business School.

Discover more...

Detecting execution failures using learned action models

Fox, M. and Gough, J. and Long, D. (2007) Detecting execution failures using learned action models. In: Proceedings of AAAI 2007. Association for the Advancement of Artificial Intelligence. ISBN 978-1-57735-323-2

[img]
Preview
PDF (strathprints003424.pdf)
strathprints003424.pdf

Download (586kB) | Preview

Abstract

Planners reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours interacting with the unpredictable uncertainties of the environment can lead to failure. One of the challenges for intelligent autonomy is to recognise when the actual execution of a behaviour has diverged so far from the expected behaviour that it can be considered to be a failure. In this paper we present an approach by which a trace of the execution of a behaviour is monitored by tracking its most likely explanation through a learned model of how the behaviour is normally executed. In this way, possible failures are identified as deviations from common patterns of the execution of the behaviour. We perform an experiment in which we inject errors into the behaviour of a robot performing a particular task, and explore how well a learned model of the task can detect where these errors occur.