Picture map of Europe with pins indicating European capital cities

Open Access research with a European policy impact...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of Open Access research papers by Strathclyde researchers, including by researchers from the European Policies Research Centre (EPRC).

EPRC is a leading institute in Europe for comparative research on public policy, with a particular focus on regional development policies. Spanning 30 European countries, EPRC research programmes have a strong emphasis on applied research and knowledge exchange, including the provision of policy advice to EU institutions and national and sub-national government authorities throughout Europe.

Explore research outputs by the European Policies Research Centre...

Detecting execution failures using learned action models

Fox, Maria and Gough, Jonathan and Long, Derek (2007) Detecting execution failures using learned action models. In: Proceedings of AAAI 2007. Association for the Advancement of Artificial Intelligence, Menlo Park, CA, pp. 968-973. ISBN 9781577353232

[img]
Preview
Text (strathprints003424)
strathprints003424.pdf - Accepted Author Manuscript

Download (499kB) | 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.