Detecting execution failures using learned action models

Maria Fox, Jonathan Gough, Derek Long

Research output: Chapter in Book/Report/Conference proceedingChapter

5 Citations (Scopus)
50 Downloads (Pure)

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.
Original languageEnglish
Title of host publicationProceedings of AAAI 2007
EditorsRobert C. Holte, Adele Howe
Place of PublicationMenlo Park, CA
Pages968-973
Number of pages6
Publication statusPublished - Jul 2007
EventTwenty-Second AAA1 Conference on Artificial Intelligence - Vancouver, Colombia
Duration: 22 Jul 200726 Jul 2007

Conference

ConferenceTwenty-Second AAA1 Conference on Artificial Intelligence
Country/TerritoryColombia
CityVancouver
Period22/07/0726/07/07

Keywords

  • execution failures
  • action models
  • errors

Fingerprint

Dive into the research topics of 'Detecting execution failures using learned action models'. Together they form a unique fingerprint.

Cite this