Novelty Detection on a Mobile Robot Using Habituation

Simple item page
dc.creatorMarsland, Stephen
dc.creatorNehmzow, Ulrich
dc.creatorShapiro, Jonathan
dc.date2000-06-02
dc.date.accessioned2026-07-07T03:16:16Z
dc.date.available2026-07-07T03:16:16Z
dc.descriptionIn this paper a novelty filter is introduced which allows a robot operating in an un structured environment to produce a self-organised model of its surroundings and to detect deviations from the learned model. The environment is perceived using the rob ot's 16 sonar sensors. The algorithm produces a novelty measure for each sensor scan relative to the model it has learned. This means that it highlights stimuli which h ave not been previously experienced. The novelty filter proposed uses a model of hab ituation. Habituation is a decrement in behavioural response when a stimulus is pre sented repeatedly. Robot experiments are presented which demonstrate the reliable o peration of the filter in a number of environments.
dc.description10 pages, 6 figures. In From Animals to Animats, The Sixth International Conference on Simulation of Adaptive Behaviour, Paris, 2000
dc.identifierhttps://arxiv.org/abs/cs/0006007
dc.identifierhttp://arxiv.org/abs/cs/0006007
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30284
dc.subjectRobotics
dc.subjectNeural and Evolutionary Computing
dc.subjectAdaptation and Self-Organizing Systems
dc.subjectI.2.6
dc.titleNovelty Detection on a Mobile Robot Using Habituation
dc.typetext

Files

Collections

arXiv