Logo des Repositoriums
 

Knowledge Based Perceptual Anchoring

dc.contributor.authorDaoutis, Marios
dc.date.accessioned2018-01-08T09:16:32Z
dc.date.available2018-01-08T09:16:32Z
dc.date.issued2013
dc.description.abstractPerceptual anchoring is the process of creating and maintaining a connection between the sensor data corresponding to a physical object and its symbolic description. It is a subset of the symbol grounding problem, introduced by Harnad (Phys. D, Nonlinear Phenom. 42(1–3):335–346, 1990) and investigated over the past years in several disciplines including robotics. This PhD dissertation focuses on a method for grounding sensor data of physical objects to the corresponding semantic descriptions, in the context of cognitive robots where the challenge is to establish the connection between percepts and concepts referring to objects, their relations and properties. We examine how knowledge representation can be used together with an anchoring framework, so as to complement the meaning of percepts while supporting better linguistic interaction with the use of the corresponding concepts. The proposed method addresses the need to represent and process both perceptual and semantic knowledge, often expressed in different abstraction levels, while originating from different modalities. We then focus on the integration of anchoring with a large scale knowledge base system and with perceptual routines. This integration is applied in a number of studies, where in the context of a smart home, several evaluations spanning from spatial and commonsense reasoning to linguistic interaction and concept acquisition.
dc.identifier.pissn1610-1987
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/11348
dc.publisherSpringer
dc.relation.ispartofKI - Künstliche Intelligenz: Vol. 27, No. 2
dc.relation.ispartofseriesKI - Künstliche Intelligenz
dc.subjectAnchoring
dc.subjectCognitive perception
dc.subjectCommon-sense information
dc.subjectKnowledge representation
dc.subjectSymbol grounding
dc.titleKnowledge Based Perceptual Anchoring
dc.typeText/Journal Article
gi.citation.endPage182
gi.citation.startPage179

Dateien