oru.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Knowledge based perceptual anchoring: grounding percepts to concepts in cognitive robots
Örebro universitet, Institutionen för naturvetenskap och teknik.
2013 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

A successful articial cognitive agent needs to integrate its perception of the environment with reasoning and actuation. A key aspect of this integration is the perceptual-symbolic correspondence, which intends to give meaning to the concepts the agent refers to { known as Anchoring. However, perceptual representations alone (e.g., feature lists) cannot entirely provide sucient abstraction and enough richness to deal with the complex nature of the concepts' meanings. On the other hand, neither plain symbol manipulation appears capable of attributing the desired intrinsic meaning.

We approach this integration in the context of cognitive robots which operate in the physical world. Specically we investigate the challenge of establishing 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 linguistic interaction. This implies that robots need to represent both their perceptual and semantic knowledge, which is often expressed in dierent abstraction levels and may originate from dierent modalities.

The solution proposed in this thesis concerns the specication, design and implementation ofa hybrid cognitive computational model, which extends a classical anchoring framework, in order to address the creation and maintenance of the perceptual-symbolic correspondences. The model is based on four main aspects: (a) robust perception, by relying on state-of-the art techniques from computer vision and mobile robot localisation; (b) symbol grounding, using topdown and bottom-up information acquisition processes as well as multi-modal representations; (c) knowledge representation and reasoning techniques in order to establish a common language and semantics regarding physical objects, their properties and relations, that are to be used between heterogeneous robotic agents and humans; and (d) commonsense information in order to enable high-level reasoning as well as to enhance the semantic

descriptions of objects.

The resulting system and the proposed integration has the potential to strengthen and expand the knowledge of a cognitive robot. Specically, by providing more robust percepts it is possible to cope better with the ambiguity and uncertainty of the perceptual data. In addition, the framework is able to exploit mutual interaction between dierent levels of representation while integrating dierent sources of information. By modelling and using semantic & perceptual knowledge, the robot can: acquire, exchange and reason formally about concepts, while prior knowledge can become a cognitive bias in the acquisition of novel concepts.

Ort, förlag, år, upplaga, sidor
Örebro: Örebro universitet , 2013. , s. 99
Serie
Örebro Studies in Technology, ISSN 1650-8580 ; 55
Nyckelord [en]
anchoring, knowledge representation, cognitive perception, symbol grounding, common-sense information
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
Datavetenskap
Identifikatorer
URN: urn:nbn:se:oru:diva-26510ISBN: 978-91-7668-912-7 (tryckt)OAI: oai:DiVA.org:oru-26510DiVA, id: diva2:571925
Disputation
2013-01-17, 10:36 (Engelska)
Opponent
Handledare
Tillgänglig från: 2012-11-26 Skapad: 2012-11-26 Senast uppdaterad: 2018-01-12Bibliografiskt granskad
Delarbeten
1. Using Knowledge Representation for Perceptual Anchoring in a Robotic System
Öppna denna publikation i ny flik eller fönster >>Using Knowledge Representation for Perceptual Anchoring in a Robotic System
2008 (Engelska)Ingår i: International Journal on Artificial Intelligence Tools, ISSN 0218-2130, Vol. 17, nr 5, s. 925-944Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

In this work we introduce symbolic knowledge representation and reasoning capabilities to enrich perceptual anchoring. The idea that encompasses perceptual anchoring is the creation and maintenance of a connection between the symbolic and perceptual description that refer to the same object in the environment. In this work we further extend the symbolic layer by combining a knowledge representation and reasoning (KRR) system with the anchoring module to exploit a knowledge inference mechanisms. We implemented a prototype of this novel approach to explore through initial experimentation the advantages of integrating a symbolic knowledge system to the anchoring framework in the context of an intelligent home. Our results show that using the KRR we are better able to cope with ambiguities in the anchoring module through exploitation of human robot interaction.

Nationell ämneskategori
Teknik och teknologier Data- och informationsvetenskap
Forskningsämne
Data- och systemvetenskap
Identifikatorer
urn:nbn:se:oru:diva-5175 (URN)
Tillgänglig från: 2009-02-24 Skapad: 2009-01-29 Senast uppdaterad: 2018-01-13Bibliografiskt granskad
2. Grounding commonsense knowledge in intelligent systems
Öppna denna publikation i ny flik eller fönster >>Grounding commonsense knowledge in intelligent systems
2009 (Engelska)Ingår i: Journal of Ambient Intelligence and Smart Environments, ISSN 1876-1364, E-ISSN 1876-1372, Vol. 1, nr 4, s. 311-321Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Ambient environments which integrate a number of sensing devices and actuators intended for use by human users need to be able to express knowledge about objects, their functions and their properties to assist in the performance of everyday tasks. For this to occur perceptual data must be grounded to symbolic information that in its turn can be used in the communication with the human. For symbolic information to be meaningful it should be part of a rich knowledge base that includes an ontology of concepts and common sense. In this work we present an integration between ResearchCyc and an anchoring framework that mediates the connection between the perceptual information in an intelligent home environment and the reasoning system. Through simple dialogues we validate how objects placed in the home environment are grounded by a network of sensors and made available to a larger KB where reasoning is exploited. This first integration work is a step towards integrating the richness of a KRR system developed over many years in isolation, with a physically embedded intelligent system.

Ort, förlag, år, upplaga, sidor
Amsterdam: IOS Press, 2009
Nyckelord
Physical Symbol Grounding, Commonsense Knowledge Representation, Human Robot Interaction, Intelligent Home
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
Datavetenskap; Informationsteknologi
Identifikatorer
urn:nbn:se:oru:diva-8485 (URN)10.3233/AIS-2009-0040 (DOI)000207842000002 ()2-s2.0-78651496919 (Scopus ID)
Tillgänglig från: 2009-11-09 Skapad: 2009-11-09 Senast uppdaterad: 2018-01-12Bibliografiskt granskad
3. Cooperative knowledge based perceptual anchoring
Öppna denna publikation i ny flik eller fönster >>Cooperative knowledge based perceptual anchoring
2012 (Engelska)Ingår i: International journal on artificial intelligence tools, ISSN 0218-2130, Vol. 21, nr 3, artikel-id 1250012Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

In settings where heterogenous robotic systems interact with humans, information from the environment must be systematically captured, organized and maintained in time. In this work, we propose a model for connecting perceptual information to semantic information in a multi-agent setting. In particular, we present semantic cooperative perceptual anchoring, that captures collectively acquired perceptual information and connects it to semantically expressed commonsense knowledge. We describe how we implemented the proposed model in a smart environment, using different modern perceptual and knowledge representation techniques. We present the results of the systemand investigate different scenarios in which we use the common sense together with perceptual knowledge, for communication, reasoning and exchange of information.

Ort, förlag, år, upplaga, sidor
World Scientific, 2012
Nyckelord
Cognitive robotics; physical symbol grounding; commonsense information; multi-agent perception; object recognition
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
Datalogi
Identifikatorer
urn:nbn:se:oru:diva-24226 (URN)10.1142/S0218213012500121 (DOI)000305795900008 ()2-s2.0-84863086324 (Scopus ID)
Forskningsfinansiär
Vetenskapsrådet
Tillgänglig från: 2012-08-06 Skapad: 2012-08-05 Senast uppdaterad: 2018-01-12Bibliografiskt granskad
4. Towards concept anchoring for cognitive robots
Öppna denna publikation i ny flik eller fönster >>Towards concept anchoring for cognitive robots
2012 (Engelska)Ingår i: Intelligent Service Robotics, ISSN 1861-2784, Vol. 5, nr 4, s. 213-228Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

We present a model for anchoring categorical conceptual information which originates from physical perception and the web. The model is an extension of the anchoring framework which is used to create and maintain over time semantically grounded sensor information. Using the augmented anchoring framework that employs complex symbolic knowledge from a commonsense knowledge base, we attempt to ground and integrate symbolic and perceptual data that are available on the web. We introduce conceptual anchors which are representations of general, concrete conceptual terms. We show in an example scenario how conceptual anchors can be coherently integrated with perceptual anchors and commonsense information for the acquisition of novel concepts.

Ort, förlag, år, upplaga, sidor
Springer Berlin/Heidelberg, 2012
Nyckelord
Anchoring; Categorical perception; Near sets; Knowledge representation; Commonsense information
Nationell ämneskategori
Robotteknik och automation Datorseende och robotik (autonoma system) Datavetenskap (datalogi)
Forskningsämne
Datavetenskap
Identifikatorer
urn:nbn:se:oru:diva-26831 (URN)10.1007/s11370-012-0117-z (DOI)000208947900002 ()2-s2.0-84867580722 (Scopus ID)
Forskningsfinansiär
Vetenskapsrådet
Tillgänglig från: 2013-01-10 Skapad: 2013-01-10 Senast uppdaterad: 2018-01-11Bibliografiskt granskad

Open Access i DiVA

sammanfattning(13011 kB)281 nedladdningar
Filinformation
Filnamn SUMMARY01.pdfFilstorlek 13011 kBChecksumma SHA-512
3484f8619dce759832f497ff27c7da48bc81cd2b68c1f3c61e33c62f821c285f332c5f2536bdac6223b27518df48768cc5ea2cce3092a5f5ce514c3e851f5c40
Typ summaryMimetyp application/pdf
omslag(1555 kB)130 nedladdningar
Filinformation
Filnamn COVER01.pdfFilstorlek 1555 kBChecksumma SHA-512
ca73bcff4e211b2ed48aeb1829745574a8d41b5f70a970e0953525e03855fcad53751f01c42893722e061f7c8322f1cb0634ec23637281898dc7d1232ca950ec
Typ coverMimetyp application/pdf
spikblad(204 kB)16 nedladdningar
Filinformation
Filnamn SPIKBLAD01.pdfFilstorlek 204 kBChecksumma SHA-512
bc139bc80df36c0458c099cd57ca3248a7ecd356bca92e0548c9c7c61db90de9b292bca97d427430106af975efcae3a24ada209e1f78a3010b518dc91452f19e
Typ spikbladMimetyp application/pdf

Personposter BETA

Daoutis, Marios

Sök vidare i DiVA

Av författaren/redaktören
Daoutis, Marios
Av organisationen
Institutionen för naturvetenskap och teknik
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 798 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf