Forschungs- & Entwicklungsinformationsdienst der Gemeinschaft - CORDIS

FP7 Xperience project logo

Xperience

Project ID: 270273
Gefördert unter

Robots Bootstrapped through Learning from Experience

Von 2011-01-01 bis 2015-12-31, Abgeschlossenes Projekt | Xperience Website

Projektdetails

Gesamtkosten:

EUR 10 046 377

EU-Beitrag:

EUR 7 634 000

Koordiniert in:

Germany

Aufruf zur Vorschlagseinreichung:

FP7-ICT-2009-6See other projects for this call

Finanzierungsprogramm:

CP - Collaborative project (generic)

Description

Xperience will implement a complete robot system for automating introspective, predictive, and interactive understanding of actions and dynamic situations based on structural bootstrapping
Humans are able to rapidly create new concepts and react to unanticipated situations using their experience. They use generative mechanisms, like imagining and internal simulation, based on prior knowledge to predict the immediate future. Current artificial cognitive systems do not yet use generative mechanisms in this way. The <a href="http://www.xperience.org/" target="_blank">Xperience </a>project addresses this problem by structural bootstrapping, an idea taken from language acquisition research: if you know the structure of a process the role of unknown actions and entities can be inferred from their location and use in the process. This approach will enable rapid generalisation and allow agents to communicate effectively. Xperience will have a major impact in a wide range of autonomous robotics applications that benefit from efficient learning through exploration, predictive reasoning and external guidance.

Ziel

Current research in embodied cognition builds on the idea that physical interaction with and exploration of the world allows an agent to acquire intrinsically grounded, cognitive representations which are better adapted to guiding behavior than human crafted rules. Exploration and discriminative learning, however, are relatively slow processes. Humans are able to rapidly create new concepts and react to unanticipated situations using their experience. They use generative mechanisms, like imagining and internal simulation, based on prior knowledge to predict the immediate future. Such generative mechanisms increase both the bandwidth and speed of cognitive development, however, current artificial cognitive systems do not yet use generative mechanisms in this way.The Xperience project addresses this problem by structural bootstrapping, an idea taken from language acquisition research: knowledge about grammar allows a child to infer the meaning of an unknown word from its grammatical role together with understood remainder of the sentence. Structural bootstrapping generalizes this idea for general cognitive learning: if you know the structure of a process the role of unknown actions and entities can be inferred from their location and use in the process. This approach will enable rapid generalization and allow agents to communicate effectively.Xperience will implement a complete robot system for automating introspective, predictive, and interactive understanding of actions and dynamic situations based on structural bootstrapping. Xperience will evaluate and benchmark this on state-of-the-art humanoid robots demonstrating rich interactions with humans. By equipping embodied artificial agents with the means to exploit prior experience via generative inner models, XPERIENCE will have a major impact in a wide range of autonomous robotics applications that benefit from efficient learning through exploration, predictive reasoning and external guidance.

Kontaktangaben des Koordinators

Ruediger DILLMANN, (Professor)
Tel.: +49 721 6083846
Fax: +49 721 6084077
E-Mail-Adresse

Koordinator

Karlsruher Institut fuer Technologie
Germany

EU-Beitrag: EUR 1 603 038


Kaiserstrasse 12
76131 Karlsruhe
Germany
Activity type: Private for-profit entities (excluding Higher or Secondary Education Establishments)
Administrative Kontaktangaben: Ruediger Dillmann
Tel.: +49 721 6083846
Fax: +49 721 6084077
E-Mail-Adresse

Teilnehmer

UNIVERSITAET INNSBRUCK
Austria

EU-Beitrag: EUR 781 644


INNRAIN 52
6020 INNSBRUCK
Austria
Activity type: Higher or Secondary Education Establishments
Administrative Kontaktangaben: Boris Puschtiz
Tel.: +43 512 5076102
Fax: +43 512 5076105
E-Mail-Adresse
GEORG-AUGUST-UNIVERSITAT GOTTINGENSTIFTUNG OFFENTLICHEN RECHTS
Germany

EU-Beitrag: EUR 1 208 900


WILHELMSPLATZ 1
37073 GOTTINGEN
Germany
Activity type: Higher or Secondary Education Establishments
Administrative Kontaktangaben: Nadja Daghbouche
Tel.: +49 551 393058
Fax: +49 551 39183058
E-Mail-Adresse
SYDDANSK UNIVERSITET
Denmark

EU-Beitrag: EUR 781 692


CAMPUSVEJ 55
5230 ODENSE M
Denmark
Activity type: Higher or Secondary Education Establishments
Administrative Kontaktangaben: Norbert Krüger
Tel.: +45 65507483
Fax: +45 65503681
E-Mail-Adresse
FONDAZIONE ISTITUTO ITALIANO DI TECNOLOGIA
Italy

EU-Beitrag: EUR 846 070


VIA MOREGO 30
16163 GENOVA
Italy
Activity type: Research Organisations
Administrative Kontaktangaben: Chiara Andreoli
Tel.: +3901071781854
Fax: +390107170817
E-Mail-Adresse
INSTITUT JOZEF STEFAN
Slovenia

EU-Beitrag: EUR 781 665


Jamova 39
1000 LJUBLJANA
Slovenia
Activity type: Research Organisations
Administrative Kontaktangaben: Jadran Lenarčič
Tel.: +386 1 4773513
Fax: +386 1 4773906
E-Mail-Adresse
THE UNIVERSITY OF EDINBURGH
United Kingdom

EU-Beitrag: EUR 1 630 991


OLD COLLEGE, SOUTH BRIDGE
EH8 9YL EDINBURGH
United Kingdom
Activity type: Higher or Secondary Education Establishments
Administrative Kontaktangaben: Frederick Max-Lino
Tel.: +44 131 650 4442
Fax: +44 131 650 6626
E-Mail-Adresse
Folgen Sie uns auf: RSS Facebook Twitter YouTube Verwaltet vom Amt für Veröffentlichungen der EU Nach oben