Logo des Repositoriums
 

Self-organization at the lowest level: proactively learning skills in autonomous systems

dc.contributor.authorRichert, Willi
dc.contributor.authorKleinjohann, Bernd
dc.contributor.authorMurmann, Alexander
dc.contributor.editorHochberger, Christian
dc.contributor.editorLiskowsky, Rüdiger
dc.date.accessioned2019-06-12T12:32:08Z
dc.date.available2019-06-12T12:32:08Z
dc.date.issued2006
dc.description.abstractTo enable autonomous systems to learn basic skills for unknown and changing environments and stay robust in case of change, Organic Computing principles have to be applied at all layers. In this work an architecture is presented that can be used at the lowest layer providing robust skills to higher-level strategy layers, that depend on encapsulated actions. With emphasis on robustness it is able to learn to control its actors without a priori information about their meaning. This is made possible by skill modules that are learned together with their action-effect dependencies and their enabling preconditions by proactively carrying out experiments within their environment. The architecture is evaluated by simulating a differentially driven robot.en
dc.identifier.isbn978-3-88579-187-4
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/23666
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofINFORMATIK 2006 – Informatik für Menschen, Band 1
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-93
dc.titleSelf-organization at the lowest level: proactively learning skills in autonomous systemsen
dc.typeText/Conference Paper
gi.citation.endPage136
gi.citation.publisherPlaceBonn
gi.citation.startPage128
gi.conference.date2.-6. Oktober 2006
gi.conference.locationDresden
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
GI-Proceedings-93-20.pdf
Größe:
204.08 KB
Format:
Adobe Portable Document Format