PSchema: A developmental schema learning framework for embodied agents

H...............H

Show simple item record

dc.contributor.author Sheldon, Michael
dc.contributor.author Lee, Mark
dc.date.accessioned 2011-11-21T11:04:20Z
dc.date.available 2011-11-21T11:04:20Z
dc.date.issued 2011-11-21
dc.identifier.citation Sheldon , M & Lee , M 2011 , ' PSchema: A developmental schema learning framework for embodied agents ' Paper presented at First IEEE Joint International Conference on Development and Learning, and Epigenetic Robotics 2011. , Frankfurt am Main , Germany , 24/08/11 - 27/08/11 , pp. 421-427 . en
dc.identifier.citation conference en
dc.identifier.other PURE: 173789
dc.identifier.other dspace: 2160/7698
dc.identifier.uri http://hdl.handle.net/2160/7698
dc.description Sheldon, M., Lee, M. (2011). PSchema: A developmental schema learning framework for embodied agents. Paper presented at First IEEE Joint International Conference on Development and Learning, and Epigenetic Robotics 2011., Frankfurt am Main, Germany, 421-427. en
dc.description.abstract In this paper we introduce PSchema, a framework for Piagetian schema learning which allows for the direct use of symbolic schema learning in a robotic environment. We show the benefit of a developmental progression to aid in the learning of the system and introduce a generalisation mechanism which further increases the capabilities of these techniques. Using a robotic arm we demonstrate the system’s ability to learn to touch objects placed in front of it and how it can represent the knowledge gained from this in a manner suitable for continuous on-line learning. We then go on to demonstrate how these mechanisms can be used to provide a framework for the learning of language, grounded in the robot’s sensory perception of the world. en
dc.format.extent 7 en
dc.language.iso eng
dc.relation.ispartof en
dc.title PSchema: A developmental schema learning framework for embodied agents en
dc.type Text en
dc.type.publicationtype Conference paper en
dc.contributor.institution Department of Computer Science en
dc.contributor.institution Intelligent Robotics Group en
dc.description.status Peer reviewed en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

My Account