Generalization capabilities of co-evolution in learning robot behavior

e-Archivo Repository

Show simple item record Berlanga de Jesús, Antonio Sanchis de Miguel, María Araceli Isasi, Pedro Molina López, José Manuel 2009-11-27T12:41:11Z 2009-11-27T12:41:11Z 2002-09-18
dc.identifier.bibliographicCitation Journal of Robotic Systems, 2002, vol. 19, n. 10, p. 455-467
dc.identifier.issn 0741-2223
dc.description.abstract In this article, a co-evolutive method is used to evolve neural controllers for general obstacle-avoidance of a Braitenberg vehicle. During a first evolutionary process, Evolution Strategies were applied to generate neural controllers; the generality of the obtained behaviors was quite poor. During a second evolutionary process, a new co-evolutive method, called Uniform Co-evolution, is introduced to co-evolve both the controllers and the environment. A comparison of both methods shows that the co-evolutive approach improves the generality of controllers.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Wiley-Blackwell
dc.rights © Wiley Periodicals
dc.title Generalization capabilities of co-evolution in learning robot behavior
dc.type article PeerReviewed
dc.description.status Publicado
dc.subject.eciencia Informática
dc.identifier.doi 10.1002/rob.10054
dc.rights.accessRights openAccess
dc.identifier.publicationfirstpage 455
dc.identifier.publicationissue 10
dc.identifier.publicationlastpage 467
dc.identifier.publicationtitle Journal of Robotic Systems
dc.identifier.publicationvolume 19
dc.identifier.uxxi AR/0000004509
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record