Publication:
Applying evolution strategies to neural networks robot controller

dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)es
dc.contributor.authorBerlanga de Jesús, Antonio
dc.contributor.authorMolina López, José Manuel
dc.contributor.authorSanchis de Miguel, María Araceli
dc.contributor.authorIsasi, Pedro
dc.date.accessioned2009-04-17T12:44:05Z
dc.date.available2009-04-17T12:44:05Z
dc.date.issued1999
dc.descriptionProceeding of: International Work-Conference on Artificial and Natural Neural Networks, IWANN'99 Alicante, Spain, June 2–4, 1999
dc.description.abstractIn this paper an evolution strategy (ES) is introduced, to learn weights of a neural network controller in autonomous robots. An ES is used to learn high-performance reactive behavior for navigation and collisions avoidance. The learned behavior is able to solve the problem in different environments; so, the learning process has proven the ability to obtain a specialized behavior. All the behaviors obtained have been tested in a set of environment and the capability of generalization is showed for each learned behavior. No subjective information about “how to accomplish the task” has been included in the fitness function. A simulator based on mini-robot Khepera has been used to learn each behavior.
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationEngineering applications of bio-inspired artificial neural networks. Berlin: Springer, 1999. p. 516-525 (Lecture Notes in Computer Science; 1607)
dc.identifier.doi10.1007/BFb0100519
dc.identifier.isbn978-3-540-66068-2
dc.identifier.issn1611-3349 (Online)
dc.identifier.publicationfirstpage516
dc.identifier.publicationlastpage525
dc.identifier.publicationtitleEngineering applications of bio-inspired artificial neural networks
dc.identifier.urihttps://hdl.handle.net/10016/4006
dc.language.isoeng
dc.publisherSpringer
dc.relation.eventdateJune 2–4, 1999
dc.relation.eventnumber5
dc.relation.eventplaceAlicante (Spain)
dc.relation.eventtitleInternational Work-Conference on Artificial and Natural Neural Networks, (IWANN'99)
dc.relation.ispartofseriesLecture Notes in Computer Science
dc.relation.ispartofseriesVolume 1607/1999
dc.relation.publisherversionhttp://dx.doi.org/10.1007/BFb0100519
dc.rights© Springer
dc.rights.accessRightsopen access
dc.subject.ecienciaInformática
dc.titleApplying evolution strategies to neural networks robot controller
dc.typeconference paper*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
applying_LNCS_1999_ps.pdf
Size:
871.63 KB
Format:
Adobe Portable Document Format