Publication:
Neural networks robot controller trained with evolution strategies

Simple item page
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.authorIsasi, Pedro
dc.contributor.authorSanchis de Miguel, María Araceli
dc.contributor.authorMolina López, José Manuel
dc.date.accessioned2009-04-22T14:31:50Z
dc.date.available2009-04-22T14:31:50Z
dc.date.issued1999-07
dc.descriptionCongress on Evolutionary Computation. Washington, DC, 6-9 July 1999.
dc.description.abstractNeural networks (NN) can be used as controllers in autonomous robots. The specific features of the navigation problem in robotics make generation of good training sets for the NN difficult. An evolution strategy (ES) is introduced to learn the weights of the NN instead of the learning method of the network. The ES is used to learn high performance reactive behavior for navigation and collision avoidance. No subjective information about “how to accomplish the task” has been included in the fitness function. The learned behaviors are able to solve the problem in different environments; therefore, the learning process has the proven ability to obtain a specialized behavior. All the behaviors obtained have been tested in a set of environments and the capability of generalization is shown for each learned behavior. A simulator based on the mini-robot, Khepera, has been used to learn each behavior.
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationProceeding of the 1999 Congress on Evolutionary Computation (CEC 99).vol. 1. p. 413-419
dc.identifier.doi10.1109/CEC.1999.781954
dc.identifier.isbn0-7803-5536-9
dc.identifier.publicationfirstpage413
dc.identifier.publicationlastpage419
dc.identifier.publicationtitleProceeding of the 1999 Congress on Evolutionary Computation (CEC 99)
dc.identifier.urihttps://hdl.handle.net/10016/4026
dc.language.isoeng
dc.publisherIEEE
dc.relation.eventdate6-9 July 1999
dc.relation.eventplaceWashington DC (USA)
dc.relation.eventtitleCongress on Evolutionary Computation
dc.relation.publisherversionhttp://dx.doi.org/10.1109/CEC.1999.781954
dc.rights© IEEE
dc.rights.accessRightsopen access
dc.subject.ecienciaInformática
dc.titleNeural networks robot controller trained with evolution strategies
dc.typeconference paper*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
neural-networks_CEC_1999.pdf
Size:
526.57 KB
Format:
Adobe Portable Document Format
Download
Collections
DI - GCERN - Comunicaciones en Congresos y otros eventos