A general learning co-evolution method to generalize autonomous robot navigation behavior

e-Archivo Repository

Show simple item record

dc.contributor.author Berlanga de Jesús, Antonio
dc.contributor.author Sanchis de Miguel, María Araceli
dc.contributor.author Isasi, Pedro
dc.contributor.author Molina López, José Manuel
dc.date.accessioned 2009-04-23T09:11:57Z
dc.date.available 2009-04-23T09:11:57Z
dc.date.issued 2000-07
dc.identifier.bibliographicCitation Proceedings of the 2000 Congress on Evolutionary Computation, 2000. vol.1. p. 769-776
dc.identifier.isbn 0-7803-6375-2
dc.identifier.uri http://hdl.handle.net/10016/4051
dc.description Congress on Evolutionary Computation. La Jolla, CA, 16-19 July 2000.
dc.description.abstract A new coevolutive method, called Uniform Coevolution, is introduced, to learn weights for a neural network controller in autonomous robots. An evolutionary strategy is used to learn high-performance reactive behavior for navigation and collision avoidance. The coevolutive method allows the evolution of the environment, to learn a general behavior able to solve the problem in different environments. Using a traditional evolutionary strategy method without coevolution, the learning process obtains a specialized behavior. All the behaviors obtained, with or without coevolution have been tested in a set of environments and the capability for generalization has been shown for each learned behavior. A simulator based on the mini-robot Khepera has been used to learn each behavior. The results show that Uniform Coevolution obtains better generalized solutions to example-based problems.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher IEEE
dc.rights © IEEE
dc.title A general learning co-evolution method to generalize autonomous robot navigation behavior
dc.type conferenceObject
dc.type bookPart
dc.relation.publisherversion http://dx.doi.org/10.1109/CEC.2000.870376
dc.subject.eciencia Informática
dc.identifier.doi 10.1109/CEC.2000.870376
dc.rights.accessRights openAccess
dc.relation.eventdate 16-19 July 2000
dc.relation.eventplace La Jolla (California, USA)
dc.relation.eventtitle Congress on Evolutionary Computation
dc.relation.eventtype proceedings
dc.identifier.publicationfirstpage 769
dc.identifier.publicationlastpage 776
dc.identifier.publicationtitle Proceedings of the 2000 Congress on Evolutionary Computation
dc.identifier.publicationvolume 1
 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