Show simple item record

dc.contributor.authorOlivier, Paul
dc.contributor.authorMoreno Aróstegui, Juan Manuel
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica
dc.date.accessioned2011-11-18T19:30:20Z
dc.date.available2011-11-18T19:30:20Z
dc.date.created2011
dc.date.issued2011
dc.identifier.citationOlivier, P.; Moreno, J. Equilibrium-Driven Adaptive Behavior Design. A: International Work-Conference on Artificial Neural Networks. "11th International Work-Conference on Artificial Neural Networks". Torremolinos: Springer Verlag, 2011, p. 589-596.
dc.identifier.isbn978-3-642-21497-4
dc.identifier.urihttp://hdl.handle.net/2117/13975
dc.description.abstractIn autonomous robotics, scalability is a primary discriminator for evaluating a behavior design methodology. Such a proposed methodology must also allow efficient and effective conversion from desired to implemented behavior. From the concepts of equilibrium and homeostasis, it follows that behavior could be seen as driven rather than controlled. Homeostatic variables allow the development of need elements to completely implement drive and processing elements in a synthetic nervous system. Furthermore, an autonomous robot or system must act with a sense of meaning as opposed to being a human-command executor. Learning is fundamental in adding adaptability, and its efficient implementation will directly improve scalability. It is shown how using classical conditioning to learn obstacle avoidance can be implemented with need elements instead of an existing artificial neural network (ANN) solution.
dc.format.extent8 p.
dc.language.isoeng
dc.publisherSpringer Verlag
dc.subjectÀrees temàtiques de la UPC::Informàtica::Robòtica
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshRobotics
dc.titleEquilibrium-Driven Adaptive Behavior Design
dc.typeConference report
dc.subject.lemacRobòtica
dc.subject.lemacXarxes neuronals (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. AHA - Arquitectures Hardware Avançades
dc.identifier.doi10.1007/978-3-642-21498-1_74
dc.description.peerreviewedPeer Reviewed
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac8647252
dc.description.versionPostprint (published version)
local.citation.authorOlivier, P.; Moreno, J.
local.citation.contributorInternational Work-Conference on Artificial Neural Networks
local.citation.pubplaceTorremolinos
local.citation.publicationName11th International Work-Conference on Artificial Neural Networks
local.citation.startingPage589
local.citation.endingPage596


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder