Emerging behaviors by learning joint coordination in articulated mobile robots

Vista senzilla d'ítem
dc.contributor.authorPardo Ayala, Diego Esteban
dc.contributor.authorAngulo Bahón, Cecilio
dc.contributor.groupUniversitat Politècnica de Catalunya. GREC - Grup de Recerca en Enginyeria del Coneixement
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.date.accessioned2010-10-21T11:41:31Z
dc.date.available2010-10-21T11:41:31Z
dc.date.created2007
dc.date.issued2007
dc.descriptionA Policy Gradient Reinforcement Learning (RL) technique is used to design the low level controllers that drives the joints of articulated mobile robots: A search in the controller’s parameters space. There is an unknown value function that measures the quality of the controller respect to the parameters of it. The search is orientated by the approximation of the gradient of the value function. The approximation is made by means of the robot experiences and then the behaviors emerge. This technique is employed in a structure that processes sensor information to achieve coordination. The structure is based on a modularization principle in which complex overall behavior is the result of the interaction of individual ‘simple’ components. The simple components used are standard low level controllers (PID) which output is combined, sharing information between articulations and therefore taking integrated control actions. Modularization and Learning are cognitive features, here we endow the robots with this features. Learning experiences in simulated robots are presented as demonstration.
dc.description.peerreviewedPeer Reviewed
dc.description.versionPostprint (published version)
dc.format.extent8 p.
dc.identifier.citationPardo, D.; Angulo, C. Emerging behaviors by learning joint coordination in articulated mobile robots. A: International Work-Conference on Artificial Neural Networks. "9th International Work-Conference on Artificial Neural Networks. IWANN 2007". Sant Sebastián: Springer, 2007, p. 806-813.
dc.identifier.doi10.1007/978-3-540-73007-1_97
dc.identifier.urihttps://hdl.handle.net/2117/9904
dc.language.isoeng
dc.publisherSpringer
dc.relation.publisherversionhttp://www.springerlink.com/content/8759jq6173515421/
dc.rights.accessRestricted access - publisher's policy
dc.subjectÀrees temàtiques de la UPC::Informàtica::Robòtica
dc.subject.lcshCognitive robotics
dc.subject.lcshSensor-motor control
dc.subject.lemacRobots articulats
dc.subject.lemacRobots mòbils -- Disseny i construcció
dc.titleEmerging behaviors by learning joint coordination in articulated mobile robots
dc.typeConference report
dspace.entity.typePublication
local.citation.authorPardo, D.; Angulo, C.
local.citation.contributorInternational Work-Conference on Artificial Neural Networks
local.citation.endingPage813
local.citation.publicationName9th International Work-Conference on Artificial Neural Networks. IWANN 2007
local.citation.pubplaceSant Sebastián
local.citation.startingPage806
local.identifier.drac2454073

Fitxers

Paquet original

Mostrant 1 - 1 de 1
Miniatura
Nom:
Emerging behaviors by learning joint coordination in articulated mobile robots.pdf
Mida:
767.9 KB
Format:
Adobe Portable Document Format
Descripció:
Descarregar (Accés restringit) Sol·licita una còpia a l'autor

Col·leccions

Enviament des de DRAC
Ponències/Comunicacions de congressos
Ponències/Comunicacions de congressos