Mostra el registre d'ítem simple

dc.contributor.authorRozo Castañeda, Leonel
dc.contributor.authorJiménez Schlegl, Pablo
dc.contributor.authorTorras, Carme
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2014-12-05T18:40:48Z
dc.date.available2014-12-05T18:40:48Z
dc.date.created2013
dc.date.issued2013
dc.identifier.citationRozo, L.; Jimenez, P.; Torras, C. Force-based robot learning of pouring skills using parametric hidden Markov models. A: International Workshop on Robot Motion and Control. "Robot Motion and Control (RoMoCo), 2013 9th Workshop on". Wasowo: 2013, p. 227-232.
dc.identifier.urihttp://hdl.handle.net/2117/24956
dc.description.abstractRobot learning from demonstration faces new challenges when applied to tasks in which forces play a key role. Pouring liquid from a bottle into a glass is one such task, where not just a motion with a certain force profile needs to be learned, but the motion is subtly conditioned by the amount of liquid in the bottle. In this paper, the pouring skill is taught to a robot as follows. In a training phase, the human teleoperates the robot using a haptic device, and data from the demonstrations are statistically encoded by a parametric hidden Markov model, which compactly encapsulates the relation between the task parameter (dependent on the bottle weight) and the force-torque traces. Gaussian mixture regression is then used at the reproduction stage for retrieving the suitable robot actions based on the force perceptions. Computational and experimental results show that the robot is able to learn to pour drinks using the proposed framework, outperforming other approaches such as the classical hidden Markov models in that it requires less training, yields more compact encodings and shows better generalization capabilities.
dc.format.extent6 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Automàtica i control
dc.subject.lcshRobot programming
dc.subject.otherlearning (artificial intelligence) robot programming Author keywords: learning from demonstration
dc.subject.otherforce-based control
dc.subject.otherhidden Markov models
dc.titleForce-based robot learning of pouring skills using parametric hidden Markov models
dc.typeConference report
dc.subject.lemacRobòtica
dc.contributor.groupUniversitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
dc.identifier.doi10.1109/RoMoCo.2013.6614613
dc.description.peerreviewedPeer Reviewed
dc.subject.inspecClassificació INSPEC::Automation::Robots::Intelligent robots
dc.relation.publisherversionhttp://dx.doi.org/10.1109/RoMoCo.2013.6614613
dc.rights.accessOpen Access
local.identifier.drac13044014
dc.description.versionPostprint (author’s final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/269959/EU/Intelligent observation and execution of Actions and manipulations/INTELLACT
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/287728/EU/STIFFness controllable Flexible and Learn-able manipulator for surgical OPerations/STIFF-FLOP
local.citation.authorRozo, L.; Jimenez, P.; Torras, C.
local.citation.contributorInternational Workshop on Robot Motion and Control
local.citation.pubplaceWasowo
local.citation.publicationNameRobot Motion and Control (RoMoCo), 2013 9th Workshop on
local.citation.startingPage227
local.citation.endingPage232


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple