Publication:
Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

Simple item page
dc.affiliation.dptoUC3M. Departamento de Ingeniería de Sistemas y Automáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Laboratorio de Robótica (Robotics Lab)es
dc.contributor.authorGonzález-Fierro Palacios, Migueles
dc.contributor.authorBalaguer Bernaldo de Quirós, Carloses
dc.contributor.authorSwann, Nicola
dc.contributor.authorNanayakkara, Thrishantha
dc.date.accessioned2015-02-19T09:03:28Z
dc.date.available2015-05-01T22:00:06Z
dc.date.issued2014-04
dc.description.abstractIn this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a different kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by defining a multi-objective reward function of zero moment point and joint torques to represent the stability and effort, we computed reward profiles for each demonstration. Since individual reward profiles show variability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward profiles of the robot should show the same temporal structure of those of the human, we used differential evolution to compute a trajectory that fits all humanoid constraints and minimizes the difference between the robot reward profile and the predicted profile if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown.en
dc.description.sponsorshipThe research leading to these results has received funding from the ARCADIA project DPI2010-21047-C02-01, funded by CICYT project grant on behalf of Spanish Ministry of Economy and Competitiveness and from the RoboCity2030-II-CM project (S2009/DPI-1559), funded by Programas de Actividades I+D en la Comunidad de Madrid and co-funded by Structural Funds of the EU.en
dc.description.statusPublicadoes
dc.format.extent33
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationInternational Journal of Humanoid Robotics (2014). 11(2).en
dc.identifier.doi10.1142/S0219843614500121
dc.identifier.issn0219-8436 (print)
dc.identifier.issn1793-6942 (online)
dc.identifier.publicationfirstpage1
dc.identifier.publicationissue2
dc.identifier.publicationlastpage33
dc.identifier.publicationtitleInternational Journal of Humanoid Roboticsen
dc.identifier.publicationvolume11
dc.identifier.urihttps://hdl.handle.net/10016/20064
dc.identifier.uxxiAR/0000015524
dc.language.isoengen
dc.publisherWorld Scientific Publishing Companyen
dc.relation.projectIDGobierno de España. DPI2010-21047-C02-01en
dc.relation.projectIDComunidad de Madrid. S2009/DPI-1559/ROBOCITY2030 IIen
dc.relation.publisherversionhttp://dx.doi.org/10.1142/S0219843614500121
dc.rights© 2014. World Scientific Publishing Companyen
dc.rights.accessRightsopen accesses
dc.subject.ecienciaRobótica e Informática Industriales
dc.subject.otherLearning from demonstrationen
dc.subject.otherSkill innovationen
dc.subject.otherPostural controlen
dc.subject.otherHumanoid roboten
dc.titleFull-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovationen
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
full_IJHR_2014_ps.pdf
Size:
2.68 MB
Format:
Adobe Portable Document Format
Download
Collections
DISA - LR - Artículos de Revistas