Publication:
Towards clothes hanging via cloth simulation and deep convolutional networks

dc.affiliation.dptoUC3M. Departamento de Ingeniería de Sistemas y Automáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Laboratorio de Robótica (Robotics Lab)es
dc.contributor.authorEstévez Fernández, David
dc.contributor.authorGonzález Víctores, Juan Carlos
dc.contributor.authorFernández Fernández, Raúl
dc.contributor.authorBalaguer Bernaldo de Quirós, Carlos
dc.contributor.funderComunidad de Madrides
dc.date.accessioned2022-03-29T10:34:09Z
dc.date.available2022-03-29T10:34:09Z
dc.date.issued2021-03
dc.descriptionProceeding of: 10th EUROSIM Congress on Modelling and Simulation (EUROSIM 2019), Logroño, La Rioja, Spain, July 1-5, 2019en
dc.description.abstractPeople spend several hours a week doing laundry, with hanging clothes being one of the laundry tasks to be performed. Nevertheless, deformable object manipulation still proves to be a challenge for most robotic systems, due to the extremely large number of internal degrees of freedom of a piece of clothing and its chaotic nature. This work presents a step towards automated robot clothes hanging by modeling the dynamics of the hanging task via deep convolutional models. Two models are developed to address two different problems: determining if the garment will hang or not (classification), and estimating the future garment location in space (regression). Both models have been trained with a synthetic dataset formed by 15k examples generated though a dynamic simulation of a deformable object. Experiments show that the deep convolutional models presented perform better than a human expert, and that future predictions are largely influenced by time, with uncertainty influencing directly the accuracy of the predictions.en
dc.description.sponsorshipThis work was supported by RoboCity2030-III-CM project (S2013/MIT-2748), funded by Programas de Actividades I+D in Comunidad de Madrid and EU and by a FPU grant funded by Ministerio de Educación, Cultura y Deporte. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the NVIDIA Titan X GPU used for this research.en
dc.format.extent8es
dc.identifier.bibliographicCitationBalaguer Bernaldo de Quirós, Carlos; González Victores, Juan Carlos; Estévez Fernández, David; Fernández Fernández, Raúl. Towards clothes hanging via cloth simulation and deep convolutional networks. In: Simulation notes Europe: journal on developments and trends in modelling and simulation, 31(3) (Selected EUROSIM 2019 Postconf. Publ.), March 2021, Pp. 169-176en
dc.identifier.doihttps://doi.org/10.11128/sne.31.tn.10578
dc.identifier.issn2305-9974
dc.identifier.issn2306-0271 (online)
dc.identifier.publicationfirstpage169es
dc.identifier.publicationissue3es
dc.identifier.publicationlastpage176es
dc.identifier.publicationtitleSimulation notes Europe: journal on developments and trends in modelling and simulation (Selected EUROSIM 2019 Postconf. Publ.)en
dc.identifier.publicationvolume31es
dc.identifier.urihttps://hdl.handle.net/10016/34480
dc.identifier.uxxiCC/0000030904
dc.language.isoengen
dc.publisherArgesimen
dc.relation.eventdate2019-07-01es
dc.relation.eventplaceLOGROÑO, La Riojaes
dc.relation.eventtitle10th EUROSIM Congress on Modeling and Simulation (EUROSIM 2019)en
dc.relation.projectIDComunidad de Madrid. S2013/MIT-2748/RoboCity2030-III-CMes
dc.rightsARGESIM’s primary publication is the journal SNE – Simulation Notes Europe with open access to all contributions; generally, the authors retain the copyright of their SNE contributions.en
dc.rights.accessRightsopen accesses
dc.subject.ecienciaRobótica e Informática Industriales
dc.subject.otherRoboticsen
dc.subject.otherDeformable objectsen
dc.subject.otherLaundryen
dc.subject.otherDeep learningen
dc.titleTowards clothes hanging via cloth simulation and deep convolutional networksen
dc.typeconference paper*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
towards_EUROSIM_2019.pdf
Size:
244.6 KB
Format:
Adobe Portable Document Format