Transferring human emotions to robot motions using Neural Policy Style Transfer

Simple item page
dc.contributor.authorFernández Fernández, Raúl
dc.contributor.authorŁukawski, Bartek
dc.contributor.authorGonzalez Victores, Juan
dc.contributor.authorPacchierotti, Claudio
dc.date.accessioned2023-07-14T11:46:10Z
dc.date.available2023-07-14T11:46:10Z
dc.date.issued2023-05-20
dc.description.abstractNeural Style Transfer (NST) was originally proposed to use feature extraction capabilities of Neural Networks as a way to perform Style Transfer with images. Pre-trained image classification architectures were selected for feature extraction, leading to new images showing the same content as the original but with a different style. In robotics, Style Transfer can be employed to transfer human motion styles to robot motions. The challenge lies in the lack of pre-trained classification architectures for robot motions that could be used for feature extraction. Neural Policy Style Transfer TD3 (NPST3) is proposed for the transfer of human motion styles to robot motions. This framework allows the same robot motion to be executed in different human-centered motion styles, such as in an “angry”, “happy”, “calm”, or “sad” fashion. The Twin Delayed Deep Deterministic Policy Gradient (TD3) network is introduced for the generation of control policies. An autoencoder network is in charge of feature extraction for the Style Transfer step. The Style Transfer step can be performed both offline and online: offline for the autonomous executions of human-style robot motions, and online for adapting at runtime the style of e.g., a teleoperated robot. The framework is tested using two different robotic platforms: a robotic manipulator designed for telemanipulation tasks, and a humanoid robot designed for social interaction. The proposed approach was evaluated for both platforms, performing a total of 147 questionnaires asking human subjects to recognize the human motion style transferred to the robot motion for a predefined set of actions.
dc.description.departmentDepto. de Arquitectura de Computadores y Automática
dc.description.facultyEdiciones Complutense
dc.description.refereedTRUE
dc.description.sponsorshipUnión Europea
dc.description.sponsorshipMinisterio de Ciencia e Innovación
dc.description.sponsorshipComunidad de Madrid
dc.description.sponsorshipISCIII
dc.description.statuspub
dc.identifier.citationFernandez-Fernandez R, Łukawski B, G. Victores J, Pacchierotti C. Transferring human emotions to robot motions using Neural Policy Style Transfer. Cognitive Systems Research. 2023 December; 82:101121
dc.identifier.doihttps://doi.org/10.1016/j.cogsys.2023.05.010
dc.identifier.officialurlhttps://www.sciencedirect.com/science/article/pii/S1389041723000499
dc.identifier.urihttps://hdl.handle.net/20.500.14352/87225
dc.journal.titleCognitive Systems Research
dc.language.isoeng
dc.publisherElsevier
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internationalen
dc.rights.accessRightsopen access
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject.cdu004.8
dc.subject.keywordStyle transfer; Deep reinforcement learning; TD3; Autoencoders; NPST
dc.subject.ucmInteligencia artificial (Informática)
dc.subject.unesco1203.04 Inteligencia Artificial
dc.titleTransferring human emotions to robot motions using Neural Policy Style Transfer
dc.title.alternativeTransferencia de emociones humanas a movimientos de robots usando Neural Policy Style Transfer
dc.typejournal article
dc.type.hasVersionVoR
dc.volume.number82
dspace.entity.typePublication
Download
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S1389041723000499-main.pdf
Size:
1.97 MB
Format:
Adobe Portable Document Format
downoload Download
Collections
Artículos