Adaptive robot behavior based on human comfort using reinforcement learning

Vista sencilla de ítem
dc.contributor.authorGonzález Santocildes, Asier
dc.contributor.authorVazquez, Juan-Ignacio
dc.contributor.authorEguíluz, Andoni
dc.date.accessioned2025-03-05T08:21:38Z
dc.date.available2025-03-05T08:21:38Z
dc.date.issued2024
dc.date.updated2025-03-05T08:21:38Z
dc.description.abstractThis study explores the potential of training robots using reinforcement learning (RL) to adapt their behavior based on human comfort levels during tasks. An experimental environment has been developed and made available to the research community, facilitating the replication of these experiments. The results demonstrate that adjusting a single comfort-related input parameter during training leads to significant variations in the robot's behavior. Detailed discussions of the reward functions and obtained results validate these behavioral adaptations, confirming that robots can dynamically respond to human needs, thereby enhancing human-robot interaction. While the study highlights the effectiveness of this approach, it also raises the question of real-time comfort measurement, suggesting various systems for future exploration. These findings contribute to the development of more intuitive and emotionally responsive robots, offering new possibilities for future research in advancing human-robot interaction.en
dc.description.sponsorshipThis work was supported in part by the Project AI-Driven Cognitive Robotic Platform for Agile Production Environments (ACROBA) through European Union’s Horizon 2020 Research and Innovation Programme under Grant 101017284, and in part by the Project EdGe Technologies for Industrial Distributed AI Applications (EGIA) through the ELKARTEK Programme from the Basque Government under Grant KK-2022/00119en
dc.identifier.citationGonzalez-Santocildes, A., Vazquez, J.-I., & Eguiluz, A. (2024). Adaptive Robot Behavior Based on Human Comfort Using Reinforcement Learning. IEEE Access, 12, 122289-122299. https://doi.org/10.1109/ACCESS.2024.3451663
dc.identifier.doi10.1109/ACCESS.2024.3451663
dc.identifier.eissn2169-3536
dc.identifier.urihttps://hdl.handle.net/20.500.14454/2454
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.rights© 2024 The Authors
dc.subject.otherCommunity environment
dc.subject.otherHuman-robot interaction
dc.subject.otherLearning parameters
dc.subject.otherReinforcement learning
dc.subject.otherRobot behavior
dc.subject.otherTask adaptation
dc.subject.otherUser comfort
dc.titleAdaptive robot behavior based on human comfort using reinforcement learningen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.endPage122299
oaire.citation.startPage122289
oaire.citation.titleIEEE Access
oaire.citation.volume12
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
gonzalez_adaptative_2024.pdf
Tamaño:
1.08 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos