Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Collaborative Transport Robots (CTRs) Applicable in the Proximal Urban Environment: A Review

  • Garrell, Anaís
  • Pino, Iván del
  • Santamaria-Navarro, Àngel
  • Sanfeliu, Alberto
Collaborative Transport Robots (CTRs) are not yet a frequent or well-known reality for many urban stakeholders, including city agents, transportation planners, policymakers, construction professionals, service providers, and other relevant participants in the urban mobility ecosystem. This lack of familiarity presents a significant barrier to the development and implementation of novel, adaptive, and creative urban mobility solutions. It also hinders the integration of CTRs into already-existing transport networks, systems, and physical infrastructure. CTRs represent a broad, versatile, and rapidly evolving category of robotic systems designed specifically for deployment in urban environments. These robots are typically equipped with an array of advanced sensors, artificial intelligence technologies, and connectivity features. These tools enable them to operate autonomously, navigate complex urban landscapes, and interact safely and efficiently with humans, vehicles, and other robotic systems in real time. Moreover, CTRs hold the potential to significantly increase the efficiency, sustainability, and safety of urban transit systems. They can help reduce congestion, streamline last-mile delivery, enhance pedestrian experiences, and offer novel mobility options for individuals who face transportation barriers, such as the elderly or those with disabilities. In addition, CTRs may contribute to reducing carbon emissions and improving air quality through the automation of low-emission mobility tasks. As the technology behind CTRs continues to develop, urban decision-makers and stakeholders must become more aware of and engaged with these innovations. A better understanding of CTR capabilities and applications will be essential for shaping future cities that are more accessible, resilient, and responsive to the needs of all residents., This work has been partially supported by Horizon Europe under the grant agreement No. 101189557 (TORNADO); by the Spanish Ministry of Science and Innovation under the project LENA (PID2022-142039NA-I00, funded by MCIN/AEI/10.13039/501100011033 and by "ERDF A way of making Europe"); by the BotNet project (23S06128-00), funded by the Ajuntament de Barcelona and Fundació la Caixa; and by the Consolidated Research Group RAIG (2021 SGR 00510) of the Departament de Recerca i Universitats de la Generalitat de Catalunya., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

TORNADO: Foundation models for robots that handle small, soft and deformable objects

  • Moutousi, Maria
  • El Saer, Andreas
  • Nikolaou, Nikos
  • Sanfeliu Cortés, Alberto
  • Garrell Zulueta, Anaís
  • Bláha, Lukáš
  • Čech, Martin
  • Markakis, Evangelos K.
  • Kefaloukos, Ioannis
  • Lagomarsino, Marta
  • Margetis, George
  • Adamakis, Emmanouil
  • Poulakidas, Athanasios
  • Lykokanellos, Filopoimin
  • Stefanidou, Artemis
  • Cani, Jorgen
  • Radoglou-Grammatikis, Panagiotis
  • Siganos, Marios
  • Ajoudani, Arash
  • Papadopoulos, Georgios Th.
Trabajo presentado en el 6th International Conference in Electronic Engineering & Information Technology (EEITE), celebrado en Chania (Grecia), del 4 al 6 de junio de 2025, This paper introduces TORNADO, a cloud-integrated robotics platform designed to tackle the challenges of autonomous manipulation in dynamic indoor environments, particularly those involving small, soft, or deformable objects. TORNADO integrates large-scale foundation models for perception, language comprehension, and high-level reasoning, to achieve strong zero-shot generalization across a wide range of tasks. At its core, the platform features an adaptive cognitive pipeline capable of dynamically reconfiguring its modules—including semantic 3D SLAM, people-aware navigation, dexterous manipulation, and human-in-the-loop learning—to manage uncertainty and adapt to changing conditions. Additionally, TORNADO incorporates a multi-modal Learning-from-Demonstration interface and an Explainable AI engine, enhancing transparency and easing the burden of teaching new tasks. The system is validated through three industry-relevant scenarios: (1) flexible gear and ply-sheet handling in a mechanical parts factory, (2) patient support in a hospital palliative ward, and (3) product sampling and waste management in a distribution center. TORNADO aims to significantly improve the agility, safety, and overall task performance of mobile manipulators operating in dynamic, human-centric environments., The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The work was supported by the European Union through the research and innovation program under Grant No. 101189557 (TORNADO). In addition, certain sections may include content generated or refined by AI, any of which has been carefully reviewed, edited, and integrated by the authors., Peer reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Human perception in social tasks: a comparative evaluation of autonomous and teleoperated robots

  • Hriscu Acsinte-Staut, Lavinia Beatrice
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
  • Garrell Zulueta, Anais|||0000-0002-4629-0723
© 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/, Robots and artificial intelligence technologies are becoming increasingly integrated into our daily lives. The introduction of humanoid robots into everyday settings is a gradual but ongoing process—one that society is already beginning to navigate. Yet this shift raises important questions: Who or what is truly behind these physical agents? And can we, as users, perceive differences in our interactions depending on whether a robot acts autonomously or it’s teleoperated by a human? In this study, we present the results of an experiment in which participants interacted with a robot under two control conditions—autonomous and teleoperated—while it performed two distinct tasks in both static and dynamic movement scenarios. In our results, human operators outperformed autonomous systems in tasks requiring spatial awareness and contextual reasoning. Conversely, the autonomous robot—powered by a Large Language Model and operating without visual input—was perceived more favorably in tasks that demanded rapid access to broad and diverse information., This work was supported in part by JST Moonshot R, D under Grant JPMJMS2011-85, in part by the Spanish Ministry of Science, Innovation and Universities under the project LENA under Grant PID2022-142039NA-I00, funded by MCIU/AEI/10.13 039/50110001103, in part by the European project TORNADO under Grant HORIZON-CL4-2024-DIGITAL-EMERGING-01-101189557, and in part by Predoctoral Program AGAUR-FI ajuts under Grant 2025FI-101034 Joan Oró, through the Secretariat of Universities and Research of Department of Research and Universities of the Generalitat of Catalonia and European Social Plus Fund. (Corresponding author: Lavinia Hriscu.), Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

TORNADO: foundation models for robots that handle small, soft and deformable objects

  • Moutousi, Maria
  • El Saer, Andreas
  • Nikolaou, Nikos
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
  • Garrell Zulueta, Anais|||0000-0002-4629-0723
  • Markakis, Evangelos
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper introduces TORNADO, a cloud-integrated robotics platform designed to tackle the challenges of autonomous manipulation in dynamic indoor environments, particularly those involving small, soft, or deformable objects. TORNADO integrates large-scale foundation models for perception, language comprehension, and high-level reasoning, to achieve strong zero-shot generalization across a wide range of tasks. At its core, the platform features an adaptive cognitive pipeline capable of dynamically reconfiguring its modules—including semantic 3D SLAM, people-aware navigation, dexterous manipulation, and human-in-the-loop learning—to manage uncertainty and adapt to changing conditions. Additionally, TORNADO incorporates a multi-modal Learning-from-Demonstration interface and an Explainable AI engine, enhancing transparency and easing the burden of teaching new tasks. The system is validated through three industry-relevant scenarios: (1) flexible gear and ply-sheet handling in a mechanical parts factory, (2) patient support in a hospital palliative ward, and (3) product sampling and waste management in a distribution center. TORNADO aims to significantly improve the agility, safety, and overall task performance of mobile manipulators operating in dynamic, human-centric environments., The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The work was supported by the European Union through the research and innovation program under Grant No. 101189557 (TORNADO). In addition, certain sections may include content generated or refined by AI, any of which has been carefully reviewed, edited, and integrated by the authors., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

AI or human? Understanding perceptions of embodied robots with LLMs

  • Hriscu Acsinte-Staut, Lavinia Beatrice
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
  • Garrell Zulueta, Anais|||0000-0002-4629-0723
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The pursuit of artificial intelligence has long been associated to the the challenge of effectively measuring intelligence. Even if the Turing Test was introduced as a means of assessing a system's intelligence, its relevance and application within the field of human-robot interaction remain largely underexplored. This study investigates the perception of intelligence in embodied robots by performing a Turing Test within a robotic platform. A total of 34 participants were tasked with distinguishing between AI- and human-operated robots while engaging in two interactive tasks: an information retrieval and a package handover. These tasks assessed the robot’s perception and navigation abilities under both static and dynamic conditions. Results indicate that participants were unable to reliably differentiate between AI- and human-controlled robots beyond chance levels. Furthermore, analysis of participant responses reveals key factors influencing the perception of artificial versus human intelligence in embodied robotic systems. These findings provide insights into the design of future interactive robots and contribute to the ongoing discourse on intelligence assessment in AI-driven systems., This work has been supported by JST Moonshot R & D (JPMJMS2011-85) and the European project TORNADO with grant number HORIZONCL4-2024-DIGITAL-EMERGING-01-101189557, Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Collaborative transport robots (CTRs) applicable in the proximal urban environment: a review, Robots de transporte colaborativo (CTR) aplicables en el entorno urbano próximo: una revisión, Robots de Transport Col·laboratius (CTR) aplicables a l'entorn urbà proper: una revisió

  • Garrell Zulueta, Anais|||0000-0002-4629-0723
  • Pino Bastida, Iván del|||0000-0003-0516-7443
  • Santamaria Navarro, Àngel|||0000-0002-6328-1423
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
Collaborative Transport Robots (CTRs) are not yet a frequent or well-known reality for many urban stakeholders, including city agents, transportation planners, policymakers, construction professionals, service providers, and other relevant participants in the urban mobility ecosystem. This lack of familiarity presents a significant barrier to the development and implementation of novel, adaptive, and creative urban mobility solutions. It also hinders the integration of CTRs into already-existing transport networks, systems, and physical infrastructure. CTRs represent a broad, versatile, and rapidly evolving category of robotic systems designed specifically for deployment in urban environments. These robots are typically equipped with an array of advanced sensors, artificial intelligence technologies, and connectivity features. These tools enable them to operate autonomously, navigate complex urban landscapes, and interact safely and efficiently with humans, vehicles, and other robotic systems in real time. Moreover, CTRs hold the potential to significantly increase the efficiency, sustainability, and safety of urban transit systems. They can help reduce congestion, streamline last-mile delivery, enhance pedestrian experiences, and offer novel mobility options for individuals who face transportation barriers, such as the elderly or those with disabilities. In addition, CTRs may contribute to reducing carbon emissions and improving air quality through the automation of low-emission mobility tasks. As the technology behind CTRs continues to develop, urban decision-makers and stakeholders must become more aware of and engaged with these innovations. A better understanding of CTR capabilities and applications will be essential for shaping future cities that are more accessible, resilient, and responsive to the needs of all residents., Els Robots de Transport Col·laboratius (CTR) encara no són una realitat freqüent ni ben coneguda per a molts agents urbans, incloent planificadors de transport, responsables polítics, professionals de la construcció, proveïdors de serveis i altres participants rellevants en l'ecosistema de mobilitat urbana. Aquesta manca de familiaritat representa una barrera important per al desenvolupament i implementació de solucions de mobilitat urbana noves, adaptatives i creatives. També dificulta la integració dels CTR en xarxes, sistemes i infraestructures físiques de transport ja existents. Els CTR representen una categoria ampla, versàtil i en ràpida evolució de sistemes robòtics dissenyats específicament per al desplegament en entorns urbans. Aquests robots solen estar equipats amb una varietat de sensors avançats, tecnologies d'intel·ligència artificial i funcions de connectivitat. Aquestes eines els permeten operar de manera autònoma, navegar per paisatges urbans complexos i interactuar de manera segura i eficient amb humans, vehicles i altres sistemes robòtics en temps real. A més, els CTR tenen el potencial d'augmentar significativament l'eficiència, sostenibilitat i seguretat dels sistemes de trànsit urbà. Poden ajudar a reduir la congestió, optimitzar l'última milla de distribució, millorar l'experiència dels vianants i oferir noves opcions de mobilitat per a persones que enfronten barreres de transport, com els ancians o persones amb discapacitat. Addicionalment, els CTR podrien contribuir a reduir les emissions de carboni i millorar la qualitat de l'aire mitjançant l'automatització de tasques de mobilitat de baixes emissions. A mesura que la tecnologia dels CTR continua desenvolupant-se, els responsables de decisions urbanes i les parts interessades han d'adquirir més consciència i implicar-se amb aquestes innovacions. Una millor comprensió de les capacitats i aplicacions dels CTR serà essencial per configurar ciutats futures més accessibles, resilients i sensibles a les necessitats de tots els residents., Los Robots de Transporte Colaborativo (CTRs, por sus siglas en inglés) aún no son una realidad frecuente ni ampliamente conocida para muchos actores urbanos, incluidos agentes municipales, planificadores de transporte, responsables políticos, profesionales de la construcción, proveedores de servicios y otros participantes relevantes en el ecosistema de movilidad urbana. Esta falta de familiaridad representa una barrera significativa para el desarrollo e implementación de soluciones de movilidad urbana novedosas, adaptativas y creativas. También dificulta la integración de los CTRs en redes de transporte, sistemas e infraestructuras físicas ya existentes. Los CTRs representan una categoría amplia, versátil y en rápida evolución de sistemas robóticos diseñados específicamente para su implementación en entornos urbanos. Estos robots suelen estar equipados con una variedad de sensores avanzados, tecnologías de inteligencia artificial y funciones de conectividad. Estas herramientas les permiten operar de forma autónoma, navegar por paisajes urbanos complejos e interactuar de manera segura y eficiente con personas, vehículos y otros sistemas robóticos en tiempo real. Además, los CTRs tienen el potencial de aumentar significativamente la eficiencia, sostenibilidad y seguridad de los sistemas de transporte urbano. Pueden ayudar a reducir la congestión, optimizar la entrega de última milla, mejorar la experiencia peatonal y ofrecer nuevas opciones de movilidad para personas que enfrentan barreras de transporte, como los adultos mayores o personas con discapacidades. Asimismo, los CTRs pueden contribuir a la reducción de emisiones de carbono y a la mejora de la calidad del aire mediante la automatización de tareas de movilidad de bajas emisiones. A medida que la tecnología detrás de los CTRs sigue avanzando, los responsables de la toma de decisiones urbanas y otros actores deben familiarizarse más con estas innovaciones. Comprender mejor las capacidades y aplicaciones de los CTRs será esencial para dar forma a ciudades futuras más accesibles, resilientes y receptivas a las necesidades de todos los residentes., This work has been partially supported by Horizon Europe under the grant agreement No. 101189557 (TORNADO); by the Spanish Ministry of Science and Innovation under the project LENA (PID2022-142039NA-I00, funded by MCIN/AEI/10.13039/501100011033 and by "ERDF A way of making Europe"); by the BotNet project (23S06128-00), funded by the Ajuntament de Barcelona and Fundació la Caixa; and by the Consolidated Research Group RAIG (2021 SGR 00510) of the Departament de Recerca i Universitats de la Generalitat de Catalunya., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

TORNADO: foundation models for robots that handle small, soft and deformable objects

  • Moutousi, Maria
  • El Saer, Andreas
  • Nikolaou, Nikos
  • Sanfeliu Cortés, Alberto
  • Garrell Zulueta, Anais
  • Markakis, Evangelos
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., This paper introduces TORNADO, a cloud-integrated robotics platform designed to tackle the challenges of autonomous manipulation in dynamic indoor environments, particularly those involving small, soft, or deformable objects. TORNADO integrates large-scale foundation models for perception, language comprehension, and high-level reasoning, to achieve strong zero-shot generalization across a wide range of tasks. At its core, the platform features an adaptive cognitive pipeline capable of dynamically reconfiguring its modules—including semantic 3D SLAM, people-aware navigation, dexterous manipulation, and human-in-the-loop learning—to manage uncertainty and adapt to changing conditions. Additionally, TORNADO incorporates a multi-modal Learning-from-Demonstration interface and an Explainable AI engine, enhancing transparency and easing the burden of teaching new tasks. The system is validated through three industry-relevant scenarios: (1) flexible gear and ply-sheet handling in a mechanical parts factory, (2) patient support in a hospital palliative ward, and (3) product sampling and waste management in a distribution center. TORNADO aims to significantly improve the agility, safety, and overall task performance of mobile manipulators operating in dynamic, human-centric environments., The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The work was supported by the European Union through the research and innovation program under Grant No. 101189557 (TORNADO). In addition, certain sections may include content generated or refined by AI, any of which has been carefully reviewed, edited, and integrated by the authors., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

AI or human? Understanding perceptions of embodied robots with LLMs

  • Hriscu Acsinte-Staut, Lavinia Beatrice
  • Sanfeliu Cortés, Alberto
  • Garrell Zulueta, Anais
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The pursuit of artificial intelligence has long been associated to the the challenge of effectively measuring intelligence. Even if the Turing Test was introduced as a means of assessing a system's intelligence, its relevance and application within the field of human-robot interaction remain largely underexplored. This study investigates the perception of intelligence in embodied robots by performing a Turing Test within a robotic platform. A total of 34 participants were tasked with distinguishing between AI- and human-operated robots while engaging in two interactive tasks: an information retrieval and a package handover. These tasks assessed the robot’s perception and navigation abilities under both static and dynamic conditions. Results indicate that participants were unable to reliably differentiate between AI- and human-controlled robots beyond chance levels. Furthermore, analysis of participant responses reveals key factors influencing the perception of artificial versus human intelligence in embodied robotic systems. These findings provide insights into the design of future interactive robots and contribute to the ongoing discourse on intelligence assessment in AI-driven systems., This work has been supported by JST Moonshot R & D (JPMJMS2011-85) and the European project TORNADO with grant number HORIZONCL4-2024-DIGITAL-EMERGING-01-101189557, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Human perception in social tasks: a comparative evaluation of autonomous and teleoperated robots

  • Hriscu Acsinte-Staut, Lavinia Beatrice
  • Sanfeliu Cortés, Alberto
  • Garrell Zulueta, Anais
© 2025 The Authors. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/, Robots and artificial intelligence technologies are becoming increasingly integrated into our daily lives. The introduction of humanoid robots into everyday settings is a gradual but ongoing process—one that society is already beginning to navigate. Yet this shift raises important questions: Who or what is truly behind these physical agents? And can we, as users, perceive differences in our interactions depending on whether a robot acts autonomously or it’s teleoperated by a human? In this study, we present the results of an experiment in which participants interacted with a robot under two control conditions—autonomous and teleoperated—while it performed two distinct tasks in both static and dynamic movement scenarios. In our results, human operators outperformed autonomous systems in tasks requiring spatial awareness and contextual reasoning. Conversely, the autonomous robot—powered by a Large Language Model and operating without visual input—was perceived more favorably in tasks that demanded rapid access to broad and diverse information., This work was supported in part by JST Moonshot R, D under Grant JPMJMS2011-85, in part by the Spanish Ministry of Science, Innovation and Universities under the project LENA under Grant PID2022-142039NA-I00, funded by MCIU/AEI/10.13 039/50110001103, in part by the European project TORNADO under Grant HORIZON-CL4-2024-DIGITAL-EMERGING-01-101189557, and in part by Predoctoral Program AGAUR-FI ajuts under Grant 2025FI-101034 Joan Oró, through the Secretariat of Universities and Research of Department of Research and Universities of the Generalitat of Catalonia and European Social Plus Fund. (Corresponding author: Lavinia Hriscu.), Peer Reviewed, Postprint (published version)