Pasar al contenido principal

APRENDIZAJE CONTINUO PARA LA NAVEGACION DE ROBOTS CON INTERACCIONES HUMANAS

PID2022-142039NA-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 21
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Probabilistic Graph-Based Real-Time Ground Segmentation for Urban Robotics

  • del Pino, Iván
  • Santamaria-Navarro, Angel
  • Garrell Zulueta, Anaís
  • Torres, Fernando
  • Andrade-Cetto, Juan
  • Torres, Fernando|||/items/17ced7cb-5c1d-429d-b922-315f91fddc33
Terrain analysis is of paramount importance for the safe navigation of autonomous robots. In this study, we introduce GATA, a probabilistic real-time graph-based method for segmentation and traversability analysis of point clouds. In the method, we iteratively refine the parameters of a ground plane model and identify regions imaged by a LiDAR as traversable and non-traversable. The method excels in delivering rapid, high-precision obstacle detection, surpassing existing state-of-the-art methods. Furthermore, our method addresses the need to distinguish between surfaces with varying traversability, such as vegetation or unpaved roads, depending on the specific application. To achieve this, we integrate a shallow neural network, which operates on features extracted from the ground model. This enhancement not only boosts performance but also maintains real-time efficiency, without the need for GPUs. The method is rigorously evaluated using the SemanticKitti dataset and its practicality is showcased through real-world experiments with an urban last-mile delivery autonomous robot.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Toward the Deployment of an Autonomous Last-Mile Delivery Robot in Urban Areas: The Ona Prototype Platform

  • Santamaria-Navarro, Angel
  • Hernández, Sergi
  • Herrero, Fernando
  • López, Alejandro
  • del Pino, Iván
  • Rodríguez-Linares, Nicolás
  • Fernández, Carlos
  • Baldó, Albert
  • Lemardelé, Clément
  • Garrell Zulueta, Anaís
  • Vallvé, Joan
  • Taher, Hafsa
  • Puig-Pey, Ana M.
  • Pagès, Laia
  • Sanfeliu, Alberto
Nowadays, the skyrocketing last-mile freight transportation in urban areas is leading to very negative effects (e.g., pollution, noise or traffic congestion), which could be minimized by using autonomous electric vehicles. In this sense, this paper presents the first prototype of Ona, an autonomous last-mile delivery robot that, in contrast to existing platforms, has a medium-sized storage capacity with the capability of navigating in both street and pedestrian areas. Here, we describe the platform and position it with respect to other existing prototypes, providing its main Software modules and the first validation experiments, carried out in the Barcelona Robot Lab (Universitat Politècnica de Catalunya); Esplugues de Llobregat (next to Barcelona); and Debrecen (Hungary), which are representative urban scenarios. In such validations, we focus our analysis on the key localization module, whose errors could cascade down the rest of the navigation pipeline (e.g., planning or control). Aside from robotic technical details, we also include the results of the technology acceptance by the public present in the Esplugues de Llobregat test, collected in situ through a survey.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challenges

  • Teja Singamaneni, Phani
  • Bachiller-Burgos, Pilar
  • Manso, Luis J.
  • Garrell, Anaís
  • Sanfeliu, Alberto
  • Spalanzani, Anne
  • Alami, Rachid
Socially aware robot navigation is gaining popularity with the increase in delivery and assistive robots. The research is further fueled by a need for socially aware navigation skills in autonomous vehicles to move safely and appropriately in spaces shared with humans. Although most of these are ground robots, drones are also entering the field. In this paper, we present a literature survey of the works on socially aware robot navigation in the past 10 years. We propose four different faceted taxonomies to navigate the literature and examine the field from four different perspectives. Through the taxonomic review, we discuss the current research directions and the extending scope of applications in various domains. Further, we put forward a list of current research opportunities and present a discussion on possible future challenges that are likely to emerge in the field., This work was supported by the Horizon Europe Framework Programme [Grant: euROBIN 101070596]; Agence Nationale de la Recherche [Grant: ANITI ANR-19-PI3A-0004]; European project CANOPIES [Grant: H2020-ICT-2020-2-101016906]; Spanish Government (MCIN/AEI) and European Union (“NextGenerationEU”/PRTR) [Grant: TED2021-131739-C22]; Spanish Government (MCIN) [Grant: PDC2022-133597-C41]; Spanish Government (MCIN) [Grant: PID2022-142039NA-I00]., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Probabilistic Graph-based Real-Time Ground Segmentation for Urban Robotics

  • Pino, Iván del
  • Santamaria-Navarro, Àngel
  • Garrell, Anaís
  • Torres, Fernando
  • Andrade-Cetto, Juan
Terrain analysis is of paramount importance for the safe navigation of autonomous robots. In this study, we introduce GATA, a probabilistic real-time graph-based method for segmentation and traversability analysis of point clouds. In the method, we iteratively refine the parameters of a ground plane model and identify regions imaged by a LiDAR as traversable and non-traversable. The method excels in delivering rapid, high-precision obstacle detection, surpassing existing state-of-the-art methods. Furthermore, our method addresses the need to distinguish between surfaces with varying traversability, such as vegetation or unpaved roads, depending on the specific application. To achieve this, we integrate a shallow neural network, which operates on features extracted from the ground model. This enhancement not only boosts performance but also maintains real-time efficiency, without the need for GPUs. The method is rigorously evaluated using the SemanticKitti dataset and its practicality is showcased through real-world experiments with an urban last-mile delivery autonomous robot. The code is publicly available at <uri>https://gitlab.iri.upc.edu/idelpino/iri_ground_segmentation</uri>, This work was supported in part by the EIT Urban Mobility project LOGISMILE under Grant EIT-UM-2020-22140 and Grant EIT-UM-2023-23374, in part by the Spanish Projects EBCON under Grant PID2020-119244GB-I00, in part by MCIN/AEI/10.13039/501100011033, AUDEL under Grant TED2021- 131759A-I00, in part by MCIN/ AEI/10.13039/501100011033, in part by the “European Union NextGenerationEU/PRTR” and LENA under Grant PID2022- 142039NA-I00, in part by MCIN/ AEI/10.13039/501100011033, in part by “ERDF A way of making Europe”, in part by BotNet under Grant 23S06128-00, in part by the “Ajuntament de Barcelona” and “Fundació la Caixa”, in part by the Consolidated Research Group RAIG under Grant 2021 SGR 00510 of the Departament de Recerca i Universitats de la Generalitat de Catalunya, in part by aMargarita Salas Fellowship to IDP (MARSALAS21-08) funded by the Spanish Ministry of Universities, in part by the European Union-Next Generation, and in part by the University of Alicante., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Toward the Deployment of an Autonomous Last-Mile Delivery Robot in Urban Areas: The Ona Prototype Platform

  • Santamaria-Navarro, Àngel
  • Hernandez, Sergi
  • Herrero, Fernando
  • Lopez, Alejandro
  • Del Pino, Ivan
  • Rodriguez-Linares, Nicolas
  • Fernández, Carlos
  • Baldo, Albert
  • Lemardele, Clement
  • Garrell, Anaís
  • Vallvé, Joan
  • Taher, Hafsa
  • Puig-Pey, Ana M.
  • Pages, Laia
  • Sanfeliu, Alberto
Nowadays, the skyrocketing last-mile freight transportation in urban areas is leading to very negative effects (e.g., pollution, noise or traffic congestion), which could be minimized by using autonomous electric vehicles. In this sense, this paper presents the first prototype of Ona, an autonomous last-mile delivery robot that, in contrast to existing platforms, has a medium-sized storage capacity with the capability of navigating in both street and pedestrian areas. Here, we describe the platform and position it with respect to other existing prototypes, providing its main Software modules and the first validation experiments, carried out in the Barcelona Robot Lab (Universitat Politècnica de Catalunya); Esplugues de Llobregat (next to Barcelona); and Debrecen (Hungary), which are representative urban scenarios. In such validations, we focus our analysis on the key localization module, whose errors could cascade down the rest of the navigation pipeline (e.g., planning or control). Aside from robotic technical details, we also include the results of the technology acceptance by the public present in the Esplugues de Llobregat test, collected in situ through a survey., This work has been partially supported by the European Union project LogiSmile (EIT-UM-2020-22140); by Horizon Europe under Grant agreement 101168042 [auTonomous Robotic aId For increasing FIrst responDers efficiency TRIFFID]; by the Spanish Ministry of Science and Innovation under the projects Autonomous package delivery in urban areas (AUDEL) (TED2021-131759A-I00, funded by MCIN/AEI/10.13039/501100011033 and by the” European Union NextGenerationEU/PRTR”) and Lifelong navigation learning using human-robot interaction (LENA) (PID2022-142039NA- I0 0, funded by MCIN/ AEI/10.13039/501100011033 and by “ERDF A way of making Europe”); by the Nou model de repartiment de paquets en superilles urbanes mitjançant una xarxa de vehicles elèctrics autònoms (BotNet) project (23S06128-00), funded by the Ajuntament de Barcelona and Fundació la Caixa; and by the Consolidated Research Group RAIG (Mobile Robotics and Artificial Intelligence Group, 2021 SGR 00510) of the Departament de Recerca i Universitats de la Generalitat de Catalunya. We thank the Spanish Ministerio de Universidades, the European Union-Next Generation and the University of Alicante for the financial support ( Margarita Salas, MARSALAS21-08). This article has supplementary downloadable material available at https://doi.org/10.1109/ MRA.2024.3487321, provided by the authors, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Leveraging Pedestrian Detection and Tracking in Robotics Navigation: A Survey With Practical Illustrations

  • Picello, Niko
  • Herrero, Fernando
  • Hernàndez, Sergi
  • López Gestoso, Alejandro
  • Santamaria-Navarro, Àngel
Pedestrian Detection and Tracking (PDT) plays a pivotal role in enabling autonomous robots to navigate safely and efficiently in dynamic, human-populated environments. This paper presents a comprehensive survey of PDT methods, structured according to the sensing modalities employed: RGB cameras, LiDAR, thermal imaging, RGB-D sensors, and multi-modal fusion systems. For each category, we analyze representative techniques, synthesize their strengths and limitations, and discuss recent advancements including deep learning approaches and cross-modal fusion strategies. We highlight persistent challenges such as handling occlusions, achieving real-time performance, and ensuring robustness across diverse environments. In addition to this structured review, we provide two practical examples using the Ona autonomous robot platform (see Figure ) to illustrate how PDT techniques can enhance robotic capabilities in real-world scenarios. These examples focus on improving SLAM consistency and enabling proxemic-aware navigation strategies. Through this survey, we aim to clarify the current state of the art, identify emerging trends, and suggest future research directions for robust and socially-aware robotic navigation., This work has been partially supported by Horizon Europe under the grant agreement No. 101168042 (TRIFFID: auTonomous Robotic aId For increasing FIrst responDers efficiency); by the Spanish Ministry of Science and Innovation under the project ‘‘LENA: Lifelong navigation learning using human-robot interaction’’ (PID2022-142039NA-I00, funded by the ‘‘Ministerio de Ciencia, Innovación y Universidades’’ through the ‘‘Agencia Estatal de Investigación’’, MCIN/AEI/10.13039/501100011033 and by the European Regional Development Fund, ‘‘ERDF A way of making Europe’’); by the project ‘‘BotNet: Nou model de repartiment de paquets en superilles urbanes mitjançant una xarxa de vehicles elèctrics autònoms’’ (23S06128-00), funded by the ‘‘Ajuntament de Barcelona’’ and ‘‘Fundació la Caixa’’; and by the Consolidated Research Group ‘‘RAIG: Mobile Robotics and Artificial Intelligence Group’’ (2021 SGR 00510) of the ‘‘Departament de Recerca i Universitats de la Generalitat de Catalunya’’., Peer reviewed
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
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)

Negotiation of assignation plans in human-robot team task scheduling

  • Fuster Pala, Llum
  • Dalmasso Blanch, Marc|||0000-0003-1734-7863
  • Aubach Altes, Artur
  • Izquierdo Badiola, Silvia
  • 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., In recent years, considerable attention has been given to improving human-robot collaboration. Despite advances in robotic capabilities and interaction techniques, achieving a fair distribution of tasks remains challenging due to the dynamic nature of human preferences and situational constraints. This paper presents a novel negotiation framework that enables robots to effectively communicate with humans to facilitate fair and adaptive task allocation. Our approach leverages automated planning techniques with the Planning Domain Definition Language (PDDL), explicitly encoding tasks, constraints, and preferences from both human and robotic perspectives. Task allocation is optimized based on three key criteria: the robot’s effort, the human’s effort, and overall task success. Additionally, we integrate a Natural Language Processing (NLP) model that interprets human preferences and informs the negotiation process, ensuring that the robot generates task proposals aligned with human input. The negotiation follows an alternating-offer protocol, with the robot employing a sigmoid conceder strategy to iteratively refine task allocation, leading to balanced and mutually acceptable plans. To evaluate our approach, we conduct a comprehensive user study with non-trained volunteers interacting with the robot, assessing the effectiveness, fairness, and adaptability of the proposed system in real-world scenarios., This work was partially supported by JST Moonshot R, D grant number JPMJMS2011 and LENA project (PID2022-142039NA-I00), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Enhancing context-aware human motion prediction for efficient robot handovers

  • Gomez Izquierdo, Gerard
  • Laplaza Galindo, Javier|||0000-0003-4864-5759
  • 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., Accurate human motion prediction (HMP) is critical for seamless human-robot collaboration, particularly in handover tasks that require real-time adaptability. Despite the high accuracy of state-of-the-art models, their computational complexity limits practical deployment in real-world robotic applications. In this work, we enhance human motion forecasting for handover tasks by leveraging siMLPe [1], a lightweight yet powerful architecture, and introducing key improvements. Our approach, named IntentMotion incorporates intention-aware conditioning, task-specific loss functions, and a novel intention classifier, significantly improving motion prediction accuracy while maintaining efficiency. Experimental results demonstrate that our method reduces body loss error by over 50%, achieves 200× faster inference, and requires only 3% of the parameters compared to existing state-of-the-art HMP models in robotics. These advancements establish our framework as a highly efficient and scalable solution for real-time human-robot interaction., This work was partially supported by JST Moonshot R, D grant number JPMJMS2011 and LENA (PID2022-142039NA-I00), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

A survey on socially aware robot navigation: Taxonomy and future challenges

  • Singamaneni, Phani Teja
  • Bachiller Burgos, Pilar
  • Manso, Luis J.
  • Garrell Zulueta, Anais|||0000-0002-4629-0723
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
  • Spalanzani, Anne
  • Alami, Rachid
Socially aware robot navigation is gaining popularity with the increase in delivery and assistive robots. The research is further fueled by a need for socially aware navigation skills in autonomous vehicles to move safely and appropriately in spaces shared with humans. Although most of these are ground robots, drones are also entering the field. In this paper, we present a literature survey of the works on socially aware robot navigation in the past 10 years. We propose four different faceted taxonomies to navigate the literature and examine the field from four different perspectives. Through the taxonomic review, we discuss the current research directions and the extending scope of applications in various domains. Further, we put forward a list of current research opportunities and present a discussion on possible future challenges that are likely to emerge in the field., This work was supported by the Horizon Europe Framework Programme [Grant: euROBIN 101070596]; Agence Nationale de la Recherche [Grant: ANITI ANR-19-PI3A0004]; European project CANOPIES [Grant: H2020ICT-2020-2-101016906]; Spanish Government (MCIN/AEI) and European Union (“NextGenerationEU”/PRTR) [Grant: TED2021-131739-C22]; Spanish Government (MCIN) [Grant: PDC2022-133597-C41]; Spanish Government (MCIN) [Grant: PID2022-142039NA-I00]., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Leveraging pedestrian detection and tracking in robotics navigation: a survey with practical illustrations

  • Picello, Niko
  • Herrero Cotarelo, Fernando|||0000-0003-4116-0265
  • Hernández Juan, Sergi
  • López Gestoso, Alejandro|||0009-0008-9731-2145
  • Santamaria Navarro, Àngel|||0000-0002-6328-1423
Pedestrian Detection and Tracking (PDT) plays a pivotal role in enabling autonomous robots to navigate safely and efficiently in dynamic, human-populated environments. This paper presents a comprehensive survey of PDT methods, structured according to the sensing modalities employed: RGB cameras, LiDAR, thermal imaging, RGB-D sensors, and multi-modal fusion systems. For each category, we analyze representative techniques, synthesize their strengths and limitations, and discuss recent advancements including deep learning approaches and cross-modal fusion strategies. We highlight persistent challenges such as handling occlusions, achieving real-time performance, and ensuring robustness across diverse environments. In addition to this structured review, we provide two practical examples using the Ona autonomous robot platform (see Figure 1) to illustrate how PDT techniques can enhance robotic capabilities in real-world scenarios. These examples focus on improving SLAM consistency and enabling proxemic-aware navigation strategies. Through this survey, we aim to clarify the current state of the art, identify emerging trends, and suggest future research directions for robust and socially-aware robotic navigation., This work has been partially supported by Horizon Europe under the grant agreement No. 101168042 (TRIFFID: auTonomous Robotic aId For increasing FIrst responDers efficiency); by the Spanish Ministry of Science and Innovation under the project ‘‘LENA: Lifelong navigation learning using human-robot interaction’’ (PID2022-142039NA-I00, funded by the ‘‘Ministerio de Ciencia, Innovación y Universidades’’ through the ‘‘Agencia Estatal de Investigación’’, MCIN/AEI/10.13039/501100011033 and by the European Regional Development Fund, ‘‘ERDF A way of making Europe’’); by the project ‘‘BotNet: Nou model de repartiment de paquets en superilles urbanes mitjançant una xarxa de vehicles elèctrics autònoms’’ (23S06128-00), funded by the ‘‘Ajuntament de Barcelona’’ and ‘‘Fundació la Caixa’’; and by the Consolidated Research Group ‘‘RAIG: Mobile Robotics and Artificial Intelligence Group’’ (2021 SGR 00510) of the ‘‘Departament de Recerca i Universitats de la Generalitat de Catalunya’’., 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
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Personalised explainable robots using LLMs

  • Gebellí Guinjoan, Ferran
  • Hriscu Acsinte-Staut, Lavinia Beatrice
  • Ros, Raquel
  • Lemaignan, Séverin
  • Sanfeliu Cortés, Alberto|||0000-0003-3868-9678
  • Garrell Zulueta, Anais|||0000-0002-4629-0723
In the field of Human-Robot Interaction (HRI), a key challenge lies in enabling humans to comprehend the decisions and behaviours of robots. One promising approach involves leveraging Theory of Mind (ToM) frameworks, wherein a robot estimates the mental model that a user holds about its functioning and compares this with the representation of its internal mental model. This comparison allows the robot to identify potential mismatches and generate communicative actions to bridge such gaps. Effective communication requires the robot to maintain unique mental models for each user and personalise explanations based on past interactions. To address this, we propose an architecture grounded in Large Language Models (LLMs) that operationalises this theoretical framework. We demonstrate the feasibility of this approach through qualitative examples, showcasing responses provided by a robot patrolling a geriatric hospital., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Negotiation of assignation plans in human-robot team task scheduling

  • Fuster Pala, Llum
  • Dalmasso Blanch, Marc
  • Aubach Altes, Artur
  • Izquierdo Badiola, Silvia
  • 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., In recent years, considerable attention has been given to improving human-robot collaboration. Despite advances in robotic capabilities and interaction techniques, achieving a fair distribution of tasks remains challenging due to the dynamic nature of human preferences and situational constraints. This paper presents a novel negotiation framework that enables robots to effectively communicate with humans to facilitate fair and adaptive task allocation. Our approach leverages automated planning techniques with the Planning Domain Definition Language (PDDL), explicitly encoding tasks, constraints, and preferences from both human and robotic perspectives. Task allocation is optimized based on three key criteria: the robot’s effort, the human’s effort, and overall task success. Additionally, we integrate a Natural Language Processing (NLP) model that interprets human preferences and informs the negotiation process, ensuring that the robot generates task proposals aligned with human input. The negotiation follows an alternating-offer protocol, with the robot employing a sigmoid conceder strategy to iteratively refine task allocation, leading to balanced and mutually acceptable plans. To evaluate our approach, we conduct a comprehensive user study with non-trained volunteers interacting with the robot, assessing the effectiveness, fairness, and adaptability of the proposed system in real-world scenarios., This work was partially supported by JST Moonshot R, D grant number JPMJMS2011 and LENA project (PID2022-142039NA-I00), funded by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Body gestures recognition for social human-robot interaction

  • Laplaza Galindo, Javier
  • Sanfeliu Cortés, Alberto
  • Garrell Zulueta, Anais
In this paper, a solution for human gesture classification is proposed. The solution uses a Deep Learning model and is meant to be useful for non-verbal communication between humans and robots. The research focuses on the creation of the “temPoral bOdy geSTUre REcognition model” (POSTURE) that can recognise continuous gestures performed in real-life situations. The suggested model takes into account spatial and temporal components so as to achieve the recognition of more natural and intuitive gestures. In a first step, a framework extracts from all the images the corresponding landmarks for each of the body joints. Next, some data filtering techniques are applied with the aim of avoiding problems related with the data. And finally, different neural network configurations and approaches are tested to find the optimal performance. The validation of the model is accomplished throughout an extensive set of simulations and real-life experiments., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Leveraging pedestrian detection and tracking in robotics navigation: a survey with practical illustrations

  • Picello, Niko
  • Herrero Cotarelo, Fernando
  • Hernández Juan, Sergi
  • López Gestoso, Alejandro
  • Santamaria Navarro, Àngel
Pedestrian Detection and Tracking (PDT) plays a pivotal role in enabling autonomous robots to navigate safely and efficiently in dynamic, human-populated environments. This paper presents a comprehensive survey of PDT methods, structured according to the sensing modalities employed: RGB cameras, LiDAR, thermal imaging, RGB-D sensors, and multi-modal fusion systems. For each category, we analyze representative techniques, synthesize their strengths and limitations, and discuss recent advancements including deep learning approaches and cross-modal fusion strategies. We highlight persistent challenges such as handling occlusions, achieving real-time performance, and ensuring robustness across diverse environments. In addition to this structured review, we provide two practical examples using the Ona autonomous robot platform (see Figure 1) to illustrate how PDT techniques can enhance robotic capabilities in real-world scenarios. These examples focus on improving SLAM consistency and enabling proxemic-aware navigation strategies. Through this survey, we aim to clarify the current state of the art, identify emerging trends, and suggest future research directions for robust and socially-aware robotic navigation., This work has been partially supported by Horizon Europe under the grant agreement No. 101168042 (TRIFFID: auTonomous Robotic aId For increasing FIrst responDers efficiency); by the Spanish Ministry of Science and Innovation under the project ‘‘LENA: Lifelong navigation learning using human-robot interaction’’ (PID2022-142039NA-I00, funded by the ‘‘Ministerio de Ciencia, Innovación y Universidades’’ through the ‘‘Agencia Estatal de Investigación’’, MCIN/AEI/10.13039/501100011033 and by the European Regional Development Fund, ‘‘ERDF A way of making Europe’’); by the project ‘‘BotNet: Nou model de repartiment de paquets en superilles urbanes mitjançant una xarxa de vehicles elèctrics autònoms’’ (23S06128-00), funded by the ‘‘Ajuntament de Barcelona’’ and ‘‘Fundació la Caixa’’; and by the Consolidated Research Group ‘‘RAIG: Mobile Robotics and Artificial Intelligence Group’’ (2021 SGR 00510) of the ‘‘Departament de Recerca i Universitats de la Generalitat de Catalunya’’., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Enhancing context-aware human motion prediction for efficient robot handovers

  • Gomez Izquierdo, Gerard
  • Laplaza Galindo, Javier
  • 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., Accurate human motion prediction (HMP) is critical for seamless human-robot collaboration, particularly in handover tasks that require real-time adaptability. Despite the high accuracy of state-of-the-art models, their computational complexity limits practical deployment in real-world robotic applications. In this work, we enhance human motion forecasting for handover tasks by leveraging siMLPe [1], a lightweight yet powerful architecture, and introducing key improvements. Our approach, named IntentMotion incorporates intention-aware conditioning, task-specific loss functions, and a novel intention classifier, significantly improving motion prediction accuracy while maintaining efficiency. Experimental results demonstrate that our method reduces body loss error by over 50%, achieves 200× faster inference, and requires only 3% of the parameters compared to existing state-of-the-art HMP models in robotics. These advancements establish our framework as a highly efficient and scalable solution for real-time human-robot interaction., This work was partially supported by JST Moonshot R, D grant number JPMJMS2011 and LENA (PID2022-142039NA-I00), funded by MCIN/AEI/10.13039/501100011033., 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)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Personalised explainable robots using LLMs

  • Gebellí Guinjoan, Ferran
  • Hriscu Acsinte-Staut, Lavinia Beatrice
  • Ros, Raquel
  • Lemaignan, Séverin
  • Sanfeliu Cortés, Alberto
  • Garrell Zulueta, Anais
In the field of Human-Robot Interaction (HRI), a key challenge lies in enabling humans to comprehend the decisions and behaviours of robots. One promising approach involves leveraging Theory of Mind (ToM) frameworks, wherein a robot estimates the mental model that a user holds about its functioning and compares this with the representation of its internal mental model. This comparison allows the robot to identify potential mismatches and generate communicative actions to bridge such gaps. Effective communication requires the robot to maintain unique mental models for each user and personalise explanations based on past interactions. To address this, we propose an architecture grounded in Large Language Models (LLMs) that operationalises this theoretical framework. We demonstrate the feasibility of this approach through qualitative examples, showcasing responses provided by a robot patrolling a geriatric hospital., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

A survey on socially aware robot navigation: Taxonomy and future challenges

  • Singamaneni, Phani Teja
  • Bachiller Burgos, Pilar
  • Manso, Luis J.
  • Garrell Zulueta, Anais
  • Sanfeliu Cortés, Alberto
  • Spalanzani, Anne
  • Alami, Rachid
Socially aware robot navigation is gaining popularity with the increase in delivery and assistive robots. The research is further fueled by a need for socially aware navigation skills in autonomous vehicles to move safely and appropriately in spaces shared with humans. Although most of these are ground robots, drones are also entering the field. In this paper, we present a literature survey of the works on socially aware robot navigation in the past 10 years. We propose four different faceted taxonomies to navigate the literature and examine the field from four different perspectives. Through the taxonomic review, we discuss the current research directions and the extending scope of applications in various domains. Further, we put forward a list of current research opportunities and present a discussion on possible future challenges that are likely to emerge in the field., This work was supported by the Horizon Europe Framework Programme [Grant: euROBIN 101070596]; Agence Nationale de la Recherche [Grant: ANITI ANR-19-PI3A0004]; European project CANOPIES [Grant: H2020ICT-2020-2-101016906]; Spanish Government (MCIN/AEI) and European Union (“NextGenerationEU”/PRTR) [Grant: TED2021-131739-C22]; Spanish Government (MCIN) [Grant: PDC2022-133597-C41]; Spanish Government (MCIN) [Grant: PID2022-142039NA-I00]., Peer Reviewed, Postprint (author's final draft)