Garrell Zulueta, Anais
Total activity: 17
Institute
Institute of Robotics and Industrial Informatics
E-mail
agarrelliri.upc.es
Contact details
UPC directory Open in new window

Graphic summary
  • Show / hide key
  • Information


Scientific and technological production
  •  

1 to 17 of 17 results
  • Access to the full text
    Robot interactive learning through human assistance  Open access

     Ferrer Minguez, Gonzalo; Garrell Zulueta, Anais; Villamizar Vergel, Michael Alejandro; Huerta Casado, Iván; Sanfeliu Cortes, Alberto
    DOI: 10.1007/978-3-642-35932-3_11
    Date of publication: 2013
    Book chapter

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Postprint (author’s final draft)

  • Cooperative social robots: accompanying, guiding and interacting with people  Open access

     Garrell Zulueta, Anais
    Universitat Politècnica de Catalunya
    Theses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    El desenvolupament de robots socials capaços d'interactuar amb els éssers humans és un dels principals reptes en el camp de la robòtica. Actualment, els robots comencen a aparèixer en entorns dinàmics, com zones de vianants, universitats o hospitals; per aquest motiu, aquesta interacció ha de realitzar-se de manera natural, progressiva i cordial, ja que la seva utilització pot ser col.laboració, assistència o ajuda a les persones. Per tant, la navegació i la interacció amb els humans, en aquests entorns, són habilitats importants que les futures generacions de robots han de posseir, a més a més, els robots han de ser aptes de cooperar entre ells si fos requerit. El present treball estudia aquests reptes plantejats. S¿han desenvolupat un conjunt de tècniques que permeten als robots interectuar de manera natural amb les persones i el seu entorn, mentre que guien o acompanyen als humans en zones urbanes. En aquest sentit, el moviment dels robots s¿inspira en la manera com es mouen els humans en les convenvions socials, així com l¿espai personal.El primer punt que aquesta tesi comprèn és el desenvolupament d¿un nou mètode per a "robots-acompanyants" basat en el nou model estès de forces socials. S¿ha evaluat com es mouen les persones i s¿han formulat un conjunt de forces socials virtuals que descriuren el comportament del robot en termes de moviments. Aquesta evaluació es basa en el concepte de ¿proxemics¿ i assegura que la navegació del robot està socialment acceptada per la persona que està sent acompanyada i per la gent que es troba a l¿entorn. Per mitjà d¿un estudi social, mostrem que els humans interpreten el comportament del robot d¿acord amb les normes socials. Així mateix, un nou sistema per a guiar a persones en zones urbanes amb un conjunt de robots mòbils que cooperen és presentat. El model proposat ofereix diferents avantatges comparat amb treballs anteriors. Primer, es permet a un grup de persones ser guiades en entorns oberts o amb alta densitat d¿obstacles; segon, s¿utilitzen diferents robots que cooperen; tercer, els robots són capaços de reincorporar a la formació les persones que s¿han allunyat del grup anteriorment de manera segura. La base del nostre enfocament es basa en el nou model anomenat ¿Discrete Time Motion¿, el qual representa els movimients dels humans i els robots, prediu el comportament de les persones, i planeja i proporciona una ruta als robots.Posteriorment, aquesta tesi va un pas més enllà amb el desenvolupament del model ¿Prediction and Anticipation Model¿. Aquest model ens permet determinar la distribució òptima de robots per a prevenir que les persones s¿allunyin del grup en zones especíifiques del mapa, i per tant facilitar la tasca dels robots. A més, s¿optimitza localment el treball realitzat pels robots i les persones, produint d¿aquesta manera un moviment més amigable.Finalment, s¿introdueix un robot autònom mòbil capaç d¿interactuar amb les persones per realitzar un aprenentatge assistit. Incialment, es presenten diferents comportaments del robot per apropar-se a una persona i crear un víincle amb ell/ella. Basant-nos en aquesta idea, un mòdul visual per a la detecció de cares humanes en temps real va ser proporcionat al robot. Hem observat que les persones atribueixen diferents personalitats al robot en funció dels seus diferents comportaments. Una vegada que el contacte va ser iniciat es va donar l¿oportunitat als voluntaris d¿ajudar al robot per a millorar les seves habilitats visuals. Després d¿aquesta etapa d¿aprenentatge assistit, el robot va ser capaç d¿identificar a les persones mitjançant l'ús de mètodes visuals.En resum, aquesta tesi presenta i demostra la necessitat de robots que siguin capaços d¿operar de forma acceptable amb la gent i que es comportin d¿acord amb les normes socials mentres acompanyen o guien a persones. Per altra banda, aquest treball mostra que la coperació entre un grup de robots pot optimitzar el rendiment tant dels robots com dels humans.

    The development of social robots capable of interacting with humans is one of the principal challenges in the field of robotics. More and more, robots are appearing in dynamic environments, like pedestrian walkways, universities, and hospitals; for this reason, their interaction with people must be conducted in a natural, gradual, and cordial manner, given that their function could be aid, or assist people. Therefore, navigation and interaction among humans in these environments are key skills that future generations of robots will require to have. Additionally, robots must also be able to cooperate with each other, if necessary. This dissertation examines these various challenges and describes the development of a set of techniques that allow robots to interact naturally with people in their environments, as they guide or accompany humans in urban zones. In this sense, the robots' movements are inspired by the persons' actions and gestures, determination of appropriate personal space, and the rules of common social convention. The first issue this thesis tackles is the development of an innovative robot-companion approach based on the newly founded Extended Social-Forces Model. We evaluate how people navigate and we formulate a set of virtual social forces to describe robot's behavior in terms of motion. Moreover, we introduce a robot companion analytical metric to effectively evaluate the system. This assessment is based on the notion of "proxemics" and ensures that the robot's navigation is socially acceptable by the person being accompanied, as well as to other pedestrians in the vicinity. Through a user study, we show that people interpret the robot's behavior according to human social norms. In addition, a new framework for guiding people in urban areas with a set of cooperative mobile robots is presented. The proposed approach offers several significant advantages, as compared with those outlined in prior studies. Firstly, it allows a group of people to be guided within both open and closed areas; secondly, it uses several cooperative robots; and thirdly, it includes features that enable the robots to keep people from leaving the crowd group, by approaching them in a friendly and safe manner. At the core of our approach, we propose a "Discrete Time Motion" model, which works to represent human and robot motions, to predict people's movements, so as to plan a route and provide the robots with concrete motion instructions. After, this thesis goes one step forward by developing the "Prediction and Anticipation Model". This model enables us to determine the optimal distribution of robots for preventing people from straying from the formation in specific areas of the map, and thus to facilitate the task of the robots. Furthermore, we locally optimize the work performed by robots and people alike, and thereby yielding a more human-friendly motion. Finally, an autonomous mobile robot capable of interacting to acquire human-assisted learning is introduced. First, we present different robot behaviors to approach a person and successfully engage with him/her. On the basis of this insight, we furnish our robot with a simple visual module for detecting human faces in real-time. We observe that people ascribe different personalities to the robot depending on its different behaviors. Once contact is initiated, people are given the opportunity to assist the robot to improve its visual skills. After this assisted learning stage, the robot is able to detect people by using the enhanced visual methods. Both contributions are extensively and rigorously tested in real environments. As a whole, this thesis demonstrates the need for robots that are able to operate acceptably around people; to behave in accordance with social norms while accompanying and guiding them. Furthermore, this work shows that cooperation amongst a group of robots optimizes the performance of the robots and people as well.

    El desenvolupament de robots socials capaços d'interactuar amb els éssers humans és un dels principals reptes en el camp de la robòtica. Actualment, els robots comencen a aparèixer en entorns dinàmics, com zones de vianants, universitats o hospitals; per aquest motiu, aquesta interacció ha de realitzar-se de manera natural, progressiva i cordial, ja que la seva utilització pot ser col.laboració, assistència o ajuda a les persones. Per tant, la navegació i la interacció amb els humans, en aquests entorns, són habilitats importants que les futures generacions de robots han de posseir, a més a més, els robots han de ser aptes de cooperar entre ells si fos requerit. El present treball estudia aquests reptes plantejats. S’han desenvolupat un conjunt de tècniques que permeten als robots interectuar de manera natural amb les persones i el seu entorn, mentre que guien o acompanyen als humans en zones urbanes. En aquest sentit, el moviment dels robots s’inspira en la manera com es mouen els humans en les convenvions socials, així com l’espai personal.El primer punt que aquesta tesi comprèn és el desenvolupament d’un nou mètode per a "robots-acompanyants" basat en el nou model estès de forces socials. S’ha evaluat com es mouen les persones i s’han formulat un conjunt de forces socials virtuals que descriuren el comportament del robot en termes de moviments. Aquesta evaluació es basa en el concepte de “proxemics” i assegura que la navegació del robot està socialment acceptada per la persona que està sent acompanyada i per la gent que es troba a l’entorn. Per mitjà d’un estudi social, mostrem que els humans interpreten el comportament del robot d’acord amb les normes socials. Així mateix, un nou sistema per a guiar a persones en zones urbanes amb un conjunt de robots mòbils que cooperen és presentat. El model proposat ofereix diferents avantatges comparat amb treballs anteriors. Primer, es permet a un grup de persones ser guiades en entorns oberts o amb alta densitat d’obstacles; segon, s’utilitzen diferents robots que cooperen; tercer, els robots són capaços de reincorporar a la formació les persones que s’han allunyat del grup anteriorment de manera segura. La base del nostre enfocament es basa en el nou model anomenat “Discrete Time Motion”, el qual representa els movimients dels humans i els robots, prediu el comportament de les persones, i planeja i proporciona una ruta als robots.Posteriorment, aquesta tesi va un pas més enllà amb el desenvolupament del model “Prediction and Anticipation Model”. Aquest model ens permet determinar la distribució òptima de robots per a prevenir que les persones s’allunyin del grup en zones especíıfiques del mapa, i per tant facilitar la tasca dels robots. A més, s’optimitza localment el treball realitzat pels robots i les persones, produint d’aquesta manera un moviment més amigable. Finalment, s’introdueix un robot autònom mòbil capaç d’interactuar amb les persones per realitzar un aprenentatge assistit. Incialment, es presenten diferents comportaments del robot per apropar-se a una persona i crear un víıncle amb ell/ella. Basant-nos en aquesta idea, un mòdul visual per a la detecció de cares humanes en temps real va ser proporcionat al robot. Hem observat que les persones atribueixen diferents personalitats al robot en funció dels seus diferents comportaments. Una vegada que el contacte va ser iniciat es va donar l’oportunitat als voluntaris d’ajudar al robot per a millorar les seves habilitats visuals. Després d’aquesta etapa d’aprenentatge assistit, el robot va ser capaç d’identificar a les persones mitjançant l'ús de mètodes visuals.En resum, aquesta tesi presenta i demostra la necessitat de robots que siguin capaços d’operar de forma acceptable amb la gent i que es comportin d’acord amb les normes socials mentres acompanyen o guien a persones. Per altra banda, aquest treball mostra que la coperació entre un grup de robots pot optimitzar el rendiment tant dels robots com dels humans.

  • Access to the full text
    Proactive behavior of an autonomous mobile robot for human-assisted learning  Open access

     Garrell Zulueta, Anais; Villamizar Vergel, Michael Alejandro; Moreno Noguer, Francesc d'Assis; Sanfeliu Cortes, Alberto
    IEEE International Symposium on Robot and Human Interactive Communication
    p. 107-113
    DOI: 10.1109/ROMAN.2013.6628463
    Presentation's date: 2013
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    During the last decade, there has been a growing interest in making autonomous social robots able to interact with people. However, there are still many open issues regarding the social capabilities that robots should have in order to perform these interactions more naturally. In this paper we present the results of several experiments conducted at the Barcelona Robot Lab in the campus of the ¿Universitat Politècnica de Catalunya¿ in which we have analyzed different important aspects of the interaction between a mobile robot and non-trained human volunteers. First, we have proposed different robot behaviors to approach a person and create an engagement with him/her. In order to perform this task we have provided the robot with several perception and action capabilities, such as that of detecting people, planning an approach and verbally communicating its intention to initiate a conversation. Once the initial engagement has been created, we have developed further communication skills in order to let people assist the robot and improve its face recognition system. After this assisted and online learning stage, the robot becomes able to detect people under severe changing conditions, which, in turn enhances the number and the manner that subsequent human-robot interactions are performed.

    During the last decade, there has been a growing interest in making autonomous social robots able to interact with people. However, there are still many open issues regarding the social capabilities that robots should have in order to perform these interactions more naturally. In this paper we present the results of several experiments conducted at the Barcelona Robot Lab in the campus of the “Universitat Politècnica de Catalunya” in which we have analyzed different important aspects of the interaction between a mobile robot and non-trained human volunteers. First, we have proposed different robot behaviors to approach a person and create an engagement with him/her. In order to perform this task we have provided the robot with several perception and action capabilities, such as that of detecting people, planning an approach and verbally communicating its intention to initiate a conversation. Once the initial engagement has been created, we have developed further communication skills in order to let people assist the robot and improve its face recognition system. After this assisted and online learning stage, the robot becomes able to detect people under severe changing conditions, which, in turn enhances the number and the manner that subsequent human-robot interactions are performed.

    Postprint (author’s final draft)

  • Cooperative social robots to accompany groups of people

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    International journal of robotics research
    Vol. 31, num. 13, p. 1675-1701
    DOI: 10.1177/0278364912459278
    Date of publication: 2012
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Online human-assisted learning using random ferns  Open access

     Villamizar Vergel, Michael Alejandro; Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto; Moreno Noguer, Francesc d'Assis
    International Conference on Pattern Recognition
    p. 2821-2824
    Presentation's date: 2012
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    We present an Online Random Ferns (ORFs) classifier that progressively learns and builds enhanced models of object appearances. During the learning process, we allow the human intervention to assist the classifier and discard false positive training samples. The amount of human intervention is minimized and integrated within the online learning, such that in a few seconds, complex object appearances can be learned. After the assisted learning stage, the classifier is able to detect the object under severe changing conditions. The system runs at a few frames per second, and has been validated for face and object detection tasks on a mobile robot platform. We show that with minimal human assistance we are able to build a detector robust to viewpoint changes, partial occlusions, varying lighting and cluttered backgrounds. 2012 ICPR Org Committee.

    We present an Online Random Ferns (ORFs) classifier that progressively learns and builds enhanced models of object appearances. During the learning process, we allow the human intervention to assist the classifier and discard false positive training samples. The amount of human intervention is minimized and integrated within the online learning, such that in a few seconds, complex object appearances can be learned. After the assisted learning stage, the classifier is able to detect the object under severe changing conditions. The system runs at a few frames per second, and has been validated for face and object detection tasks on a mobile robot platform. We show that with minimal human assistance we are able to build a detector robust to viewpoint changes, partial occlusions, varying lighting and cluttered backgrounds.

    Postprint (author’s final draft)

  • Cooperación robots humanos en areas urbanas (RobTaskCoop) (DPI2010-17112)

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    Competitive project

     Share

  • Access to the full text
    Adaptive multi agent system for guiding groups of people in urban areas  Open access

     Garrell Zulueta, Anais; Sandoval Torres, Oscar; Sanfeliu Cortes, Alberto
    International Conference on Practical Applications of Agents and Multiagent Systems
    p. 175-184
    DOI: 10.1007/978-3-642-19917-2_22
    Presentation's date: 2011
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This article presents a new approach for guiding a group of people using an adaptive multi agent system. For the simulations of the group of people we use social forces, with theses forces human motion is controlled depending on the dynamic environment. To get the group of people being guide we use a set of agents that work cooperatively and they adapt their behavior according to the situation where they are working and how people react. For that reason, we present a model that overcomes the limitations of existing approaches, which are either tailored to tightly bounded environments, or based on unrealistic human behaviors. In particular we define a Discrete-Time- Motion model, which from one side represents the environment by means of a potential field, and on the other hand the motion models for people and robots respond to realistic situations, and for instance human behaviors such as leaving the group are considered. Furthermore, we present an analysis of forces actuating among agents and humans throughout simulations of different situations of robot and human configurations and behaviors. Finally, a new model of multi-robot task allocation applied to people guidance in urban settings is presented. The developed architecture overcomes some of the limitations of existing approaches, such as emergent cooperation or resource sharing.

    Postprint (author’s final draft)

  • Robot companions for guiding people in urban areas

     Garrell Zulueta, Anais; Corominas Murtra, Andreu; Sanfeliu Cortes, Alberto
    Workshop Español de Robótica
    p. 419-426
    Presentation's date: 2011
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • La influencia del efecto "Uncanny Valley" en el diseño de un robot social

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    International Congress of Design and Innovation of Catalonia
    p. 84-95
    Presentation's date: 2010
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Local optimization of cooperative robot movements for guiding and regrouping people in a guiding mission  Open access

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    IEEE/RSJ International Conference on Intelligent Robots and Systems
    p. 3294-3299
    DOI: 10.1109/IROS.2010.5649009
    Presentation's date: 2010
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This article presents a novel approach for optimizing locally the work of cooperative robots and obtaining the minimum displacement of humans in a guiding people mission. Unlike other methods, we consider situations where individuals can move freely and can escape from the formation, moreover they must be regrouped by multiple mobile robots working cooperatively. The problem is addressed by introducing a “Discrete Time Motion” model (DTM) and a new cost function that minimizes the work required by robots for leading and regrouping people. The guiding mission is carried out in urban areas containing multiple obstacles and building constraints. Furthermore, an analysis of forces actuating among robots and humans is presented throughout simulations of different situations of robot and human configurations and behaviors.

    Postprint (author’s final draft)

  • Cooperative robot movements for guiding and regrouping people using cost function evaluation

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    Workshop on Learning for Human-Robot Interaction Modeling in Robotics: Science and Systems (RSS)
    p. 14-15
    Presentation's date: 2010
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Model validation: robot behavior in people guidance mission using DTM model and estimation of human motion behavior

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    IEEE/RSJ International Conference on Intelligent Robots and Systems
    p. 5836-5841
    DOI: 10.1109/IROS.2010.5651685
    Presentation's date: 2010
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Cooperative robots in people guidance mission: DTM model validation and local optimization motion  Open access

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    IROS Workshop on Network Robot Systems
    p. 1-34
    Presentation's date: 2010
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This work presents a novel approach for optimizing locally the work of cooperative robots and obtaining the minimum displacement of humans in a guiding people mission. This problem is addressed by introducing a “Discrete Time Motion” model (DTM) and a new cost function that minimizes the work required by robots for leading and regrouping people. Furthermore, an analysis of forces actuating among robots and humans is presented throughout simulations of different situations of robot and human configurations and behaviors. Finally, we describe the process of modeling and validation by simulation that have been used to explore the new possibilities of interaction when humans are guided by teams of robots that work cooperatively in urban areas.

  • Guiding and regrouping people missions in urban areas using cooperative multi-robot task allocation

     Garrell Zulueta, Anais; Sandoval Torres, Oscar; Mirats Tur, Josep Maria; Sanfeliu Cortes, Alberto
    IEEE International Conference on Emerging Technologies and Factory Automation
    p. 2682-2690
    DOI: 10.1109/ETFA.2010.5641323
    Presentation's date: 2010
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Discrete time motion model for guiding people in urban areas using multiple robots  Open access

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto; Moreno Noguer, Francesc d'Assis
    IEEE/RSJ International Conference on Intelligent Robots and Systems
    p. 486-491
    Presentation's date: 2009
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    We present a new model for people guidance in urban settings using several mobile robots, that overcomes the limitations of existing approaches, which are either tailored to tightly bounded environments, or based on unrealistic human behaviors. Although the robots motion is controlled by means of a standard particle filter formulation, the novelty of our approach resides in how the environment and human and robot motions are modeled. In particular we define a “Discrete-Time-Motion” model, which from one side represents the environment by means of a potential field, that makes it appropriate to deal with open areas, and on the other hand the motion models for people and robots respond to realistic situations, and for instance human behaviors such as “leaving the group” are considered.

  • - Robotica Ubicua para entornos urbanos. (DPI2007-61452)

     Garrell Zulueta, Anais; Sanfeliu Cortes, Alberto
    Competitive project

     Share