Graphic summary
  • Show / hide key
  • Information


Scientific and technological production
  •  

1 to 50 of 257 results
  • Interpolation based deformation model for minimally invasive beating heart surgery

     Aviles Rivero, Angelica Ivone; Casals Gelpi, Alicia
    Mediterranean Conference on Medical and Biological Engineering and Computing
    Presentation's date: 2014-09-26
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Heart motion compensation is a key issue in medical robotics due to the benefits that minimally invasive beating heart surgery offers over traditional cardiac surgery. Although different proposals have been presented, nowadays, there is not yet a suitable solution working in real clinical environments due to the lack of robustness of existing methods. The process of heart motion estimation required to produce the compensation actions can be tackled as a process of three iterative steps. The first based on generating a deformation model from the processing of a video sequence of the beating heart. The selection of a deformation model is crucial in the sense that it has to offer both valuable information and good computational performance. These characteristics are required when the reaction time has a significant repercussion over the system behavior, as in this case. This paper, presents a computational analysis of deformation model based on interpolation methods. In particular, wavelet and thin-plate splines are evaluated. The significance of this study relies on the fact that it is a reference starting point of reference for creating both a common framework and a robust solution. In addition, the obtained results will contribute to increase the robustness from the initial stage of the solution.

  • Diseño y desarrollo de una estación automática de pulido para grandes superficies

     Casals Gelpi, Alicia
    Participation in a competitive project

     Share

  • Characterization of anastomosis techniques for robot assisted surgery

     Campos Carol, Jordi; Laporte, Enric; Gili, Gabriel; Peñas, Carlos; Casals Gelpi, Alicia; Amat Girbau, Josep
    Mediterranean Conference on Medical and Biological Engineering and Computing
    Presentation's date: 2013-09-26
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    A connection between two vessels or other tubular structures is known as anastomosis, one of the most common procedures in its field but, at the same time, one of the most complex suture-based techniques. This procedure requires not only a lot of skill and dexterity but also a lot of attention and plenty of concentration from the surgeon. This makes many of the actions to be performed irregularly, exposing the patient to human error resulting from the monotony. On the other hand, the field of robotics has earned itself a place in medicine, especially as assistants during a surgical intervention. Even so, medical robotics is quite young and still has not done much in the field of vessel anastomosis. Therefore, this paper presents a preliminary study of the most common suturing techniques, taking into account their typology and performance, within all the possible anastomosis procedures known. Subsequently, a detailed study of workflow and actions during an anastomosis is made, obtaining a diagram for each of the suturing techniques studied. This allows analyzing all procedures and to create a tool to find those actions and repeated tasks and/or common in all of them, indicating which of these are potential candidates for an automation study. This preliminary work focuses on finding where robotics can help to avoid rutinary tasks, which can be learned in a mechanical level and therefore, relatively easy to be automated using a robotic system or to assist the surgeon in certain tasks that need a lot of skill and attention.

  • Evaluating spatial characteristics of upper-limb movements from EMG signals

     Urra, Oiane; Casals Gelpi, Alicia; Jane Campos, Raimon
    Mediterranean Conference on Medical and Biological Engineering and Computing
    Presentation's date: 2013-09-27
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Stroke is a major cause of disability, usually causing hemiplegic damage on the motor abilities of the patient. Stroke rehabilitation seeks restoring normal motion on the affected limb. However, `normality¿ of movements is usually assessed by clinical and functional tests, without considering how the motor system responds to therapy. We hypothesized that electromyographic (EMG) recordings could provide useful information for evaluating the outcome of rehabilitation from a neuromuscular perspective. Four healthy subjects were asked to perform 14 different functional movements simulating the action of reaching over a table. Each movement was defined according to the starting and target positions that the subject had to connect using linear trajectories. Bipolar recordings of EMG signals were taken from biceps and triceps muscles, and spectral and temporal characteristics were extracted for each movement. Using pattern recognition techniques we found that only two EMG channels were sufficient to accurately determine the spatial characteristics of motor activity: movement direction, length and execution zone. Our results suggest that muscles may fire in a patterned way depending on the specific characteristics of the movement and that EMG signals may codify such detailed information. These findings may be of great value to quantitatively assess poststroke rehabilitation and to compare the neuromuscular activity of the affected and unaffected limbs, from a physiological perspective. Furthermore, disturbed movements could be characterized in terms of the muscle function to identify, which is the spatial characteristic that fails, e.g. movement direction, and guide personalized rehabilitation to enhance the training of such characteristic.

  • Handling disturbances on planned trajectories in robotic rehabilitation therapies

     Kumar Rajasekaran, Vijay; Aranda López, Juan; Casals Gelpi, Alicia
    Mediterranean Conference on Medical and Biological Engineering and Computing
    Presentation's date: 2013-09-27
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Robotic rehabilitation therapies are an emerging tool in the field of Neurorehabilitation in order to achieve an effective therapeutic development in the patient. In this paper, the role of disturbances caused by muscle synergies or unpredictable effects of artificial stimulation in muscles during rehabilitation therapies is analyzed. In terms of gait assistance it is also important to maintain synchronized movements to ensure a dynamically stable gait. Although, disturbances affecting joints are corrected by a force control approach, we define two methods to ensure stability and synchronization of joint movements in the trajectory to be followed. The performance of the presented methods is evaluated in comparison with a preplanned trajectory to be followed by the patients.

  • Exploring improvements on the complexity-performance ratio and usability of surgical robots

     Casals Gelpi, Alicia; Frigola Bourlon, Manel; Bergés Martín, Eduard; Amat Girbau, Josep
    IEEE International Conference on Robotics and Automation
    Presentation's date: 2013-05-06
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Surgical robots are endowed with valuable features that allow surgeons mproving their work in terms of accuracy, quality, efficiency and liability. Tremor reduction, scaled movements, virtual fixtures, pre and intraoperative imaging are some examples of enhancing aids for the surgeon. Moreover, being robotics surgery still at an early phase of development, current research efforts are focused to develop robotic systems able to solve more complex tasks, though the associated costs of robotics makes the convenience of its use in some kind of interventions questionable. After analyzing the main performances and limitations of current surgical robots, this paper foresees dvances towards ideal robotic systems that satisfy the requirements of future robots.

  • Considering civil liability as a safety criteria for cognitive surgical robots

     Bergés Martín, Eduard; Casals Gelpi, Alicia
    Mediterranean Conference on Medical and Biological Engineering and Computing
    Presentation's date: 2013-09-26
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    One of the challenges of the robotics community is to develop robots that behave more and more autonomously. Therefore, it is necessary to establish new design criteria, as well as more complex methodologies supporting the analysis of associated risks. The procedure described in this paper includes civil liability as an additional criterion to validate the safety of a surgical robot. In order to understand the concept, a methodology is presented through the description of a simple case. This work aims to establish the basis for a further implementation.

  • Human motion recognition from 3D pose information - Trisarea: a new pose-based feature

     Vinagre Ruiz, Manuel; Aranda López, Juan; Casals Gelpi, Alicia
    Internacional Conference on Informatics in Control, Automation and Robotics
    Presentation's date: 2013-07-30
    Presentation of work at congresses

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    The use of pose-based features has demonstrated to be a promising approach for human motion recognition. Encouraged by the results achieved, a new relational pose-based feature, Trisarea, based on geometric relationship between human joints, is proposed and analysed. This feature is defined as the area of the triangle formed by connecting three joints. The paper shows how the variation of a selected set of Trisarea features over time constitutes a descriptor of human motion. It also demonstrates how this motion descriptor based on Trisarea features can provide useful information in terms of human motion for its application to action recognition tasks.

  • Estudio de las Fuerzas de Interacción para la Minimización de Esfuerzos en Rehabilitación Robotizada

     Amigo Vásquez, Luis Ernesto
    Defense's date: 2013-10-17
    Universitat Politècnica de Catalunya
    Theses

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

  • Premio a la Mejor Tesis Doctoral sobre Robótica 2012

     Muñoz Morgado, Luis Miguel; Casals Gelpi, Alicia
    Award or recognition

    View View Open in new window  Share

  • Diseño y desarrollo de una estación automática de pulido para grandes superficies

     Casals Gelpi, Alicia
    Participation in a competitive project

     Share

  • Virtual Robot: a new teleoperation paradigm for minimally invasive robotic surgery

     Hernansanz Prats, Albert; Amat Girbau, Josep; Casals Gelpi, Alicia
    IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics
    Presentation's date: 2012-06-26
    Presentation of work at congresses

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

  • Study of patient-orthosis interaction forces in rehabilitation therapies

     Amigo, Luis; Fernández, Q.; Giralt, Xavier; Casals Gelpi, Alicia; Amat Girbau, Josep
    IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics
    Presentation's date: 2012-06-25
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    The design of mechanical joints that kinematically behave as their biological counterparts is a challenge that if not addressed properly can cause inadequate forces transmission between robot and patient. This paper studies the interaction forces in rehabilitation therapies of the elbow joint. To measure the effect of orthosis-patient misalignments, a force sensor with a novel distributed architecture has been designed and used for this study. A test-bed based on an industrial robot acting as a virtual exoskeleton that emulates the action of a therapist has been developed and the interaction forces analyzed.

  • Dynamic scaling interface for assisted teleoperation

     Muñoz Morgado, Luis Miguel; Casals Gelpi, Alicia
    IEEE International Conference on Robotics and Automation
    Presentation's date: 2012
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Teleoperation, by adequately adapting computer interfaces, can benefit from the knowledge on human factors and psychomotor models in order to improve the effectiveness and efficiency in the execution of a task. While scaling is one of the performances frequently used in teleoperation tasks that require high precision, such as surgery, this article presents a scaling method that considers the system dynamics as well. The proposed dynamic scaling factor depends on the apparent position and velocity of the robot and targets. Such scaling improves the performance of teleoperation interfaces, thereby reducing user's workload.

  • Detection of movements with attention or distraction to the motor task during robot-assisted passive movements of the upper limb

     Antelis, Javier M.; Montesano, Luis; Giralt Ludevid, Xavier; Casals Gelpi, Alicia; Minguez, Javier
    IEEE Engineering in Medicine and Biology Society
    Presentation's date: 2012-08-29
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Robot-assisted rehabilitation therapies usually focus on physical aspects rather than on cognitive factors. However, cognitive aspects such as attention, motivation, and engagement play a critical role in motor learning and thus influence the long-term success of rehabilitation programs. This paper studies motor-related EEG activity during the execution of robot-assisted passive movements of the upper limb, while participants either: i) focused attention exclusively on the task; or ii) simultaneously performed another task. Six healthy subjects participated in the study and results showed lower desynchronization during passive movements with another task simultaneously being carried out (compared to passive movements with exclusive attention on the task). In addition, it was proved the feasibility to distinguish between the two conditions.

  • Improving the development of surgical skills with virtual fixtures in simulation

     Hernansanz Prats, Albert; Zerbato, Davide; Gasperotti, Lorenza; Scandola, Michele; Fiorini, Paolo; Casals Gelpi, Alicia
    International Conference on Information Processing in Computer-Assisted Interventions
    Presentation's date: 2012-06-29
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This paper focuses on the use of virtual fixtures to improve the learning of basic skills for laparoscopic surgery. Five virtual fixtures are defined, integrated into a virtual surgical simulator and used to define an experimental setup based on a trajectory following task. 46 subjects among surgeons and residents underwent a training session based on the proposed setup. Their performance has been logged and used to identify the effect of virtual fixtures on the learning curve from the point of view of accuracy and completion time. Virtual fixtures prove to be effective in improving the learning and affect differently accuracy and completion time. This suggests the possibility to tailor virtual fixtures on the specific task requirements.

  • Design and development of a guideline for ergonomic haptic interaction

     Muñoz Morgado, Luis Miguel; Ponsa Asensio, Pedro; Casals Gelpi, Alicia
    Date of publication: 2012
    Book chapter

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    The main goal of this chapter is to propose a guideline for human-robot systems focused on ergonomic haptic interaction. With this aim, this model presents several main parts: a set of heuristic indicators in order to identify the attributes of the haptic interaction, the relationship between indicators, the human task and the haptic interface requirements and finally an experimental task procedure and a qualitative performance evaluation metrics in the use of haptic interfaces. The final goal of this work is the study of possible applications of haptics in regular laboratory conditions, in order to improve the analysis, design and evaluation of human task over haptic interfaces in telerobotic applications.

  • Transformación escalar de la interfaz de operador en teleoperación asistida  Open access

     Muñoz Morgado, Luis Miguel
    Defense's date: 2012-02-03
    Institute of Industrial and Control Engineering (IOC), 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

    Human-machine interaction in teleoperation, through the adequate user interface, allows achieving the level of intelligence necessary to execute complex tasks that cannot be executed by machines or robots alone neither directly by humans. H-R interaction techniques facilitate the execution of such tasks making them more efficient and effective through the improvement of their user interface. Humans have inherent motor limitations (such as physiological tremor) and perceptive limitations (mainly perception of distance and time), which can prevent them from operating smoothly and precisely enough for certain applications. Some studies have already tackled this problem and its effect on the human-machine interaction and teleoperated systems. There are psychomotor models that show that the human manipulation efficiency, in actions such as pointing an object, depends on several factors. Among these models, the most representative corresponds to Fitts’ Law, in which the execution time is a logarithmic function of the size and distance to the object. In teleoperation, and based on these models, a modification of the visual scale in the user’s interface has a direct effect on the task execution time and on the precision that can be achieved. The same occurs with a change in the amplitude of the movement executed by the human operator with respect to that performed by the system. Therefore, scaling the movement between master and slave has a significant effect on the efficiency and effectiveness executing a task. This research work is oriented to the design and development of a method conceived to improve effectiveness thanks to a larger visual and motor efficiency of the human-machine interface. The method is based on the modification of the information flow between human, machine and interface by means of the scaling of both, the human movements and the image of the visualized task. Operation time, hand movements and the need for visual attention can thus be reduced with this computerized assistance. The changes of scale adapt to the task, which positively affects its performance in terms of precision and speed. Therefore, the proposed methodology aims to link the human operator working space to the machine or robot working space through an interface that introduces two scaling processes. A first change of scale is applied between the movement produced by the human operator and the movement produced in the visual interface (for instance, movement of the robot end-effector that is visualized on the computer screen); and a second change oriented to scale the real space of the task over the visual space of the interface. These changes of scale should be adjusted to the objects of interest, which result in a modification of the spatial resolution according to the task to be performed and to the size, shape distance and speed of the objects. Such changes modify the information flow between human and machine according to the characteristics and limitations of both.

    La interacció persona-màquina en teleoperació, a través de la interfície d’usuari, permet aconseguir el nivell d’intel•ligència necessari per executar en cooperació tasques complexes que no poden ser realitzades per màquines o robots per si sols o directament per les persones. Les tècniques d’interacció faciliten el desenvolupament d’aquestes tasques fent-les mes eficients i eficaces, mitjançant la millora de qualsevol sistema que incorpori una interfície d’usuari. Les persones posseeixen limitacions motores inherents a la naturalesa humana (com la tremolor fisiològica) i limitacions perceptives (com la percepció de la distància o el temps) que impedeixen realitzar una operació suficientment suau i precisa en certes aplicacions. Alguns estudis tracten aquest fenomen i el seu efecte en els sistemes persona-màquina i sistemes teleoperats. Existeixen models psicomotors que mostren que la eficiència de la manipulació humana en la selecció d’un objecte depèn de determinats factors. Entre aquests models, el més representatiu correspon a la Llei de Fitts, in on el temps d’execució es una funció logarítmica de la mida i la distancia al objecte. En teleoperació, i en base a aquests models psicomotors, es demostra que una modificació en l’escala visual de la interfície té un efecte directe en el temps d’execució d’una tasca i en la precisió assolible. El mateix succeeix amb un canvi en l’amplitud del moviment que realitza l’operador respecte al realitzat pel sistema, de manera que l’escalat del moviment entre mestre i esclau té un efecte significatiu en l’eficiència i eficàcia amb la que s’executa una tasca. Aquest treball d’investigació està orientat al disseny i desenvolupament d’un mètode concebut per millorar l’eficàcia gràcies a una major eficiència visual i motora de la interfície persona-màquina. El mètode es basa en la modificació del flux d’informació entre persona, màquina i interfície mitjançant l’escalat tant del moviment de la persona com de la imatge de la tasca visualitzada. El temps d’operació, els moviments de la mà de la persona i el grau d’atenció poden reduir-se amb aquesta assistència computeritzada. Els canvis d’escala s’adapten a la tasca, afectant positivament el rendiment en termes de precisió i rapidesa. Així doncs, la metodologia proposada està orientada a connectar l’espai de treball de la persona amb l’espai de treball de la màquina o robot a través de la interfície que introdueix dos processos d’escala. Un primer canvi d’escala s’aplica entre el moviment produït per l’operador i el produït a la interfície visual i un segon canvi està orientat a escalar l’espai real de la tasca sobre la interfície visual. Aquests canvis d’escala han de ser ajustats als objectes d’interès, resultant en una modificació de la resolució espacial d’acord amb la tasca a realitzar i la mida, forma, i velocitat dels objectes. Aquests canvis d’escala modifiquen el flux d’informació entre l’operador i la màquina d’acord amb les característiques i limitacions d’ambdós.

    La interacción persona-máquina en teleoperación, a través de la interfaz de usuario, permite conseguir el nivel de inteligencia necesario para ejecutar en cooperación tareas complejas que no pueden ser realizadas por máquinas o robots por si solos o directamente por las personas. Las técnicas de interacción facilitan el desarrollo de dichas tareas haciéndolas más eficientes y eficaces, mediante la mejora de cualquier sistema que incorpore una interfaz de usuario. Las personas poseen limitaciones motoras inherentes a la naturaleza humana (como el temblor fisiológico) y limitaciones perceptivas (como la percepción de la distancia o el tiempo) que impiden realizar una operación suficientemente suave y precisa en ciertas aplicaciones. Algunos estudios tratan este fenómeno y su efecto en los sistemas persona-máquina y sistemas teleoperados. Existen modelos psicomotores que muestran que la eficiencia de la manipulación humana en la selección de un objeto depende de determinados factores. Entre estos modelos, el más representativo corresponde a la Ley de Fitts en donde el tiempo de ejecución es una función logarítmica del tamaño y la distancia al objeto. En teleoperación, y en base a estos modelos psicomotores, se demuestra que una modificación en la escala visual de la interfaz tiene un efecto directo en el tiempo de ejecución de una tarea y en la precisión alcanzable. Lo mismo ocurre con un cambio en la amplitud de movimiento que realiza el operador con respecto al realizado por el sistema, con lo que el escalado del movimiento entre maestro y esclavo tiene un efecto significativo en la eficiencia y eficacia con la que se ejecuta una tarea. Este trabajo de investigación está orientado al diseño y desarrollo de un método concebido para mejorar la eficacia gracias a una mayor eficiencia visual y motora de la interfaz persona-máquina. El método se basa en la modificación del flujo de información entre persona, máquina e interfaz mediante el escalado tanto del movimiento de la persona como de la imagen de la tarea visualizada. El tiempo de operación, los movimientos de la mano de la persona y el grado de atención pueden reducirse con esta asistencia computarizada. Los cambios de escala se adaptan a la tarea, afectando positivamente al rendimiento en términos de precisión y rapidez. Por lo tanto, la metodología propuesta está orientada a conectar el espacio de trabajo de la persona con el espacio de trabajo de la máquina o robot a través de la interfaz que introduce dos procesos de escala. Un primer cambio de escala se aplica entre el movimiento producido por el operador y el producido en la interfaz visual y un segundo cambio está orientado a escalar el espacio real de la tarea sobre la interfaz visual. Estos cambios de escala deben ser ajustados a los objetos de interés, resultando en una modificación de la resolución espacial acorde con la tarea a realizar y el tamaño, forma, distancia y velocidad de los objetos. Dichos cambios de escala modifican el flujo de información entre el operador y la máquina acordes con las características y limitaciones de ambos.

  • Efficient approaches for object class detection  Open access

     Villamizar Vergel, Michael Alejandro
    Defense's date: 2012-09-18
    Institute of Industrial and Control Engineering (IOC), 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

    La visión por computador y más específicamente el reconocimiento de objetos han demostrado en los últimos años un impresionante progreso que ha llevado a la aparición de nuevas y útiles tecnologías que facilitan nuestras actividades diarias y mejoran ciertos procesos industriales. Actualmente, nosotros podemos encontrar algoritmos para el reconocimiento de objetos en computadores, videocámaras, teléfonos móviles, tablets o sitios web para la realización de ciertas tareas específicas tales como la detección de caras, el reconocimiento de gestos y escenas, la detección de peatones, la realidad aumentada, etc. No obstante, estas aplicaciones siguen siendo problemas abiertos que cada año reciben más atención por parte de la comunidad de visión por computador. Esto se demuestra por el hecho de que cientos de artículos abordando estos problemas son publicados en congresos internacionales y revistas anualmente. Desde una perspectiva general, los trabajos más recientes intentan mejorar el desempeño de clasificadores, hacer frente a nuevos y más desafiantes problemas de detección, y a aumentar la eficiencia computacional de los algoritmos resultantes con el objetivo de ser implementados comercialmente en diversos dispositivos electrónicos. Aunque actualmente, existen enfoques robustos y confiables para la detección de objetos, la mayoría de estos métodos tienen un alto coste computacional que hacen imposible su aplicación en tareas en tiempo real. En particular, el coste computacional y el desempeño de cualquier sistema de reconocimiento está determinado por el tipo de características, método de reconocimiento y la metodología utilizada para localizar los objetos dentro de las imágenes. El principal objetivo de estos métodos es obtener sistemas de detección eficaces pero también eficientes. A través de esta tesis diferentes enfoques son presentados para abordar de manera eficiente y discriminante la detección de objetos en condiciones de imagen diversas y difíciles. Cada uno de los enfoques propuestos ha sido especialmente diseñado y enfocado para la detección de objetos en circunstancias distintas, tales como la categorización de objetos, la detección bajo rotaciones en el plano o la detección de objetos a partir de múltiples vistas. Los métodos propuestos combinan varias ideas y técnicas para la obtención de detectores de objetos que son tanto altamente discriminantes como eficientes. Esto se demuestra experimentalmente en varias bases de datos del estado del arte donde los resultados alcanzados son competitivos al ser contrastados con otros métodos recientes. En concreto, esta tesis estudia y desarrolla características rápidas, algoritmos de aprendizaje, métodos para reducir el coste computacional de los clasificadores y representaciones de imagen integral que permiten un mejor cálculo de las características.

    Computer vision and more specifically object recognition have demonstrated in recent years an impressive progress that has led to the emergence of new and useful technologies that facilitate daily activities and improve some industrial processes. Currently, we can find algorithms for object recognition in computers, video cameras, mobile phones, tablets or websites, for the accomplishment of specific tasks such as face detection, gesture and scene recognition, detection of pedestrians, augmented reality, etc. However, these applications are still open problems that each year receive more attention in the computer vision community. This is demonstrated by the fact that hundreds of articles addressing these problems are published in international conferences and journals annually. In a broader view, recent work attempts to improve the performance of classifiers, to face new and more challenging problems of detection and to increase the computational efficiency of the resulting algorithms in order to be implemented commercially in diverse electronic devices. Although nowadays there are robust and reliable approaches for detecting objects, most of these methods have a high computational cost that make impossible their application for real-time tasks. In particular, the computational cost and performance of any recognition system is determined by the type of features, the method of recognition and the methodology used for localizing objects within images. The main objective of these methods is to produce not only effective but also efficient detection systems. Through this dissertation different approaches are presented for addressing efficiently and discriminatively the detection of objects in diverse and difficult imaging conditions. Each one of the proposed approaches are especially designed and focus on different detection problems, such as object categorization, detection under rotations in the plane or the detection of objects from multiple views. The proposed methods combine several ideas and techniques for obtaining object detectors that are both highly discriminative and efficient. This is demonstrated experimentally in several state-of-the-art databases where our results are competitive with other recent and successful methods. In particular, this dissertation studies and develops fast features, learning algorithms, methods for reducing the computational cost of the classifiers and integral image representations for speeding up feature computation.

  • Access to the full text
    Diseño de una arquitectura de ortesis adaptativa y estudio de la personalización de su grado de asistencia  Open access

     Amigo Vázquez, Luis Ernesto; Giralt Ludevid, Xavier; Fernández Castellvi, Quim; Casals Gelpi, Alicia; Amat Girbau, Josep
    Robótica Experimental
    Presentation's date: 2011-11-29
    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

    Uno de los principales objetivos de las terapias de rehabilitación del miembro superior asistidas por robots es incrementar la recuperación funcional al finalizar la terapia y a su vez disminuir el tiempo de esta recuperación, promoviendo la neuroplasticidad en pacientes con problemas neuromusculares. En este sentido es importante que los exoesqueletos se adapten a los movimientos del paciente y no al revés. Este artículo presenta un ortesis para la extremidad superior con servoadaptación dinámica para la articulación del codo con el objetivo de reducir las fuerzas de interacción causadas por el desalineamiento entre el robot y la extremidad superior. Se estudia además el grado de asistencia que se debe efectuar durante la terapia con el objetivo de promover la neuroplasticidad y que el paciente trabaje en la totalidad de sus capacidades optimizando así la recuperación.

  • Design of a 3-DoF joint system with dynamic servo-adaptation in orthotic applications

     Amigo, Luis; Casals Gelpi, Alicia; Amat Girbau, Josep
    IEEE International Conference on Robotics and Automation
    Presentation's date: 2011-05-10
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Most exoskeleton designs rely on structures and mechanical joints that do not guarantee the right match between the orthosis and the user. This paper proposes a virtual joint model based on three active degrees of freedom aimed to emulate a human joint. This joint is capable of performing a dynamic servo-adaptation in real-time to avoid misalignments and to provide a flexible adjustment to different users’ sizes in order to avoid undesirable interaction forces.

  • Access to the full text
    Sistema integrado de posicionado, visualización y acotamiento de áreas de trabajo en cirugía ortopédica  Open access

     Casals Gelpi, Alicia; Basomba Feliu, Joan; Bergès Martín, Eduard; Frigola Bourlon, Manel; Amat Girbau, Josep
    Robótica Experimental
    Presentation's date: 2011-11-29
    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

    La percepción que el cirujano tiene de la intervención que está realizando es esencial para garantizar una operación segura y eficiente. En cirugía robotizada los sistemas de percepción disponibles son muy limitados, lo que puede paliarse generando información visual a proyectar sobre el paciente. El trabajo describe el modo de generar y proyectar la imagen 3D obtenida por TAC, así como trayectorias previamente planificadas, que serán de ayuda al guiado. Esta información es también utilizada para el guiado del robot que trabaja en cooperación con el cirujano, en modo comanipulación, evitando situaciones de riesgo y ayudando al cirujano en el guiado de los instrumentos quirúrgicos.

  • Map-based Localization for Urban Service Mobile Robotics  Open access

     Corominas Murtra, Andreu
    Defense's date: 2011-09-23
    Institute of Industrial and Control Engineering (IOC), 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

    Mobile robotics research is currently interested on exporting autonomous navigation results achieved in indoor environments, to more challenging environments, such as, for instance, urban pedestrian areas. Developing mobile robots with autonomous navigation capabilities in such urban environments supposes a basic requirement for a upperlevel service set that could be provided to an users community. However, exporting indoor techniques to outdoor urban pedestrian scenarios is not evident due to the larger size of the environment, the dynamism of the scene due to pedestrians and other moving obstacles, the sunlight conditions, and the high presence of three dimensional elements such as ramps, steps, curbs or holes. Moreover, GPS-based mobile robot localization has demonstrated insufficient performance for robust long-term navigation in urban environments. One of the key modules within autonomous navigation is localization. If localization supposes an a priori map, even if it is not a complete model of the environment, localization is called map-based. This assumption is realistic since current trends of city councils are on building precise maps of their cities, specially of the most interesting places such as city downtowns. Having robots localized within a map allows for a high-level planning and monitoring, so that robots can achieve goal points expressed on the map, by following in a deliberative way a previously planned route. This thesis deals with the mobile robot map-based localization issue in urban pedestrian areas. The thesis approach uses the particle filter algorithm, a well-known and widely used probabilistic and recursive method for data fusion and state estimation. The main contributions of the thesis are divided on four aspects: (1) long-term experiments of mobile robot 2D and 3D position tracking in real urban pedestrian scenarios within a full autonomous navigation framework, (2) developing a fast and accurate technique to compute on-line range observation models in 3D environments, a basic step required by the real-time performance of the developed particle filter, (3) formulation of a particle filter that integrates asynchronous data streams and (4) a theoretical proposal to solve the global localization problem in an active and cooperative way, defining cooperation as either information sharing among the robots or planning joint actions to solve a common goal.

    Actualment, la recerca en robòtica mòbil té un interés creixent en exportar els resultats de navegació autònoma aconseguits en entorns interiors cap a d'altres tipus d'entorns més exigents, com, per exemple, les àrees urbanes peatonals. Desenvolupar capacitats de navegació autònoma en aquests entorns urbans és un requisit bàsic per poder proporcionar un conjunt de serveis de més alt nivell a una comunitat d'usuaris. Malgrat tot, exportar les tècniques d'interiors cap a entorns exteriors peatonals no és evident, a causa de la major dimensió de l'entorn, del dinamisme de l'escena provocada pels peatons i per altres obstacles en moviment, de la resposta de certs sensors a la il.luminació natural, i de la constant presència d'elements tridimensionals tals com rampes, escales, voreres o forats. D'altra banda, la localització de robots mòbils basada en GPS ha demostrat uns resultats insuficients de cara a una navegació robusta i de llarga durada en entorns urbans. Una de les peces clau en la navegació autònoma és la localització. En el cas que la localització consideri un mapa conegut a priori, encara que no sigui un model complet de l'entorn, parlem d'una localització basada en un mapa. Aquesta assumpció és realista ja que la tendència actual de les administracions locals és de construir mapes precisos de les ciutats, especialment dels llocs d'interés tals com les zones més cèntriques. El fet de tenir els robots localitzats en un mapa permet una planificació i una monitorització d'alt nivell, i així els robots poden arribar a destinacions indicades sobre el mapa, tot seguint de forma deliberativa una ruta prèviament planificada. Aquesta tesi tracta el tema de la localització de robots mòbils, basada en un mapa i per entorns urbans peatonals. La proposta de la tesi utilitza el filtre de partícules, un mètode probabilístic i recursiu, ben conegut i àmpliament utilitzat per la fusió de dades i l'estimació d'estats. Les principals contribucions de la tesi queden dividides en quatre aspectes: (1) experimentació de llarga durada del seguiment de la posició, tant en 2D com en 3D, d'un robot mòbil en entorns urbans reals, en el context de la navegació autònoma, (2) desenvolupament d'una tècnica ràpida i precisa per calcular en temps d'execució els models d'observació de distàncies en entorns 3D, un requisit bàsic pel rendiment del filtre de partícules a temps real, (3) formulació d'un filtre de partícules que integra conjunts de dades asíncrones i (4) proposta teòrica per solucionar la localització global d'una manera activa i cooperativa, entenent la cooperació com el fet de compartir informació, o bé com el de planificar accions conjuntes per solucionar un objectiu comú.

  • Motor-model-based dynamic scaling in human-computer interfaces

     Muñoz Morgado, Luis Miguel; Casals Gelpi, Alicia; Frigola Bourlon, Manel; Amat Girbau, Josep
    IEEE transactions on systems man and cybernetics Part B-Cybernetics
    Date of publication: 2011-04
    Journal article

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

  • Access to the full text
    Analisis de la señal del centro de presiones mediante auto-informacion mutua: Test con ojos abiertos  Open access

     Galicia, Berenice; Vallverdú Ferrer, Montserrat; Peydro, Francisca; Casals Gelpi, Alicia
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    Presentation's date: 2010-11
    Presentation of work at congresses

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

  • Friendly human-machine interaction in an adapted robotized kitchen

     Aranda López, Juan; Vinagre, Manuel; Martin Rull, Enric Xavier; Casamitjana Morales, Miquel; Casals Gelpi, Alicia
    International Conference on Computers Helping People with Special Needs
    Presentation's date: 2010-07-14
    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
    Intuitive graphic interface for assisted teleoperation in surgical applications  Open access

     Casals Gelpi, Alicia; Campos Querol, Jordi; Giralt Ludevid, Xavier; Amat Girbau, Josep
    Anglès
    Presentation's date: 2010-06-17
    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

    Human-Machine interfaces constitute a key factor to guarantee the effective use of technological equipment. In the field of image guided surgery and surgical robots, the availability of an adequate interaction means determines the suitability or not of a given technological aid. This work focuses on the problems surgeons find in planning and executing a robot assisted intervention. Analyzing the potential of computer graphics, together with the surgeons needs during, first, the planning and later on the development of a surgical intervention, the specifications and the implementation of an interface is described. In the design of this interface, special attention has been put on the gesture and attention capabilities that surgeons can devote to the interface.

  • Polyarticulated architecture for the emulation of an isocentric joint in orthetic applications

     Amigo Vasquez, Luis; Casals Gelpi, Alicia; Amat Girbau, Josep
    IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics
    Presentation's date: 2010
    Presentation of work at congresses

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

  • Friendly human-machine interaction in an adapted robotized kitchen

     Aranda López, Juan; Vinagre, Manuel; Martin Rull, Enric Xavier; Casamitjana Morales, Miquel; Casals Gelpi, Alicia
    Lecture notes in computer science
    Date of publication: 2010
    Journal article

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

  • Robotics as a support tool for experimental optimisation of surgical strategies in orthopaedic surgery

     Frigola Bourlon, Manel; Vinagre, Manuel; Casals Gelpi, Alicia; Amat Girbau, Josep; Santana, Fernando; Torrens, C.
    Applied bionics and biomechanics
    Date of publication: 2010-09
    Journal article

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

  • Robótica en sanidad: asistencia en el quirófano y asistencia a las personas

     Casals Gelpi, Alicia
    Automática e instrumentación
    Date of publication: 2010-07-10
    Journal article

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

  • La Robótica una valiosa herramienta en cirugía

     Casals Gelpi, Alicia; Frigola Bourlon, Manel; Amat Girbau, Josep
    Revista iberoamericana de automática e informática industrial
    Date of publication: 2009-01
    Journal article

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

  • Vision-Based Planning for Grasping Unknown Objects.

     Boudaba, Abdel-Madjid
    Defense's date: 2009-07-09
    Department of Automatic Control, Universitat Politècnica de Catalunya
    Theses

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Optimization criterion for safety task transfer in cooperative robotics  Open access

     Hernansanz Prats, Alberto; Amat Girbau, Josep; Casals Gelpi, Alicia
    International Conference on Advanced Robotics
    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 paper presents a strategy for a cooperative multirobot system, constituting a Virtual Robot. The Virtual Robot is composed of a set of robotic arms acting as only one, transferring the execution of a teleoperated task from one to another when necessary. To decide which of the robots is the most suitable to execute the task at every instant, a multiparametric decision function has been defined. This function is based on a set of intrinsic and extrinsic evaluation indexes of the robot. Since the internal operation of the Virtual Robot must be transparent to the user, a control architecture has been developed.

  • Ayudas funcionales en el hogar. Posibilidades de una cocina adaptada

     Casals Gelpi, Alicia; Vinagre, M; Martin Rull, Enric Xavier; Casamitjana, M
    DRT4ALL 2009 III Congreso Internacional sobre Domótica, Robótica y Teleasistencia para Todos
    Presentation's date: 2009-05-21
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Learning rest-to-rest motor coordination in articulated mobile robots

     Pardo Ayala, Diego Esteban
    Defense's date: 2009-10-07
    Department of Automatic Control, Universitat Politècnica de Catalunya
    Theses

     Share Reference managers Reference managers Open in new window

  • Optimization criterion for safety task transfer in cooperative

     Hernansanz Prats, Alberto; Amat Girbau, Josep; Casals Gelpi, Alicia
    International Conference on Advanced Robotics
    Presentation's date: 2009-06-22
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • ESTUDIO Y DESARROLLO DE ESTRATEGIAS DE COOPERACIÓN MULTIROBOT CON ARQUITECTURAS REDUNDANTES

     Aranda López, Juan; Frigola Bourlon, Manel; Mares Marti, Pere; Giralt Ludevid, Xavier; Casamitjana Morales, Miquel; Triginer Cahelles, Joaquin; Casals Gelpi, Alicia
    Participation in a competitive project

     Share

  • GRUP DE RECERCA ROÒTICA INTEL·LIGENT I SISTEMES (GRINS)

     Amat Girbau, Josep; Aranda López, Juan; Muñoz Morgado, Luis Miguel; Hernansanz Prats, Alberto; Frigola Bourlon, Manel; Fernández Ruzafa, Jose; Martin Rull, Enric Xavier; Martinez Velasco, Antonio Benito; Casals Gelpi, Alicia
    Participation in a competitive project

     Share

  • Improving the Human-Robot Interface Through Adaptive Multispace Transformation

     Muñoz Morgado, Luis Miguel; Casals Gelpi, Alicia
    IEEE transactions on robotics
    Date of publication: 2009-10
    Journal article

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

  • Monitoring and robotizing shoulder arthroplasty for training and optimization of suturing techniques

     Casals Gelpi, Alicia; Amat Girbau, Josep; Frigola Bourlon, Manel; Rodríguez-Cheu, Luis Eduardo; Torrens, Carlos; Ginés, Albert
    International journal of computer assisted radiology and sugery (Online)
    Date of publication: 2008-05
    Journal article

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

  • From Micro- to Nano: Optical-based Coordination in a Multi-tip AFM

     Jorge, Otero; Samitier Martí, Josep; Frigola Bourlon, Manel; Casals Gelpi, Alicia; Amat Girbau, Josep
    Seeing at the Nanoscale
    Presentation's date: 2008-07-10
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Estudio Cinemático de la movilidad del raquis cervical en pacientes con deficit de equilibrio utilizando técnicas de videofotogrametria

     Galicia, B; Garrido, J D; Casals Gelpi, Alicia; Peydro, M F
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    Presentation's date: 2008-10-17
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • L'impacte de la Tecnologia en el tractament quirúrgic

     Casals Gelpi, Alicia
    Date of publication: 2008-07
    Book

     Share Reference managers Reference managers Open in new window

  • Debat

     Casals Gelpi, Alicia
    IARP-IEEE/RAS Joint Workshop on Technical Challenge for Dependable Robots in Human Environments
    Presentation's date: 2008-05-18
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Compliant strategies baCompliant strategies based on force, torque, contact and proximity for Human Robot Interaction

     Casals Gelpi, Alicia; Giralt Ludevid, Xavier; Frigola Bourlon, Manel; Amat Girbau, Josep
    IARP-IEEE/RAS Joint Workshop on Technical Challenge for Dependable Robots in Human Environments
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Using stereo vision and tactile sensor features for grasp planning control

     Boudaba, Madgid; Nicolas, Gorges; Heinz, Woern; Casals Gelpi, Alicia
    Fifth International Conference on Informatics in Control, Automation and Robotics
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • sed on force, torque, contact and proximity

     Casals Gelpi, Alicia
    IARP-IEEE/RAS Joint Workshop on Technical Challenge for Dependable Robots in Human Environments
    Presentation's date: 2008-05-18
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Robotics and Autonomous Systems in the 50th Anniversary of Artificial Intelligence

     Casals Gelpi, Alicia; Fernandez Caballero, A
    Robotics and autonomous systems
    Date of publication: 2007-12
    Journal article

     Share Reference managers Reference managers Open in new window

  • Definición de un Índice de Funcionalidad y Realimentación de Esfuerzos en Prótesis de Mano

    Defense's date: 2007-12-03
    Department of Automatic Control, Universitat Politècnica de Catalunya
    Theses

     Share Reference managers Reference managers Open in new window