Miguel Realpe, Boris X. Vintimilla, & L. Vlacic. (2015). Towards Fault Tolerant Perception for autonomous vehicles: Local Fusion. In IEEE 7th International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), Siem Reap, 2015. (pp. 253–258).
Abstract: Many robust sensor fusion strategies have been developed in order to reliably detect the surrounding environments of an autonomous vehicle. However, in real situations there is always the possibility that sensors or other components may fail. Thus, internal modules and sensors need to be monitored to ensure their proper function. This paper introduces a general view of a perception architecture designed to detect and classify obstacles in an autonomous vehicle's environment using a fault tolerant framework, whereas elaborates the object detection and local fusion modules proposed in order to achieve the modularity and real-time process required by the system.
|
Dennys Paillacho, Cecilio Angulo, & Marta Díaz. (2015). An Exploratory Study of Group-Robot Social Interactions in a Cultural Center. In IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015, International Conference on, Hamburg, Germany, 2015.
Abstract: This article describes an exploratory study of social human-robot interaction with the experimental robotic platform MASHI. The experiences were carried out in La B`obila Cultural Center in Barcelona, Spain to study the visitor preferences, characterize the groups and their spatial relationships in this open and unstructured environment. Results showed that visitors prefers to play and dialogue with the robot. Children have the highest interest in interacting with the robot, more than young and adult visitors. Most of the groups consisted of more than 3 visitors, however the size of the groups during interactions was continuously changed. In static situations, the observed spatial relationships denotes a social cohesion in the human-robot interactions.
|
Miguel Realpe, Boris X. Vintimilla, & Ljubo Vlacic. (2015). Sensor Fault Detection and Diagnosis for autonomous vehicles. In 2nd International Conference on Mechatronics, Automation and Manufacturing (ICMAM 2015), International Conference on, Singapur, 2015 (Vol. 30, pp. 1–6). EDP Sciences.
Abstract: In recent years testing autonomous vehicles on public roads has become a reality. However, before having autonomous vehicles completely accepted on the roads, they have to demonstrate safe operation and reliable interaction with other traffic participants. Furthermore, in real situations and long term operation, there is always the possibility that diverse components may fail. This paper deals with possible sensor faults by defining a federated sensor data fusion architecture. The proposed architecture is designed to detect obstacles in an autonomous vehicle’s environment while detecting a faulty sensor using SVM models for fault detection and diagnosis. Experimental results using sensor information from the KITTI dataset confirm the feasibility of the proposed architecture to detect soft and hard faults from a particular sensor.
|
M. Oliveira, L. Seabra Lopes, G. Hyun Lim, S. Hamidreza Kasaei, Angel D. Sappa, & A. Tomé. (2015). Concurrent Learning of Visual Codebooks and Object Categories in Open- ended Domains. In Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on, Hamburg, Germany, 2015 (pp. 2488–2495). Hamburg, Germany: IEEE.
Abstract: In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are usually constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using codebooks constructed offline.
|
Dennis G. Romero, A. Frizera, Angel D. Sappa, Boris X. Vintimilla, & T.F. Bastos. (2015). A predictive model for human activity recognition by observing actions and context. In ACIVS 2015 (Advanced Concepts for Intelligent Vision Systems), International Conference on, Catania, Italy, 2015 (pp. 323–333).
Abstract: This paper presents a novel model to estimate human activities – a human activity is defined by a set of human actions. The proposed approach is based on the usage of Recurrent Neural Networks (RNN) and Bayesian inference through the continuous monitoring of human actions and its surrounding environment. In the current work human activities are inferred considering not only visual analysis but also additional resources; external sources of information, such as context information, are incorporated to contribute to the activity estimation. The novelty of the proposed approach lies in the way the information is encoded, so that it can be later associated according to a predefined semantic structure. Hence, a pattern representing a given activity can be defined by a set of actions, plus contextual information or other kind of information that could be relevant to describe the activity. Experimental results with real data are provided showing the validity of the proposed approach.
|
Dennys Paillacho, F. Novillo, W. Agila., & V. Huilcapi. (2015). Impacto de las redes de comunicaciones en los Sistemas Robóticos de Control. Revista Politécnica, Vol. 35, pp. 97–102.
Abstract: El análisis de incidencia que tienen las redes de comunicaciones sobre el comportamiento de los sistemas robóticos de control en red muestra grandes dificultades cuando se quieren hacer evaluaciones de tipo analítico. Por tal razón, en este trabajo un análisis que utiliza una aproximación basada en simulación es propuesto, de manera que el comportamiento temporal y espacial de un sistema robótico de control en red pueda ser evaluado. Para tal efecto, se propone un entorno de validación mediante el cual una red de comunicaciones permita distribuir mensajes de control entre el controlador principal y los controladores remotos ubicados en cada articulación angular del robot manipulador planar. Las interacciones entre los componentes del sistema han sido modeladas mediante un sistema de capas. Dicho modelo es llevado a un entorno de simulación con la finalidad de analizar el impacto de distintos parámetros de comunicaciones (i.e. tipo de red, tasa de datos y tamaño de datos) sobre el ciclo de comunicación y el error de seguimiento de trayectoria en un sistema robótico.
|
Cristhian A. Aguilera, Angel D. Sappa, & R. Toledo. (2015). LGHD: A feature descriptor for matching across non-linear intensity variations. In IEEE International Conference on, Quebec City, QC, 2015 (pp. 178–181). Quebec City, QC, Canada: IEEE.
Abstract: This paper presents a new feature descriptor suitable to the task of matching features points between images with nonlinear intensity variations. This includes image pairs with significant illuminations changes, multi-modal image pairs and multi-spectral image pairs. The proposed method describes the neighbourhood of feature points combining frequency and spatial information using multi-scale and multi-oriented Log- Gabor filters. Experimental results show the validity of the proposed approach and also the improvements with respect to the state of the art.
|
Marta Diaz, Dennys Paillacho, & Cecilio Angulo. (2015). Evaluating Group-Robot Interaction in Crowded Public Spaces: A Week-Long Exploratory Study in the Wild with a Humanoid Robot Guiding Visitors Through a Science Museum. International Journal of Humanoid Robotics, Vol. 12.
Abstract: This paper describes an exploratory study on group interaction with a robot-guide in an open large-scale busy environment. For an entire week a humanoid robot was deployed in the popular Cosmocaixa Science Museum in Barcelona and guided hundreds of people through the museum facilities. The main goal of this experience is to study in the wild the episodes of the robot guiding visitors to a requested destination focusing on the group behavior during displacement. The walking behavior follow-me and the face to face communication in a populated environment are analyzed in terms of guide- visitors interaction, grouping patterns and spatial formations. Results from observational data show that the space configurations spontaneously formed by the robot guide and visitors walking together did not always meet the robot communicative and navigational requirements for successful guidance. Therefore additional verbal and nonverbal prompts must be considered to regulate effectively the walking together and follow-me behaviors. Finally, we discuss lessons learned and recommendations for robot’s spatial behavior in dense crowded scenarios.
|
Ortiz J., Londono J., Novillo F., Ampuno A., & Chávez M. (2015). Determinación de Invariantes en Grandes Centros de Datos basados en Topología Fat-Tree. Revista Politécnica, Vol. 35, pp. 91–96.
Abstract: Durante los últimos años ha existido un fuerte incremento en el acceso a internet, causando que los centros de datos ( DC) deban adaptar dinámicamente su infraestructura de red de cara a enfrentar posibles problemas de congestión, la cual no siempre se da de forma oportuna. Ante esto, nuevas topologías de red se han propuesto en los últimos años, como una forma de brindar mejores condiciones para el manejo de tráfico interno, sin embargo es común que para el estudio de estas mejoras, se necesite recrear el comportamiento de un verdadero DC en modelos de simulación/emulación. Por lo tanto se vuelve esencial validar dichos modelos, de cara a obtener resultados coherentes con la realidad. Esta validación es posible por medio de la identificación de ciertas propiedades que se deducen a partir de las variables y los parámetros que describen la red, y que se mantienen en las topologías de los DC para diversos escenarios y/o configuraciones. Estas propiedades, conocidas como invariantes, son una expresión del funcionamiento de la red en ambientes reales, como por ejemplo la ruta más larga entre dos nodos o el número de enlaces mínimo que deben fallar antes de una pérdida de conectividad en alguno de los nodos de la red. En el presente trabajo se realiza la identificación, formulación y comprobación de dos invariantes para la topología Fat-Tree, utilizando como software emulador a mininet. Las conclusiones muestran resultados concordantes entre lo analítico y lo práctico.
|
Julien Poujol, Cristhian A. Aguilera, Etienne Danos, Boris X. Vintimilla, Ricardo Toledo, & Angel D. Sappa. (2015). A visible-Thermal Fusion based Monocular Visual Odometry. In Iberian Robotics Conference (ROBOT 2015), International Conference on, Lisbon, Portugal, 2015 (Vol. 417, pp. 517–528).
Abstract: The manuscript evaluates the performance of a monocular visual odometry approach when images from different spectra are considered, both independently and fused. The objective behind this evaluation is to analyze if classical approaches can be improved when the given images, which are from different spectra, are fused and represented in new domains. The images in these new domains should have some of the following properties: i) more robust to noisy data; ii) less sensitive to changes (e.g., lighting); iii) more rich in descriptive information, among other. In particular in the current work two different image fusion strategies are considered. Firstly, images from the visible and thermal spectrum are fused using a Discrete Wavelet Transform (DWT) approach. Secondly, a monochrome threshold strategy is considered. The obtained representations are evaluated under a visual odometry framework, highlighting their advantages and disadvantages, using different urban and semi-urban scenarios. Comparisons with both monocular-visible spectrum and monocular-infrared spectrum, are also provided showing the validity of the proposed approach.
|
