Browsing by Author "Espinace Ronda, Pablo Andrés"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    A Mobile Robotics Course for Undergraduate Students in Computer Science
    (IEEE, 2006) Soto Arriaza, Alvaro; Espinace Ronda, Pablo Andrés; Mitnik Asun, Ruben Felipe
    A first generation of mobile robots able to cope with the high uncertainty of natural environments is starting to emerge. As a consequence, there is an increasing need for theoretical and practical courses that can formally teach the state of the art of the technology. This paper describes our experience teaching a mobile robotics course as part of our computer science curriculum for undergraduate students. The course has a strong experimental part, where the goal is to provide the students with a set of hand-on experiences using real mobile robots. In particular, we show how using a simple differential drive mobile platform and a low cost visual sensor, it is possible to teach the topics that are currently most relevant to the area of mobile robot programming for autonomous navigation. The course starts by illustrating low level control routines, such as locomotion, and simple behaviors, such as obstacle avoidance and target tracking in non-structured environments. Then, as the course moves to higher level tasks such as localization and mapping, the real world becomes too complex and a more structured world is needed. A structured world, called MazeWorld is then presented where we are able to illustrate high level topics using limited perception capabilities. In addition to the main parts of the class, we also describe the perception algorithms that we developed to achieve autonomous navigation in non-structured environments and in MazeWorld. Our experience indicates that the course is highly motivating for the students. They are able to reinforce several topics from the computer science curriculum and they learn the basis for advanced coursework, research, and the development of applications in robotics and related fields, such as, artificial intelligence and computer perception
  • Thumbnail Image
    Item
    Enhancing K-Means using class labels
    (2013) Peralta Márquez, Billy Mark; Espinace Ronda, Pablo Andrés; Soto Arriaza, Álvaro Marcelo
  • Thumbnail Image
    Item
    Improving the selection and detection of visual landmarks through object tracking
    (IEEE, 2008) Espinace Ronda, Pablo Andrés; Soto Arriaza, Álvaro Marcelo
    The unsupervised selection and posterior recognition of visual landmarks is a highly valuable perceptual capability for a mobile robot. Recently, we proposed a system that aims to achieve this capability by combining a bottom-up data driven approach with top-down feedback provided by high level semantic representations. The bottom-up approach is based on three main mechanisms: visual attention, area segmentation, and landmark characterization. The top-down feedback is based on two information sources: i) An estimation of the robot position that reduces the searching scope for potential matches with previously selected landmarks, ii) A set of weights that, according to the results of previous recognitions, controls the influence of different segmentation algorithms in the recognition of each landmark. In this paper we explore the benefits of extending our previous work by including a visual tracking step for each of the selected landmarks. Our intuition is that the inclusion of a tracking step can help to improve the model of each landmark by associating and selecting information from its most significant views. Furthermore, it can also help to avoid problems related to the selection of spurious landmarks. Our results confirm these intuitions by showing that the inclusion of the tracking step produces a significant increase in the recall rate for landmark recognition.
  • Thumbnail Image
    Item
    Indoor scene recognition by a mobile robot through adaptive object detection
    (2013) Espinace Ronda, Pablo Andrés; Soto Arriaza, Álvaro Marcelo; Kollar, T.; Roy, N.
  • No Thumbnail Available
    Item
    Indoor scene recognition through object detection
    (IEEE, 2010) Espinace Ronda, Pablo Andrés; Kollar, T.; Soto, A.; Roy, N.
    Scene recognition is a highly valuable perceptual ability for an indoor mobile robot, however, current approaches for scene recognition present a significant drop in performance for the case of indoor scenes. We believe that this can be explained by the high appearance variability of indoor environments. This stresses the need to include high-level semantic information in the recognition process. In this work we propose a new approach for indoor scene recognition based on a generative probabilistic hierarchical model that uses common objects as an intermediate semantic representation. Under this model, we use object classifiers to associate low-level visual features to objects, and at the same time, we use contextual relations to associate objects to scenes. As a further contribution, we improve the performance of current state-of-the-art category-level object classifiers by including geometrical information obtained from a 3D range sensor that facilitates the implementation of a focus of attention mechanism within a Monte Carlo sampling scheme. We test our approach using real data, showing significant advantages with respect to previous state-of-the-art methods.
  • Thumbnail Image
    Item
    Visual Recognition to Access and Analyze People Density and Flow Patterns in Indoor Environments
    (IEEE, 2015) Ruz Ruz, Cristian Daniel; Pieringer Baeza, Christian Philip; Peralta Marquez, Billy Mark; Lillo Valles, Iván Alberto; Espinace Ronda, Pablo Andrés; Gonzalez, R.; Wendt González, Bruno Nicolás; Mery Quiroz, Domingo Arturo; Soto Arriaza, Álvaro
    This work describes our experience developing a system to access density and flow of people in large indoor spaces using a network of RGB cameras. The proposed system is based on a set of overlapped and calibrated cameras. This facilitates the use of geometric constraints that help to reduce visual ambiguities. These constraints are combined with classifiers based on visual appearance to produce an efficient and robust method to detect and track humans. In this work, we argue that flow and density of people are low level measurements that need to be complemented with suitable analytic tools to bridge semantic gaps and become useful information for a target application. Consequently, we also propose a set of analytic tools that help a human user to effectively take advantage of the measurements provided by the system. Finally, we report results that demonstrate the relevance of the proposed ideas.