Task-based telemanipulation for maintenance in large scientific facilities

This thesis presents a task-oriented approach to telemanipulation for maintenance in large scientific facilities, with specific focus on the particle accelerator facilities at European Organization for Nuclear Research (CERN) in Geneva, Switzerland and GSI Helmholtz Centre for Heavy Ion Research (GSI) in Darmstadt, Germany. It examines how telemanipulation can be used in these facilities and reviews how this differs from the representation of telemanipulation tasks within the literature. It provides methods to assess and compare telemanipulation procedures as well a test suite to compare telemanipulators themselves from a dexterity perspective. It presents a formalisation of telemanipulation procedures into a hierarchical model which can be then used as a basis to aid maintenance engineers in assessing tasks for telemanipulation, and as the basis for future research. The model introduces a new concept of Elemental Actions as the building block of telemanipulation movements and incorporates the dependent factors for procedures at a higher level of abstraction. In order to gain insight into realistic tasks performed by telemanipulation systems within both industrial and research environments a survey of teleoperation experts is presented. Analysis of the responses is performed from which it is concluded that there is a need within the robotics community for physical benchmarking tests which are geared towards evaluating the dexterity of telemanipulators for comparison of their dexterous abilities. A three stage test suite is presented which is designed to allow maintenance engineers to assess different telemanipulators for their dexterity. This incorporates general characteristics of the system, a method to compare kinematic reachability of multiple telemanipulators and physical test setups to assess dexterity from a both a qualitative perspective and measurably by using performance metrics. Finally, experimental results are provided for the application of the proposed test suite onto two telemanipulation systems, one from a research setting and the other within CERN. It describes the procedure performed and discusses comparisons between the two systems, as well as providing input from the expert operator of the CERN system.

Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection

We present a novel approach for detecting severe obstructive sleep apnea (OSA) cases by introducing non-linear analysis into sustained speech characterization. The proposed scheme was designed for providing additional information into our baseline system, built on top of state-of-the-art cepstral domain modeling techniques, aiming to improve accuracy rates. This new information is lightly correlated with our previous MFCC modeling of sustained speech and uncorrelated with the information in our continuous speech modeling scheme. Tests have been performed to evaluate the improvement for our detection task, based on sustained speech as well as combined with a continuous speech classifier, resulting in a 10% relative reduction in classification for the first and a 33% relative reduction for the fused scheme. Results encourage us to consider the existence of non-linear effects on OSA patients' voices, and to think about tools which could be used to improve short-time analysis.

Una contribución a la programación cognitiva: arquitecturas de segunda generación para representación del conocimiento

La tesis propone el concepto y diseño de una arquitectura cognitiva para representación de conocimiento profesional especializado en clases de dominios relacionados con el mundo físico. Constituye una extensión de los trabajos de B.Chandrasekaran, potenciando el concepto de arquitectura basada en tareas genéricas propuesta por dicho autor. En base a la arquitectura propuesta, se ha desarrollado un entorno como herramienta de construcción de sistemas expertos de segunda generación, así como un lenguaje para programación cognitiva (DECON)- Dicho entorno, programado en lenguaje C sobre UNIX, ha sido utilizado para el desarrollo de un sistema para predicción de avenidas en la Cuenca Hidrográfica del Jucar, en el marco del proyecto SAIH. Primeramente, la tesis plantea el problema de la modelización del comportamiento de los sistemas físicos, reflejando las limitaciones de las formas clásicas de representación del conocimiento para abordar dicho problema, así como los principales enfoques más recientes basados en el concepto de arquitectura cognitiva y en las técnicas de simulación cualitativa. Se realiza después una síntesis de la arquitectura propuesta, a nivel del conocimiento, para detallar posteriormente su desarrollo a nivel simbólico y de implementación, así como el método general para la construcción de modelos sobre la arquitectura. Se muestra también un resumen de los principales aspectos del desarrollo de software. Finalmente, en forma de anejos, se presenta un caso de estudio, el sistema SIRAH (Sistema Inteligente de Razonamiento Hidrológico), junto con la gramática formal del lenguaje de soporte para la definición de modelos.---ABSTRACT---The thesis proposes the concept and design of a cognitive architecture for professional knowledge representation, specialized in domain classes related to the physical world. It is an extensión of the Chandrasekaran's work, improving the concept of Generic Task based architecture introduced by this author. Based on the proposed architecture, an environment has been developed, as a case of second generation building expert systems tool, as well as a language for cognitive programming (DECON). The environment, programmed in C lenguage on UNIX operating system, has been used to develop a system for flood prediction in the Jucar watershed, inside of the SAIH project. Firstly, the behavior modeling problem of physical systems is discussed, showing the limitations of the classical representations to tackle it, beside the most recent approaches based on cognitive architecture concepts and qualitative simulation technique. An overview of the architecture at the knowledge level is then made, being followed by its symbolic and implementation level description, as well as a general guideline for building models on top of the architecture. The main aspects of software development are also introduced. Finaly, as annexes, a case of study -the SIRAH system (Sistema Inteligente de RAzonamiento Hidrológico)- is introduced, along with the formal grammar of the support language for model definition.

Cooperative Task Execution between Modular Robots Based on Tight-Loose Cooperation Strategies

The complexity in the execution of cooperative tasks is high due to the fact that a robot team requires movement coordination at the beginning of the mission and continuous coordination during the execution of the task. A variety of techniques have been proposed to give a solution to this problem assuming standard mobile robots. This work focuses on presenting the execution of a cooperative task by a modular robot team. The complexity of the task execution increases due to the fact that each robot is composed of modules which have to be coordinated in a proper way to successfully work. A combined tight and loose cooperation strategy is presented and a bar-pushing example is used as a cooperative task to show the performance of this type of system.

Accelerating FPGA-based evolution of wavelet transform filters by optimized task scheduling

Adaptive embedded systems are required in various applications. This work addresses these needs in the area of adaptive image compression in FPGA devices. A simplified version of an evolution strategy is utilized to optimize wavelet filters of a Discrete Wavelet Transform algorithm. We propose an adaptive image compression system in FPGA where optimized memory architecture, parallel processing and optimized task scheduling allow reducing the time of evolution. The proposed solution has been extensively evaluated in terms of the quality of compression as well as the processing time. The proposed architecture reduces the time of evolution by 44% compared to our previous reports while maintaining the quality of compression unchanged with respect to existing implementations. The system is able to find an optimized set of wavelet filters in less than 2 min whenever the input type of data changes.

A visual framework to accelerate knowledge discovery based on dimensionality reduction minimizing degradation of quality

Tradicionalmente, el uso de técnicas de análisis de datos ha sido una de las principales vías para el descubrimiento de conocimiento oculto en grandes cantidades de datos, recopilados por expertos en diferentes dominios. Por otra parte, las técnicas de visualización también se han usado para mejorar y facilitar este proceso. Sin embargo, existen limitaciones serias en la obtención de conocimiento, ya que suele ser un proceso lento, tedioso y en muchas ocasiones infructífero, debido a la dificultad de las personas para comprender conjuntos de datos de grandes dimensiones. Otro gran inconveniente, pocas veces tenido en cuenta por los expertos que analizan grandes conjuntos de datos, es la degradación involuntaria a la que someten a los datos durante las tareas de análisis, previas a la obtención final de conclusiones. Por degradación quiere decirse que los datos pueden perder sus propiedades originales, y suele producirse por una reducción inapropiada de los datos, alterando así su naturaleza original y llevando en muchos casos a interpretaciones y conclusiones erróneas que podrían tener serias implicaciones. Además, este hecho adquiere una importancia trascendental cuando los datos pertenecen al dominio médico o biológico, y la vida de diferentes personas depende de esta toma final de decisiones, en algunas ocasiones llevada a cabo de forma inapropiada. Ésta es la motivación de la presente tesis, la cual propone un nuevo framework visual, llamado MedVir, que combina la potencia de técnicas avanzadas de visualización y minería de datos para tratar de dar solución a estos grandes inconvenientes existentes en el proceso de descubrimiento de información válida. El objetivo principal es hacer más fácil, comprensible, intuitivo y rápido el proceso de adquisición de conocimiento al que se enfrentan los expertos cuando trabajan con grandes conjuntos de datos en diferentes dominios. Para ello, en primer lugar, se lleva a cabo una fuerte disminución en el tamaño de los datos con el objetivo de facilitar al experto su manejo, y a la vez preservando intactas, en la medida de lo posible, sus propiedades originales. Después, se hace uso de efectivas técnicas de visualización para representar los datos obtenidos, permitiendo al experto interactuar de forma sencilla e intuitiva con los datos, llevar a cabo diferentes tareas de análisis de datos y así estimular visualmente su capacidad de comprensión. De este modo, el objetivo subyacente se basa en abstraer al experto, en la medida de lo posible, de la complejidad de sus datos originales para presentarle una versión más comprensible, que facilite y acelere la tarea final de descubrimiento de conocimiento. MedVir se ha aplicado satisfactoriamente, entre otros, al campo de la magnetoencefalografía (MEG), que consiste en la predicción en la rehabilitación de lesiones cerebrales traumáticas (Traumatic Brain Injury (TBI) rehabilitation prediction). Los resultados obtenidos demuestran la efectividad del framework a la hora de acelerar y facilitar el proceso de descubrimiento de conocimiento sobre conjuntos de datos reales. ABSTRACT Traditionally, the use of data analysis techniques has been one of the main ways of discovering knowledge hidden in large amounts of data, collected by experts in different domains. Moreover, visualization techniques have also been used to enhance and facilitate this process. However, there are serious limitations in the process of knowledge acquisition, as it is often a slow, tedious and many times fruitless process, due to the difficulty for human beings to understand large datasets. Another major drawback, rarely considered by experts that analyze large datasets, is the involuntary degradation to which they subject the data during analysis tasks, prior to obtaining the final conclusions. Degradation means that data can lose part of their original properties, and it is usually caused by improper data reduction, thereby altering their original nature and often leading to erroneous interpretations and conclusions that could have serious implications. Furthermore, this fact gains a trascendental importance when the data belong to medical or biological domain, and the lives of people depends on the final decision-making, which is sometimes conducted improperly. This is the motivation of this thesis, which proposes a new visual framework, called MedVir, which combines the power of advanced visualization techniques and data mining to try to solve these major problems existing in the process of discovery of valid information. Thus, the main objective is to facilitate and to make more understandable, intuitive and fast the process of knowledge acquisition that experts face when working with large datasets in different domains. To achieve this, first, a strong reduction in the size of the data is carried out in order to make the management of the data easier to the expert, while preserving intact, as far as possible, the original properties of the data. Then, effective visualization techniques are used to represent the obtained data, allowing the expert to interact easily and intuitively with the data, to carry out different data analysis tasks, and so visually stimulating their comprehension capacity. Therefore, the underlying objective is based on abstracting the expert, as far as possible, from the complexity of the original data to present him a more understandable version, thus facilitating and accelerating the task of knowledge discovery. MedVir has been succesfully applied to, among others, the field of magnetoencephalography (MEG), which consists in predicting the rehabilitation of Traumatic Brain Injury (TBI). The results obtained successfully demonstrate the effectiveness of the framework to accelerate and facilitate the process of knowledge discovery on real world datasets.

Temporal task allocation in periodic environments. An approach based on synchronization

In this paper, we study a robot swarm that has to perform task allocation in an environment that features periodic properties. In this environment, tasks appear in different areas following periodic temporal patterns. The swarm has to reallocate its workforce periodically, performing a temporal task allocation that must be synchronized with the environment to be effective. We tackle temporal task allocation using methods and concepts that we borrow from the signal processing literature. In particular, we propose a distributed temporal task allocation algorithm that synchronizes robots of the swarm with the environment and with each other. In this algorithm, robots use only local information and a simple visual communication protocol based on light blinking. Our results show that a robot swarm that uses the proposed temporal task allocation algorithm performs considerably more tasks than a swarm that uses a greedy algorithm.

Vision-based vehicle detection and tracking with a mobile camera using a statistical framework

En esta tesis se aborda la detección y el seguimiento automático de vehículos mediante técnicas de visión artificial con una cámara monocular embarcada. Este problema ha suscitado un gran interés por parte de la industria automovilística y de la comunidad científica ya que supone el primer paso en aras de la ayuda a la conducción, la prevención de accidentes y, en última instancia, la conducción automática. A pesar de que se le ha dedicado mucho esfuerzo en los últimos años, de momento no se ha encontrado ninguna solución completamente satisfactoria y por lo tanto continúa siendo un tema de investigación abierto. Los principales problemas que plantean la detección y seguimiento mediante visión artificial son la gran variabilidad entre vehículos, un fondo que cambia dinámicamente debido al movimiento de la cámara, y la necesidad de operar en tiempo real. En este contexto, esta tesis propone un marco unificado para la detección y seguimiento de vehículos que afronta los problemas descritos mediante un enfoque estadístico. El marco se compone de tres grandes bloques, i.e., generación de hipótesis, verificación de hipótesis, y seguimiento de vehículos, que se llevan a cabo de manera secuencial. No obstante, se potencia el intercambio de información entre los diferentes bloques con objeto de obtener el máximo grado posible de adaptación a cambios en el entorno y de reducir el coste computacional. Para abordar la primera tarea de generación de hipótesis, se proponen dos métodos complementarios basados respectivamente en el análisis de la apariencia y la geometría de la escena. Para ello resulta especialmente interesante el uso de un dominio transformado en el que se elimina la perspectiva de la imagen original, puesto que este dominio permite una búsqueda rápida dentro de la imagen y por tanto una generación eficiente de hipótesis de localización de los vehículos. Los candidatos finales se obtienen por medio de un marco colaborativo entre el dominio original y el dominio transformado. Para la verificación de hipótesis se adopta un método de aprendizaje supervisado. Así, se evalúan algunos de los métodos de extracción de características más populares y se proponen nuevos descriptores con arreglo al conocimiento de la apariencia de los vehículos. Para evaluar la efectividad en la tarea de clasificación de estos descriptores, y dado que no existen bases de datos públicas que se adapten al problema descrito, se ha generado una nueva base de datos sobre la que se han realizado pruebas masivas. Finalmente, se presenta una metodología para la fusión de los diferentes clasificadores y se plantea una discusión sobre las combinaciones que ofrecen los mejores resultados. El núcleo del marco propuesto está constituido por un método Bayesiano de seguimiento basado en filtros de partículas. Se plantean contribuciones en los tres elementos fundamentales de estos filtros: el algoritmo de inferencia, el modelo dinámico y el modelo de observación. En concreto, se propone el uso de un método de muestreo basado en MCMC que evita el elevado coste computacional de los filtros de partículas tradicionales y por consiguiente permite que el modelado conjunto de múltiples vehículos sea computacionalmente viable. Por otra parte, el dominio transformado mencionado anteriormente permite la definición de un modelo dinámico de velocidad constante ya que se preserva el movimiento suave de los vehículos en autopistas. Por último, se propone un modelo de observación que integra diferentes características. En particular, además de la apariencia de los vehículos, el modelo tiene en cuenta también toda la información recibida de los bloques de procesamiento previos. El método propuesto se ejecuta en tiempo real en un ordenador de propósito general y da unos resultados sobresalientes en comparación con los métodos tradicionales. ABSTRACT This thesis addresses on-road vehicle detection and tracking with a monocular vision system. This problem has attracted the attention of the automotive industry and the research community as it is the first step for driver assistance and collision avoidance systems and for eventual autonomous driving. Although many effort has been devoted to address it in recent years, no satisfactory solution has yet been devised and thus it is an active research issue. The main challenges for vision-based vehicle detection and tracking are the high variability among vehicles, the dynamically changing background due to camera motion and the real-time processing requirement. In this thesis, a unified approach using statistical methods is presented for vehicle detection and tracking that tackles these issues. The approach is divided into three primary tasks, i.e., vehicle hypothesis generation, hypothesis verification, and vehicle tracking, which are performed sequentially. Nevertheless, the exchange of information between processing blocks is fostered so that the maximum degree of adaptation to changes in the environment can be achieved and the computational cost is alleviated. Two complementary strategies are proposed to address the first task, i.e., hypothesis generation, based respectively on appearance and geometry analysis. To this end, the use of a rectified domain in which the perspective is removed from the original image is especially interesting, as it allows for fast image scanning and coarse hypothesis generation. The final vehicle candidates are produced using a collaborative framework between the original and the rectified domains. A supervised classification strategy is adopted for the verification of the hypothesized vehicle locations. In particular, state-of-the-art methods for feature extraction are evaluated and new descriptors are proposed by exploiting the knowledge on vehicle appearance. Due to the lack of appropriate public databases, a new database is generated and the classification performance of the descriptors is extensively tested on it. Finally, a methodology for the fusion of the different classifiers is presented and the best combinations are discussed. The core of the proposed approach is a Bayesian tracking framework using particle filters. Contributions are made on its three key elements: the inference algorithm, the dynamic model and the observation model. In particular, the use of a Markov chain Monte Carlo method is proposed for sampling, which circumvents the exponential complexity increase of traditional particle filters thus making joint multiple vehicle tracking affordable. On the other hand, the aforementioned rectified domain allows for the definition of a constant-velocity dynamic model since it preserves the smooth motion of vehicles in highways. Finally, a multiple-cue observation model is proposed that not only accounts for vehicle appearance but also integrates the available information from the analysis in the previous blocks. The proposed approach is proven to run near real-time in a general purpose PC and to deliver outstanding results compared to traditional methods.

Si(100) versus Ge(100): Watching the interface formation for the growth of III-V-based solar cells on abundant substrates

We investigated the atomic surface properties of differently prepared silicon and germanium (100) surfaces during metal-organic vapour phase epitaxy/chemical vapour deposition (MOVPE/MOCVD), in particular the impact of the MOVPE ambient, and applied reflectance anisotropy/difference spectroscopy (RAS/RDS) in our MOVPE reactor to in-situ watch and control the preparation on the atomic length scale for subsequent III-V-nucleation. The technological interest in the predominant opto-electronic properties of III-V-compounds drives the research for their heteroepitaxial integration on more abundant and cheaper standard substrates such as Si(100) or Ge(100). In these cases, a general task must be accomplished successfully, i.e. the growth of polar materials on non-polar substrates and, beyond that, very specific variations such as the individual interface formation and the atomic step structure, have to be controlled. Above all, the method of choice to grow industrial relevant high-performance device structures is MOVPE, not normally compatible with surface and interface sensitive characterization tools, which are commonly based on ultrahigh vacuum (UHV) ambients. A dedicated sample transfer system from MOVPE environment to UHV enabled us to benchmark the optical in-situ spectra with results from various surfaces science instruments without considering disruptive contaminants. X-ray photoelectron spectroscopy (XPS) provided direct observation of different terminations such as arsenic and phosphorous and verified oxide removal under various specific process parameters. Absorption lines in Fourier-transform infrared (FTIR) spectra were used to identify specific stretch modes of coupled hydrides and the polarization dependence of the anti-symmetric stretch modes distinguished different dimer orientations. Scanning tunnelling microscopy (STM) studied the atomic arrangement of dimers and steps and tip-induced H-desorption proved the saturation of dangling bonds after preparati- n. In-situ RAS was employed to display details transiently such as the presence of H on the surface at lower temperatures (T <; 800°C) and the absence of Si-H bonds at elevated annealing temperature and also surface terminations. Ge buffer growth by the use of GeH4 enables the preparation of smooth surfaces and leads to a more pronounced amplitude of the features in the spectra which indicates improvements of the surface quality.

Semantic Technology Recommendation Based on the Analytic Network Process

Semantic technologies have become widely adopted in recent years, and choosing the right technologies for the problems that users face is often a difficult task. This paper presents an application of the Analytic Network Process for the recommendation of semantic technologies, which is based on a quality model for semantic technologies. Instead of relying on expert-based comparisons of alternatives, the comparisons in our framework depend on real evaluation results. Furthermore, the recommendations in our framework derive from user quality requirements, which leads to better recommendations tailored to users’ needs. This paper also presents an algorithm for pairwise comparisons, which is based on user quality requirements and evaluation results.

3D Object following based on visual information for Unmanned Aerial Vehicles

This article presents a novel system and a control strategy for visual following of a 3D moving object by an Unmanned Aerial Vehicle UAV. The presented strategy is based only on the visual information given by an adaptive tracking method based on the color information, which jointly with the dynamics of a camera fixed to a rotary wind UAV are used to develop an Image-based visual servoing IBVS system. This system is focused on continuously following a 3D moving target object, maintaining it with a fixed distance and centered on the image plane. The algorithm is validated on real flights on outdoors scenarios, showing the robustness of the proposed systems against winds perturbations, illumination and weather changes among others. The obtained results indicate that the proposed algorithms is suitable for complex controls task, such object following and pursuit, flying in formation, as well as their use for indoor navigation

Parallelizing irregular and pointer-based computations automatically: perspectives from logic and constraint programming

Irregular computations pose sorne of the most interesting and challenging problems in automatic parallelization. Irregularity appears in certain kinds of numerical problems and is pervasive in symbolic applications. Such computations often use dynamic data structures, which make heavy use of pointers. This complicates all the steps of a parallelizing compiler, from independence detection to task partitioning and placement. Starting in the mid 80s there has been significant progress in the development of parallelizing compilers for logic pro­gramming (and more recently, constraint programming) resulting in quite capable paralle­lizers. The typical applications of these paradigms frequently involve irregular computations, and make heavy use of dynamic data structures with pointers, since logical variables represent in practice a well-behaved form of pointers. This arguably makes the techniques used in these compilers potentially interesting. In this paper, we introduce in a tutoríal way, sorne of the problems faced by parallelizing compilers for logic and constraint programs and provide pointers to sorne of the significant progress made in the area. In particular, this work has resulted in a series of achievements in the areas of inter-procedural pointer aliasing analysis for independence detection, cost models and cost analysis, cactus-stack memory management, techniques for managing speculative and irregular computations through task granularity control and dynamic task allocation such as work-stealing schedulers), etc.

DAEDALUS at ImageCLEF 2011 Plant Identification Task: Using SIFT Keypoints for Object Detection

This paper describes the participation of DAEDALUS at ImageCLEF 2011 Plant Identification task. The task is evaluated as a supervised classification problem over 71 tree species from the French Mediterranean area used as class labels, based on visual content from scan, scan-like and natural photo images. Our approach to this task is to build a classifier based on the detection of keypoints from the images extracted using Lowe’s Scale Invariant Feature Transform (SIFT) algorithm. Although our overall classification score is very low as compared to other participant groups, the main conclusion that can be drawn is that SIFT keypoints seem to work significantly better for photos than for the other image types, so our approach may be a feasible strategy for the classification of this kind of visual content.

UPM system for the translation task

This paper describes the UPM system for translation task at the EMNLP 2011 workshop on statistical machine translation (http://www.statmt.org/wmt11/), and it has been used for both directions: Spanish-English and English-Spanish. This system is based on Moses with two new modules for pre and post processing the sentences. The main contribution is the method proposed (based on the similarity with the source language test set) for selecting the sentences for training the models and adjusting the weights. With system, we have obtained a 23.2 BLEU for Spanish-English and 21.7 BLEU for EnglishSpanish

Towards execution time estimation in abstract machine-based languages

Abstract machines provide a certain separation between platformdependent and platform-independent concerns in compilation. Many of the differences between architectures are encapsulated in the speciflc abstract machine implementation and the bytecode is left largely architecture independent. Taking advantage of this fact, we present a framework for estimating upper and lower bounds on the execution times of logic programs running on a bytecode-based abstract machine. Our approach includes a one-time, programindependent proflling stage which calculates constants or functions bounding the execution time of each abstract machine instruction. Then, a compile-time cost estimation phase, using the instruction timing information, infers expressions giving platform-dependent upper and lower bounds on actual execution time as functions of input data sizes for each program. Working at the abstract machine level makes it possible to take into account low-level issues in new architectures and platforms by just reexecuting the calibration stage instead of having to tailor the analysis for each architecture and platform. Applications of such predicted execution times include debugging/veriflcation of time properties, certiflcation of time properties in mobile code, granularity control in parallel/distributed computing, and resource-oriented specialization.