Este trabalho propõe um módulo básico de aquisição e pré-processamento de imagem colorida aplicado a robôs móveis, implementado em hardware reconfigurável, dentro do conceito de sistemas SoC (System-on-a-Chip). O módulo básico é apresentado em conjunto com funções mais específicas de pré-processamento de imagem, que são utilizadas como base para a verificação das funcionalidades implementadas no trabalho proposto. As principais funções realizadas pelo módulo básico são: montagem de frames a partir dos pixels obtidos da câmera digital CMOS, controle dos diversos parâmetros de configuração da câmera e conversão de padrões de cores. Já as funções mais específicas abordam as etapas de segmentação, centralização, redução e interpretação das imagens adquiridas. O tipo de dispositivo reconfigurável utilizado neste trabalho é o FPGA (Field-Programmable Gate Array), que permite maior adequação das funções específicas às necessidades das aplicações, tendo sempre como base o módulo proposto. O sistema foi aplicado para reconhecer gestos e obteve a taxa 99,57% de acerto operando a 31,88 frames por segundo. / This work proposes a basic module for a mobile robot color image capture and pre-processing, implemented in reconfigurable hardware based on SoC (System-on-a-Chip). The basic module is presented with a specifics image pre-processing function that are used as a base for verify the functionalities implemented in this research. The mains functions implemented on this basic module are: to read the pixels provide by the CMOS camera for compose the frame, to adjust the parameters of the camera control and to convert color space. The specifics image pre-processing functions are used to do image segmentation, centralization, reduction and image classification. The reconfigurable dispositive used in this research is the FPGA (Field-Programmable Gate Array) that permit to adapt the specific function according to the application needs. The system was applied to recognize gesture and had 99,57% rate of true recognition at 31,88 frames per second.

This master‘s thesis describes the design and implementation of the system for detection and recognition of speed limit road signs. It focuses on the recognition of the red circular speed limit sign from the image data using the computer vision methods. Several methods were programmed and tested as a part of this thesis. In the final solution, the segmentation based on YCbCr color model is used. Detection of the circular sign and final classification is performed by template matching method. Algorithm for the tracking of the detected signs between frames of the video is used for better performance in real-time recognition. Application is developed using MATLAB and Simulink. The result is a simple driver assistance system prototype, which can be implemented in any computer with camera. The correct function of the algorithm was confirmed during a testing in a traffic.

Au cours de ce travail nous avons utilisé les potentialités de différentes modalités d'imagerie, que nous appliquons au domaine du végétal afin de contribuer au phénotypage haut-débit des semences et plantules. Nous nous somme principalement consacré à la recherche de réponses à deux problématiques spécifiques et importantes de ce secteur. Nous commençons par montrer l'applicabilité de l'imagerie en lumière visible inactinique et de l'imagerie thermographique passive pour imager le développement des semences et plantules, un phénomène biologique se déroulant normalement dans le sol et l’obscurité. Nous présentons nos apports à ce type d’imagerie, au travers de nos contributions à la conception et à la réalisation d’un système de vision en imagerie visible inactinique, ayant pour finalité la réalisation de mesures individualisées automatisées sur les semences, les plantules et les organes des plantules. Ce système gère les croisements de plantules, via l'utilisation originale de la diffusion anisotrope, ce qui nous a permis de multiplier, sans perte d'information, les débits par dix. De plus, ce système réalise la séparation des organes au moyen d’un critère générique basé sur le gravitropisme. La validation des algorithmes de traitement d'images du système de vision utilise des voies originales (simulation numérique et test de l'influence de l'incertitude via simulation agronomique). L’imagerie thermographique, qui capte le rayonnement thermique passif des objets, nous permet de visualiser et de mesurer les semences et plantules dans l'obscurité. Elle permet aussi de réaliser la segmentation et le suivi des organes de plantules. Cette technologie d'imagerie nous a aussi permis de montrer la faisabilité d'un dosage non destructif de teneur en sucre des organes de plantules de betterave. Ensuite nous proposons une méthodologie générique permettant la conception de capteurs bas-coût spectralement optimisés, en fonction de tâches applicatives déterminées. Cette méthodologie utilise la théorie de l’information, pour extraire de l’imagerie hyperspectrale, relativement coûteuse, l’information utile à la conception des capteurs dédiés bas-coût. L’intérêt de cette méthodologie pour le phénotypage des plantes est montré et justifie le transfert de celle-ci au monde de la recherche en biologie végétale. / Along this work, we have used the potentiality of different modalities of imagery that we apply to the plant domain so as to contribute to the high-throughput phenotyping of seeds and seedlings. We have mainly committed ourselves to the search for answers to two specific and important problematic in this domain. We begin by showing the applicability of visible imaging using an inactinic light and passive thermographic imaging to image the development of seeds and seedlings, a biological phenomenon usually occurring in soil and darkness. We present our contributions to this type of imaging through our contributions to the conception and the realization of a vision system using visible inactinic imaging, whose finality is the realization of individualized automated measurement on the seeds, the seedlings and the organs of the seedlings. This system handle seedling crossing, through the original use of anisotropic diffusion, which allowed us to multiply, without information loss, the output by ten. Furthermore, this system carries out the separation of the organs by means of a generic criterion based on gravitropism. The validation of the image processing algorithms of the vision system use original ways (numerical simulation and test of the influence of the uncertainty through agronomic simulation). Thermographic imaging, which captures the passive heat radiation of objects, allows us to visualize and to measure seeds and seedlings in the darkness. It also allows realizing the segmentation and the tracking of the organs of seedlings. This imaging technology also allowed us to demonstrate the feasibility of a non-destructive determination of sugar quantity in organs of beet seedlings. We then propose a generic methodology that allows the conception of spectrally optimized low-cost sensors, according to determined application tasks. This methodology uses information theory, to extract from, relatively expensive, hyperspectral imaging, the information needed for the conception of the dedicated low-cost sensors. The interest of this methodology for plant phenotyping has been shown and justifies its transfer to the world of research in plant biology.

This study examines the automatization potential for two production lines at Scania Transmission workshop in Södertälje using Industry 4.0 technologies. In order to do so, the capabilities of the operational performance and safety features of cobots and an Automated Visual Inspection System is theoretically investigated and intended to substitute CNC operators on certain tasks such as loading of conveyors and quality controls. The purpose of the study is to generate a realistic approach and give insight to the benefits of a future practical implementation.Previous research around these technologies as well as the actual data recordings and several interviews that took place during on-site visits is presented. The results show that a significant amount of time can be saved and allocated differently. Based on the findings of the study, a layout for the cobots and AVIS placement is proposed, aiming for CNC operator’s better control over the critical parts of the production lines, thus contributing to a much more manageable workflow.

A lightweight, powerful, yet efficient quad-rotor platform was designed and constructed to obtain experimental results of completely autonomous control of a hovering micro-UAV using a complete on-board vision system. The on-board vision and control system is composed of a Helios FPGA board, an Autonomous Vehicle Toolkit daughterboard, and a Kestrel Autopilot. The resulting platform is referred to as the Helio-copter. An efficient algorithm to detect, correlate, and track features in a scene and estimate attitude information was implemented with a combination of hardware and software on the FPGA, and real-time performance was obtained. The algorithms implemented include a Harris feature detector, template matching feature correlator, RANSAC similarity-constrained homography, color segmentation, radial distortion correction, and an extended Kalman filter with a standard-deviation outlier rejection technique (SORT). This implementation was designed specifically for use as an on-board vision solution in determining movement of small unmanned air vehicles that have size, weight, and power limitations. Experimental results show the Helio-copter capable of maintaining level, stable flight within a 6 foot by 6 foot area for over 40 seconds without human intervention.

No description available.

[ES] La presente tesis aborda la Interacción Humano-Robot para tareas industriales de tratamiento superficial, con el objetivo de obtener una verdadera sinergia entre el operador humano y el sistema robotizado, así como un funcionamiento robusto. En concreto, la tesis establece las bases sobre las cuales un robot con asistencia por teleoperación o autónomamente interacciona con los humanos y con los otros robots en la zona de trabajo. Las propuestas se validan mediante experimentación real utilizando hasta dos robots manipuladores 6R y 7R respectivamente. Las principales contribuciones son: - Asistencia robótica para el lijado industrial con aproximación suave a la superficie y restricciones de límite - Control de robots bimanuales usando teleoperación asistida para tareas de tratamiento superficial - Interfaz basada en Realidad Aumentada para la teleoperación de robots bimanuales La aplicación de técnicas de Control en Modo Deslizante (SMC, por sussiglas en inglés) tanto convencional como no convencional y una arquitectura de control basada en prioridades son las herramientas clave para el desarrollo de estas contribuciones. / [CA] La present tesi aborda la Interacció Humà-Robot per a tasques industrials de tractament de superfícies, amb l'objectiu d'obtindre una veritable sinergia entre l'operador humà i el sistema robotitzat, així com un funcionament robust. En concret, la tesi estableix les bases sobre les quals un robot amb assistència per teleoperació o autònomament interacciona amb els humans i amb els altres robots a la zona de treball. Les propostes es validen mitjançant experimentació real utilitzant fins a dos robots manipuladors 6R i 7R, respectivament. Les principals contribucions són: - Assistència robòtica per al poliment industrial amb aproximació suau a la superfície i restriccions de límit - Control de robots bimanuals emprant teleoperació assistida per a tasques de tractament superficial - Intefaç basada en Realitat Augmentada per a la teleoperació de robots bimanuals L'aplicació de tècniques de Control en Mode Lliscant (SMC, per les seues sigles en anglés)tant convencional com no convencional i una arquitectura de control basada en prioritats són les eines clau pel desenvolupament d'aquestes contribucions. / [EN] The present thesis work addresses Human-Robot Interaction for industrial surface treatment tasks, aiming to attain a true synergy between the human operator and the robot system, as well as a robust performance. Specifically, this thesis establishes the basis on which a robot, either assisted by teleoperation or working autonomously, interacts with humans and with other robots in its working area. These proposals are validated through real experimentation using up to two robot manipulators, 6R and 7R respectively. The main contributions are: - Robotic assistance for industrial sanding with a smooth approach to the surface and boundary constraints - Bimanual robot control using assisted teleoperation for surface treatment tasks - Augmented reality-based interface for bimanual robot teleoperation The appliance of conventional and non-conventional Sliding Mode Control (SMC) techniques and a priority-based control architecture are the fundamental tools for the development of these contributions. / García Fernández, A. (2023). Robust human-robot collaboration for polishing tasks in the automotive industry [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/198673

Les changements climatiques ont des impacts considérables sur le temps, les océans et les rivages, la vie sauvage. Ils amènent des problèmes désormais considérés comme majeurs par les gouvernements et organisations internationales. Ces efforts ont fourni un cadre à cette thèse, qui propose de procéder en boucle fermée de l’observation d’insectes ravageurs, avec des centaines de capteurs en réseau ("light traps"), au système d’information, et enfin à des décisions de lutte, manuelles ou automatiques. Le point d’appui pratique est la conception d’un système de comptage d’insectes proliférant dans les cultures de riz (BPH). L’abstraction que nous développons est celle d’une machine environnementale de grande taille, distribuée, qui capte et synthétise l’information, élabore des connaissances, et prend des décisions. Autour de cette abstraction, nous avons élaboré un système de vision "fisheye" effectuant le comptage des insectes. Nous proposons un système d’information géographique directement connecté au réseau de capteurs. Le couplage direct, "cyber-physique", entre les systèmes d’information et l’observation de l’environnement à échelle régionale est une nouveauté transposable, qui permet de comprendre et contrôler quantité d’évolutions. / Climate changes bring problems related to nature evolutions. Global warming has an impact on sea level, weather patterns, and wild life. A number of national and international organizations are developing research programs in these directions, including threats on cultures and insect proliferation. Monitoring these phenomena, observing consequences, elaborating counteracted strategies are critical for the economy and society.The initial motivation of this work was the understanding of change impacts in the Mekong Delta region. From there, automatic observation tools were designed with a real time information system able to integrate environmental measures, then to support knowledge production.Tracking environment evolutions is distributed sensing, which can be the association of efficient sensors and radio communications, operated under the control of an information system. Sensing insects is very complex due to their diversity and dispersion. However, this is feasible in the case of intensive agricultural production as it is the case of rice, having a small number of pests. An automatic vision observatory is proposed to observe the main threats for the rice, as an evolution of manual light traps. Radio communication weaves these observatories into a network with connection to databases storing measures and possible counteractions. An example observatory has a fisheye camera and insect counting algorithms for the BPH practical case in Vietnam.By considering the observation system as an input for an abstract machine, and considering decision and actions taken as a possible control on the environment, we obtain a framework for knowledge elaboration that can be useful in lots of other situations.

Attitude and position determination systems in satellites are absolutely necessary to keep the desired trajectory. A very accurate, reliable and most used sensor for attitude determination is the star tracker, which orient itself in space by observing and comparing star constellations with known star patterns. For on earth tests of movements and docking maneuvers of spacecrafts, the new Spacecraft Maneuvering and Docking (SMD) facility at the chair of Aerospace Information Technology at the University of Würzburg has been built. Air bearing systems on the space ve- hicles help to create micro gravity environment on a smooth surface and simulate an artificial space-like surrounding. A new star tracker based optical sensor for indoor application need to be developed in order to get the attitude and position of the vehicles. The main objective of this thesis is to research on feasible star tracking algorithms for the SMD facility first and later to implement a star detection software framework with new developed voting methods to give the star tracker system its fully autonomous function of attitude determination and position tracking. Furthermore, together with image processing techniques, the software framework is embedded into a controller board. This thesis proposes also a wireless network system for the facility, where all the devices on the vehicles can uniquely communicate within the same network and a devel- opment of a ground station to monitor the star tracker process has also been introduced. Multiple test results with different scenarios on position tracking and attitude determination, discussions and suggestions on improvements complete the entire thesis work.

Die gemeinsame Integration von Bildsensor und analoger hochparalleler Verarbeitungseinheit stellt eine Möglichkeit zur Realisierung von leistungsfähigen ein-chip Bildaufnahmesystemen dar. Die vorliegende Arbeit liefert Beiträge zum systematischen Entwurf von derartigen Systemen und analysiert bekannte und neuartige Schaltungstechniken bezüglich ihrer Eignung für deren Implementierung. Anhand des vom Autor mitentwickelten CMOS-Bildsensors mit hochparalleler analoger Bildverarbeitungseinheit werden die vorgestellten Methoden und Schaltungstechniken demonstriert. Die Problematik beim Entwurf hochparalleler analoger Systeme besteht in der im Vergleich zu digitalen Systemen geringen Automatisierbarkeit. Es ist kein top-down-Entwurf möglich, da nicht jede beliebige Funktion mit beliebiger Genauigkeit realisierbar ist. Um die jeweilige Genauigkeit der Funktionsblöcke bei der Analyse des hochparallelen Systems berücksichtigen zu können, sind rechenaufwendige Simulationen nötig. Um diesen Rechenaufwand zu senken, wird vorgeschlagen, für die Simulation des Gesamtsystems einen angepaßten Simulator und für die Analyse der schaltungstechnischen Realisierung der Funktionsblöcke konventionelleWerkzeuge für elektrische Netzwerke zu verwenden. Die beiden Simulationsdomänen werden mit Hilfe von numerischen Verhaltensmodellen verbunden. Durch diese Trennung wird die Simulation des Gesamtsystems als Bestandteil des Entwurfsflusses praktikabel. Für die Bewertung, inwieweit die zufälligen Schwankungen der Bauelementeparameter das Verhalten von Baublöcken beeinflussen, wird die Varianzanalyse als Alternative zur konventionellen Monte-Carlo-Analyse vorgeschlagen. Die Varianzanalyse ist wesentlich weniger rechenaufwendig und liefert genaue Resultate für alle Schaltungseigenschaften mit hinreichend glatten Parameterabhängigkeiten, wenn die Bauelementeparameter als normalverteilt und statistisch unabhängig angenommen werden können. Sie hat darüberhinaus den Vorteil, das Schaltungsverständnis für den Entwerfer zu erhöhen, da sofort die Bauelementeparameter mit dem größten Einfluß auf das Schaltungsverhalten identifiziert werden können. Der Vergleich verschiedener Schaltungstechniken hat gezeigt, daß zeitdiskrete wertkontinuierliche Verfahren, bei denen die Information als Strom repräsentiert wird, für die Realisierung von hochparallelen analogen Systemen besonders geeignet sind. Als besonderer Vorteil ist die weitestgehende Unabhängigkeit des Verhaltens derartiger Schaltungen von Bauelementeparametern hervorzuheben.Weitere Schaltungstechniken, deren Verhalten von zufälligen Parameterabweichungen nur wenig beeinflußt werden, sind in einer Taxonomie zusammengefaßt. Es wurde ein CMOS-Bildsensor mit hochparalleler analoger Bildverarbeitungseinheit und digitaler Ausgabe realisiert. Der current-mode-Bildsensor ist separat von der Verarbeitungseinheit angeordnet. Es wurden vier verschiedene Realisierungsmöglichkeiten untersucht und eine konventionelle integrierende voltage-mode Pixelzelle mit nachfolgendem differentiellen Spannungs- Strom-Wandler realisiert. Das Rechenfeld ist für die räumliche Faltung oder lineare Transformation von Bilddaten mit digital bereitzustellenden Koeffizienten ausgelegt. Dessen Operation basiert auf einer bit-weisen analogen Verarbeitung. Der Schaltkreis wurde erfolgreich getestet. Die nachgewiesene Bildqualität deckt sich in guter Näherung mit den bei der Simulation des Gesamtsystems getroffenen Vorhersagen / The joined implementation of an image sensor and a highly parallel analog processing unit is an advantageous approach for realizing efficient single-chip vision systems. This thesis proposes a design flow for the development of such systems. Moreover known and novel circuit techniques are analysed with respect for their suitability for the implementation of highly parallel systems. The presented methodologies and circuit techniques are demonstrated at the example of a CMOS image sensor with an embedded highly parallel analog image processing unit in whose design the author was involved. One of the major problems in designing highly parallel analog circuits is the low automation compared to the design of digital circuits. As not every function can be realized with arbitrary accuracy top-down-design is not feasible. So, when analysing the system behaviour the respective precision of each function block has to be considered. As this is a very demanding task in terms of computing power, it is proposed to use a dedicated tool for the simulation of the system and conventional network analysis tools for the inspection of the circuit realizations. Both simulation domains are combined by means of numerical behavioural models. By using separate tools system-simulations of highly parallel analog systems as a part of the design flow become practicable. Variance analysis basing on parameter sensitivities is proposed as an alternative to the conventional Monte-Carlo-analysis for investigating the influence of random device parameter variations on the system behaviour. Variance analysis requires much less computational effort while providing accurate results for all circuit properties with sufficiently smooth parameter dependencies if the random parameters can be assumed normally distributed and statistically independent. Additionally, variance analysis increases the designer’s knowledge about the circuit, as the device parameters with the highest influence on the circuit performance can immediately be identified. The comparison of various circuit techniques has shown, that sampled-time continuous-valued current-mode principles are the best choice for realizing highly parallel analog systems. A distinctive advantage of such circuits is their almost independence from device parameters. A selection of further circuit techniques with low sensitivity to random device parameter variations are summarized in a taxonomy. A CMOS image sensor with embedded highly parallel analog image processing unit has been implemented. The image sensor provides a current-mode output and is arranged separate from the processing unit. Four different possibilities for realizing an image sensor have been analysed. A conventional integrating voltage-mode pixel cell with a succeeding differential voltage- to-current-converter has been selected. The processing unit is designed for performing spatial convolution and linear transformation with externally provided digital kernels. It operates in bit-wise analog manner. The chip has been tested successfully. The measured image quality in good approximation corresponds with the estimations made with system simulations.