No description available.

Autonomous visual navigation algorithms for ground mobile robotic systems working in unstructured environments have been extensively studied for decades. Among these work, algorithm performance evaluations between different design configurations mainly involve the use of benchmark datasets with a limited number of real-world trails. Such evaluations, however, have difficulties to provide sufficient statistical power for performance quantification. In addition, they are unable to independently assess the algorithm robustness to individual realistic uncertainty sources, including the environment variations and processing errors. This research presents a quantitative approach to performance and robustness evaluation and optimisation of autonomous visual navigation algorithms, using large scale Monte-Carlo analyses. The Monte-Carlo analyses are supported by a simulation environment designed to represent a real-world level of visual information, using the perturbations from realistic visual uncertainties and processing errors. With the proposed evaluation method, a stereo vision based autonomous visual navigation algorithm is designed and iteratively optimised. This algorithm encodes edge-based 3D patterns into a topological map, and use them for the subsequent global localisation and navigation. An evaluation on the performance perturbations from individual uncertainty sources indicates that the stereo match error produces significant limitation for the current system design. Therefore, an optimisation approach is proposed to mitigate such an error. This maximises the Fisher information available in stereo image pairs by manipulating the stereo geometry. Moreover, the simulation environment is further updated in association with the algorithm design, which include the quantitative modelling and simulation of localisation error to the subsequent navigation behaviour. During a long-term Monte-Carlo evaluation and optimisation, the algorithm performance has been significantly improved. Simulation experiments demonstrate that the navigation of a 3-DoF robotic system is achieved in an unstructured environment, while possessing sufficient robustness to realistic visual uncertainty sources and systematic processing errors.

Every revolution in military affairs was always, to a large extent, driven by the appearance of new types of modern technologies. Many examples from the past revolutions reflect this fact, including the recent one between the 1970s and 1990s of the 20th century. This most recent revolution in military affairs had its roots in a Soviet concept of "military-technical revolution," which, as its name already indicates, gave the technology a great significance. Both above-mentioned theoretical concepts had a practical impact on how the battle operations were conducted, on changes in military doctrines and organization of forces, and the integration of new technologies into existing weapon systems. In the last revolution in military affairs from the 1980s and 1990s, the central role was played by precision-guided munitions, command and control systems, and also communication systems. Today there is an ongoing discussion about the potential new revolution in military affairs, which main drivers are expected to be artificial intelligence and robotic systems. This diploma thesis focuses on the definition of concepts "military-technical revolution," "revolution in military affairs," their evolution, and the new technologies that can cause a new revolution in the near future- artificial intelligence and...

No description available.

<p dir="ltr">The increasing global need for food security and sustainable agriculture underscores the urgency of advancing field phenotyping for enhanced plant breeding and crop management. Soybean, a major global protein source, is at the forefront of these advancements. Proximal sensing in soybean phenotyping offers a higher signal-to-noise ratio and resolution but has been underutilized in large-scale field applications due to low throughput and high labor costs. Moreover, there is an absence of automated solutions for in vivo proximal phenotyping of dicot plants. This thesis addresses these gaps by introducing a comprehensive, technologically sophisticated approach to modern field phenotyping.</p><p dir="ltr">Fully Automated Proximal Hyperspectral Imaging System: The first chapter presents the development of a cutting-edge hyperspectral imaging system integrated with a robotic arm. This system surpasses traditional imaging limitations, providing enhanced close-range data for accurate plant health assessment.</p><p dir="ltr">Robust Leaf Pose Estimation: The second chapter discusses the application of deep learning for accurate leaf pose estimation. This advancement is crucial for in-depth plant analysis, fostering better insights into plant health and growth, thereby contributing to increased crop yield and disease resistance.</p><p dir="ltr">PhenoBee – A Drone Mobility Platform: The third chapter introduces 'PhenoBee,' a dronebased platform designed for extensive field phenotyping. This innovative technology significantly broadens the capabilities of field data collection, showcasing its viability for widespread aerial phenotyping.</p><p dir="ltr">Adaptive Sampling for Dynamic Waypoint Planning: The final chapter details an adaptive sampling algorithm for efficient, real-time waypoint planning. This strategic approach enhances field scouting efficiency and precision, ensuring optimal data acquisition.</p><p dir="ltr">By integrating deep learning, robotic automation, aerial mobility, and intelligent sampling algorithms, the proposed solution revolutionizes the adaptation of in vivo proximal phenotyping on a large scale. The findings of this study highlight the potential to automate agriculture activities with high scalability and identify nutrient deficiencies, diseases, and chemical damage in crops earlier, thereby preventing yield loss, improving food quality, and expediting the development of agricultural products. Collectively, these advancements pave the way for more effective and efficient plant breeding and crop management, directly contributing to the enhancement of global food production systems. This study not only addresses current limitations in field phenotyping but also sets a new standard for technological innovation in agriculture.</p>

Manipuladores robóticos têm ganhado cada vez mais importância em operações espaciais por poderem substituir humanos na realização de tarefas perigosas ou demasiadamente demoradas e repetitivas. Em destaque tem-se os manipuladores de base livre, por poderem ser acoplados a satélites ou estações espaciais e representarem um grande desafio para engenheiros de controle. Tais robôs possuem dois modos de operação: com base livre controlada e com base livre flutuante. No primeiro modo a base do manipulador tem atitude e translação controladas por jatos propulsores ou rodas de reação, de modo que o comportamento do robô se aproxima de um manipulador de base fixa. Porém, há um considerável consumo de combustível e energia elétrica, além de novos distúrbios que são inseridos no sistema. No segundo modo, considerado neste trabalho de mestrado, os controles da base são desligados durante a operação e ela pode mover-se livremente em resposta aos movimentos do braço. Embora tenha-se notável economia de combustível e energia elétrica, o acoplamento dinâmico entre base e braço deve ser considerado tanto na modelagem como no projeto do controlador. Para modelar o robô espacial considerado neste projeto foi aplicado o método do Manipulador Dinamicamente Equivalente, que mapeia um manipulador de base livre flutuante através de um robô sub-atuado de base fixa. Dessa forma é possível utilizar sobre robôs espaciais técnicas de controle já desenvolvidas para manipuladores terrestres. Este trabalho trata da análise de controladores robustos e adaptativo aplicados sobre um manipulador planar de base livre flutuante com dois braços para realizar a tarefa de seguimento de trajetórias definidas no espaço de tarefa. Os sistemas de controle considerados foram: Regulador Linear Quadrático Recursivo Robusto (RLQR), controlador H-infinito robusto e controlador adaptativo com modos deslizantes. Os resultados mostraram que os controladores apresentaram desempenhos distintos mas ainda assim foram capazes de realizar a tarefa de seguir trajetórias no espaço de trabalho com erros de acompanhamento bastante pequenos. Foi elaborada também uma comparação quantitativa através de índices de desempenho considerando integral de torques e norma L2 de erros de acompanhamento. / Robotic manipulators gained greater importance in space operations by being able to replace humans in dangerous or very long and repetitive tasks. Free-floating manipulators are highlighted, because they can be coupled to satellites or space stations and represent a great challenge to control engineers. These robots have two operation modes: controlled base and free-floating base. In the first mode, the base has its attitude and translation controlled by propulsion jets or reaction wheels, so that the robot behavior is similar to a fixed-base manipulator. However, there is considerable fuel and electrical energy consumption, besides additional disturbances inserted in the system. In the second mode, which is considered in this work, the base is not controlled during operation and is able to move freely in response to movements of the arm. Even though there is a remarkable fuel and electrical energy saving, the dynamic coupling between base and arm must be taken into account during modelling and controller design. To model the space manipulator considered in this work the Dynamically Equivalent Manipulator method was used, which maps a free-floating manipulator into a underactuated fixed-base manipulator. Thus, it is possible to apply known control techniques for terrestrial manipulators on free-floating ones. This work discusses robust and adaptive controllers applied on a planar dual-arm free-floating space manipulator in order to track trajectories defined in the workspace. The considered control systems are: Robust Recursive Linear Quadratic Regulator, Robust H-infinity and Adaptive Sliding Modes. Results showed that the controllers had distinct performances but were still able to perform trajectory tracking in workspace with very small tracking errors. A quantitative comparison was also elaborated with performance indexes considering integral of torques and L2 norm of tracking errors.

Manipuladores robóticos têm ganhado cada vez mais importância em operações espaciais por poderem substituir humanos na realização de tarefas perigosas ou demasiadamente demoradas e repetitivas. Em destaque tem-se os manipuladores de base livre, por poderem ser acoplados a satélites ou estações espaciais e representarem um grande desafio para engenheiros de controle. Tais robôs possuem dois modos de operação: com base livre controlada e com base livre flutuante. No primeiro modo a base do manipulador tem atitude e translação controladas por jatos propulsores ou rodas de reação, de modo que o comportamento do robô se aproxima de um manipulador de base fixa. Porém, há um considerável consumo de combustível e energia elétrica, além de novos distúrbios que são inseridos no sistema. No segundo modo, considerado neste trabalho de mestrado, os controles da base são desligados durante a operação e ela pode mover-se livremente em resposta aos movimentos do braço. Embora tenha-se notável economia de combustível e energia elétrica, o acoplamento dinâmico entre base e braço deve ser considerado tanto na modelagem como no projeto do controlador. Para modelar o robô espacial considerado neste projeto foi aplicado o método do Manipulador Dinamicamente Equivalente, que mapeia um manipulador de base livre flutuante através de um robô sub-atuado de base fixa. Dessa forma é possível utilizar sobre robôs espaciais técnicas de controle já desenvolvidas para manipuladores terrestres. Este trabalho trata da análise de controladores robustos e adaptativo aplicados sobre um manipulador planar de base livre flutuante com dois braços para realizar a tarefa de seguimento de trajetórias definidas no espaço de tarefa. Os sistemas de controle considerados foram: Regulador Linear Quadrático Recursivo Robusto (RLQR), controlador H-infinito robusto e controlador adaptativo com modos deslizantes. Os resultados mostraram que os controladores apresentaram desempenhos distintos mas ainda assim foram capazes de realizar a tarefa de seguir trajetórias no espaço de trabalho com erros de acompanhamento bastante pequenos. Foi elaborada também uma comparação quantitativa através de índices de desempenho considerando integral de torques e norma L2 de erros de acompanhamento. / Robotic manipulators gained greater importance in space operations by being able to replace humans in dangerous or very long and repetitive tasks. Free-floating manipulators are highlighted, because they can be coupled to satellites or space stations and represent a great challenge to control engineers. These robots have two operation modes: controlled base and free-floating base. In the first mode, the base has its attitude and translation controlled by propulsion jets or reaction wheels, so that the robot behavior is similar to a fixed-base manipulator. However, there is considerable fuel and electrical energy consumption, besides additional disturbances inserted in the system. In the second mode, which is considered in this work, the base is not controlled during operation and is able to move freely in response to movements of the arm. Even though there is a remarkable fuel and electrical energy saving, the dynamic coupling between base and arm must be taken into account during modelling and controller design. To model the space manipulator considered in this work the Dynamically Equivalent Manipulator method was used, which maps a free-floating manipulator into a underactuated fixed-base manipulator. Thus, it is possible to apply known control techniques for terrestrial manipulators on free-floating ones. This work discusses robust and adaptive controllers applied on a planar dual-arm free-floating space manipulator in order to track trajectories defined in the workspace. The considered control systems are: Robust Recursive Linear Quadratic Regulator, Robust H-infinity and Adaptive Sliding Modes. Results showed that the controllers had distinct performances but were still able to perform trajectory tracking in workspace with very small tracking errors. A quantitative comparison was also elaborated with performance indexes considering integral of torques and L2 norm of tracking errors.

Made available in DSpace on 2014-12-17T14:56:20Z (GMT). No. of bitstreams: 1 EinsteinGS_DISSERT.pdf: 2235729 bytes, checksum: c7975deebdcccbba6d5c03bbecc7084d (MD5) Previous issue date: 2014-01-23 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / We propose in this work a software architecture for robotic boats intended to act in diverse aquatic environments, fully autonomously, performing telemetry to a base station and getting this mission to be accomplished. This proposal aims to apply within the project N-Boat Lab NatalNet DCA, which aims to empower a sailboat navigating autonomously. The constituent components of this architecture are the memory modules, strategy, communication, sensing, actuation, energy, security and surveillance, making these systems the boat and base station. To validate the simulator was developed in C language and implemented using the graphics API OpenGL resources, whose main results were obtained in the implementation of memory, performance and strategy modules, more specifically data sharing, control of sails and rudder and planning short routes based on an algorithm for navigation, respectively. The experimental results, shown in this study indicate the feasibility of the actual use of the software architecture developed and their application in the area of autonomous mobile robotics / Propomos neste trabalho uma arquitetura de software para barcos rob?ticos destinados a atuarem em ambientes aqu?ticos diversos, de forma totalmente aut?noma, realizando telemetria com uma esta??o-base e desta recebendo miss?es a serem realizadas. Tal proposta visa aplicar-se dentro do projeto N-Boat do laborat?rio Natalnet-DCA, que tem como objetivo principal capacitar um veleiro a navegar autonomamente. Os componentes constituintes dessa arquitetura s?o os m?dulos de mem?ria, estrat?gia, comunica??o, sensoriamento, atua??o, energia, seguran?a e supervis?o, formando estes os sistemas do barco e da esta??o-base. Para sua valida??o foi desenvolvido um simulador implementado na linguagem C e utilizando recursos da API gr?fica OpenGL, cujos principais resultados foram obtidos na implementa??o dos m?dulos de mem?ria, de atua??o e de estrat?gia, mais especificamente no compartilhamento de dados, no controle das velas e do leme e no planejamento de rotas curtas baseado em um algoritmo de navega??o, respectivamente. Os resultados dos experimentos realizados, mostrados no presente trabalho, indicam a viabilidade da utiliza??o real da arquitetura de software desenvolvida e sua aplica??o na ?rea da rob?tica m?vel aut?noma

Orientador: Joao Mauricio Rosario / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-08-10T02:27:46Z (GMT). No. of bitstreams: 1 Melo_LeonimerFlaviode_D.pdf: 6867936 bytes, checksum: 344026f77cc24610774519b704ddccfa (MD5) Previous issue date: 2007 / Resumo: Este trabalho apresenta a proposta de implementação de um ambiente virtual de simulação para projeto e concepção de sistema de supervisão e controle para robôs móveis, que sejam capazes de operar e de se adaptar a diferentes ambientes e condições. Este sistema virtual tem como finalidade facilitar o desenvolvimento de protótipos de sistemas embarcados, enfatizando a implementação de ferramentas que permitam a simulação das condições cinemáticas, dinâmicas e de controle, com monitoração em tempo real de todos pontos lmportantes do sistema. Para isso, é proposta uma arquitetura aberta de controle, integrando as duas principais técnicas de implementação de controle robótico a nível de hardware: sistemas microprocessadores e dispositivos de hardware reconfiguráveis. O sistema simulador implementado é composto de um módulo gerador de trajetória, de um módulo simulador cinemático e dinâmico e de um módulo de análise de resultados e erros. O módulo gerador de trajetória tem a finalidade de, uma vez conhecendo-se o ambiente em que o robô irá atuar, com seus obstáculos e particularidades, gerar uma trajetória cartesiána ótima, respeitando os limites e características do robô móvel. Todos os resultados cinemáticos e dinâmicos colhidos durante a simulação podem ser avaliados e visualizados em formatos de gráficos e tabelas, no módulo de análise de resultados, permitindo que seja feito um aperfeiçoamento no sistema, no sentido de minimizar os erros com a otimização dos ajustes necessários. Para a implementação do controlador no sistema embarcado utiliza-se a prototipagem rápida, que é a tecnologia que permite, em conjunto com o ambiente virtual de simulação, o desenvolvimento de um projeto de um controlador para robôs móveis. A validação e testes foram realizados com modelos de robôs móveis não holonômicos de transmissão diferencial / Abstract: This work presents the proposal of virtual environment implementation for project simulation and conception of supervision aild control systems for mobile robots, that are capable to operate and adapting in different environments and conditions. This virtual system has as purpose to facilitate the development of embedded architecture systems, emphasizing the implementation of tools that alIow the simulation of the kinematic conditions, dynamic and control, with real time monitoring of alI important system points. For this, an open control architecture is proposal, integrating the two main techniques of robotic control implementation in the hardware level: systems microprocessors and reconfigurable hardware devices. The implemented simulator system is composed of a trajectory generating module, a kinematic and dynamic simulator module and of a analysis module of results and errors. The kinematic and dynamic simulator module makes alI simulation of the mobile robot folIowing the pre-determined trajectory of the trajectory generator. All the kinematic and dynamic results shown during the simulation can be evaluated and visualized in graphs and tables formats, in the results analysis module, allowing an improvement in the system, minimizing the errors with the necessary adjustments optimization. For controlIer implementation in the embedded system, it uses the rapid prototyping, that is the technology that allows, in set with the virtual simulation environment, the development of a controlIer project for mobile robots. The validation and tests had been accomplish with nonholonomics mobile robots models with diferencial transmission / Doutorado / Mecanica dos Sólidos e Projeto Mecanico / Doutor em Engenharia Mecânica

No description available.