Orientador: Paulo Roberto Gardel Kurka / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica / Made available in DSpace on 2018-08-26T21:38:28Z (GMT). No. of bitstreams: 1 Araujo_DarlaCarolinedaSilva_M.pdf: 5678583 bytes, checksum: a6ed9886369705a8853f15d431565a3d (MD5) Previous issue date: 2015 / Resumo: O presente trabalho descreve um método de odometria visual empregando a técnica de fluxo óptico, para estimar o movimento de um robô móvel, através de imagens digitais capturadas de duas câmeras estereoscópicas nele fixadas. Busca-se assim a construção de um mapa para a localização do Robô. Esta proposta, além de alternativa ao cálculo autônomo de movimento realizado por outros tipos de sensores como GPS, laser, sonares, utiliza uma técnica de processamento óptico de grande eficiência computacional. Foi construído um ambiente 3D para simulação do movimento do robô e captura das imagens necessárias para estimar sua trajetória e verificar a acurácia da técnica proposta. Utiliza-se a técnica de fluxo óptico de Lucas Kanade na identificação de características em imagens. Os resultados obtidos neste trabalho são de grande importância para os estudos de navegação robótica / Abstract: This work describes a method of visual odometry using the optical flow technique to estimate the motion of a mobile robot, through digital images captured from two stereoscopic cameras fixed on it, in order to obtain a map of location of the robot. This proposal is an alternative to the autonomous motion calculation performed by other types of sensors such as GPS, laser, sonar, and uses an optical processing technique of high computational efficiency. To check the accuracy of the technique it was necessary to build a 3D environment to simulate the robot performing a trajectory and capture the necessary images to estimate the trajectory. The optical flow technique of Lucas Kanade was used for identifying features in the images. The results of this work are of great importance for future robotic navigation studies / Mestrado / Mecanica dos Sólidos e Projeto Mecanico / Mestra em Engenharia Mecânica

Orientador: Paulo Roberto Gardel Kurka / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica / Made available in DSpace on 2018-08-28T12:48:00Z (GMT). No. of bitstreams: 1 DelgadoVargas_JaimeArmando_D.pdf: 6984853 bytes, checksum: 4647b847de6d3abb110923a021a6f376 (MD5) Previous issue date: 2015 / Resumo: A localização de robôs móveis é foco de estudo em diferentes grupos de pesquisa ao redor do mundo. Robôs móveis são equipados com diferentes sensores, utilizando uma variedade de métodos de localização para as tarefas de exploração de ambientes desconhecidos ou para seguir uma trajetória predefinida. Este trabalho apresenta a investigação e implementação de um método robusto e eficiente da estimativa de movimento utilizando visão computacional, conhecido como odometria visual. Também, é estudada a fusão de estimativas de movimento de diferentes sensores através da técnica do filtro de Kalman. Neste trabalho utilizam-se câmeras estereoscópicas com lentes fixas de 9mm e simulações do movimento de uma câmera no ambiente 3D-Max. A validação experimental dos algoritmos é feita em uma plataforma robótica tipo Seekur Jr equipada com Lasers, GPS, encoders e câmeras estereoscópicas. O movimento do robô é estimado pelos diferentes sensores gerando redundância de localização Os algoritmos de odometria visual são validados em ambientes de interiores e exteriores. A velocidade de processamento dos métodos é comparada usando em diferentes processadores de tipo CPU e GPU, indicando a possibilidade um sistema de realização de odometria visual em tempo real / Abstract: The localization of mobile robots problem is addressed to a number of research groups around the world. Mobile robots are equipped with different sensors, using a variety of methods of localization in the exploration of unknown environments or following a pre-defined trajectory. The present work investigates and implements a robust method of estimation of movement using computer vision, known as visual odometry. The work investigates also the results of fusion of the estimates of movement obtained from different sensors, using the Kalman filter technique. Visual odometry uses stereoscopic vision techniques with real time computing in graphic processing units (GPU). Stereoscopic cameras with fixed 9mm lens and movement simulations in the 3d-Max computer environment are used in the present work. Experimental validation of the visual odometry algorithms is made in a Sekur Jr mobile robot platform, equipped with lasers, GPS, wheel encoders and stereoscopic cameras. Movements of the robot are estimated from the different sensors, yielding redundant localization information. The information from such sensors are fused together through the Kalman filter. Visual odometry algorithms are tested in indoors and outdoors navigation experiments. Processing speed of the methods is compared using different processing units: CPU and GPU, indicating the possibility of performing real time visual odometry / Doutorado / Mecanica dos Sólidos e Projeto Mecanico / Doutor em Engenharia Mecânica

Orientadores: João Maurício Rosário, Humberto Ferasoli Filho / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecânica / Made available in DSpace on 2018-08-19T15:08:00Z (GMT). No. of bitstreams: 1 Alves_SilasFrancodosReis_M.pdf: 3766365 bytes, checksum: dbbe1298b44cd06d13a9d2e56dfe873e (MD5) Previous issue date: 2011 / Resumo: A navegação e a colaboração são aspectos importantes da robótica móvel. A navegação confere aos robôs móveis as habilidades básicas de interação com o ambiente, os obstáculos e agentes nele situado. Já a colaboração permite que os robôs coordenem sua navegação e interação com o ambiente de forma que os permita realizar tarefas complexas de forma rápida e eficiente. Neste trabalho de pesquisa foi desenvolvida uma plataforma de software que oferece suporte a algumas técnicas tradicionais de navegação e colaboração de robôs móveis. Com esta plataforma, é possível programar diferentes robôs com os mesmos componentes de software, o que reduz o tempo de desenvolvimento do aplicativo ao incentivar o reuso de software. Além disso, as técnicas de navegação e colaboração fornecidas pela plataforma amenizam o esforço em desenvolver o software de controle para robôs móveis colaborativos, pois a plataforma permite que o usuário concentre seus esforços na solução dos problemas pertinentes a aplicação do robô, uma vez que as técnicas de navegação e colaboração são fornecidas pela plataforma / Abstract: The navigation and collaboration are important aspects of mobile robotics. The navigation provides to mobile robots the basic skills of interaction with the environment, and the obstacles and agents located therein. The collaboration allows the robots to coordinate their navigation and interaction with the environment in a way that enables them to per-form complex tasks quickly and efficiently. This research project developed a software plat-form that supports some traditional navigation techniques and collaboration of mobile robots. With this platform, different robots can be programmed with the same software components, reducing the application's development time by encourage software reuse. Furthermore, the techniques of navigation and collaboration provided by the platform alleviate the effort to develop the control software for collaborative mobile robots, because the plat-form allows the user to focus their efforts on solving the problems relevant to the robot's application, since the navigation techniques and collaboration are provided by the platform / Mestrado / Mecanica dos Sólidos e Projeto Mecanico / Mestre em Engenharia Mecânica

In this thesis, a cognitive neural predictive controller system has been designed to guide a nonholonomic wheeled mobile robot during continuous and non-continuous trajectory tracking and to navigate through static obstacles with collision-free and minimum tracking error. The structure of the controller consists of two layers; the first layer is a neural network system that controls the mobile robot actuators in order to track a desired path. The second layer of the controller is cognitive layer that collects information from the environment and plans the optimal path. In addition to this, it detects if there is any obstacle in the path so it can be avoided by re-planning the trajectory using particle swarm optimisation (PSO) technique. Two neural networks models are used: the first model is modified Elman recurrent neural network model that describes the kinematic and dynamic model of the mobile robot and it is trained off-line and on-line stages to guarantee that the outputs of the model will accurately represent the actual outputs of the mobile robot system. The trained neural model acts as the position and orientation identifier. The second model is feedforward multi-layer perceptron neural network that describes a feedforward neural controller and it is trained off-line and its weights are adapted on-line to find the reference torques, which controls the steady-state outputs of the mobile robot system. The feedback neural controller is based on the posture neural identifier and quadratic performance index predictive optimisation algorithm for N step-ahead prediction in order to find the optimal torque action in the transient to stabilise the tracking error of the mobile robot system when the trajectory of the robot is drifted from the desired path during transient state. Three controller methodologies were developed: the first is the feedback neural controller; the second is the nonlinear PID neural feedback controller and the third is nonlinear inverse dynamic neural feedback controller, based on the back-stepping method and Lyapunov criterion. The main advantages of the presented approaches are to plan an optimal path for itself avoiding obstructions by using intelligent (PSO) technique as well as the analytically derived control law, which has significantly high computational accuracy with predictive optimisation technique to obtain the optimal torques control action and lead to minimum tracking error of the mobile robot for different types of trajectories. The proposed control algorithm has been applied to monitor a nonholonomic wheeled mobile robot, has demonstrated the capability of tracking different trajectories with continuous gradients (lemniscates and circular) or non-continuous gradients (square) with bounded external disturbances and static obstacles. Simulations results and experimental work showed the effectiveness of the proposed cognitive neural predictive control algorithm; this is demonstrated by the minimised tracking error to less than (1 cm) and obtained smoothness of the torque control signal less than maximum torque (0.236 N.m), especially when external disturbances are applied and navigating through static obstacles. Results show that the five steps-ahead prediction algorithm has better performance compared to one step-ahead for all the control methodologies because of a more complex control structure and taking into account future values of the desired one, not only the current value, as with one step-ahead method. The mean-square error method is used for each component of the state error vector to compare between each of the performance control methodologies in order to give better control results.

Domestic robots developed to support human beings by performing daily tasks such as cleaning should also be able to help in emergencies by finding, analysing, and assisting persons in need of first aid. Here such a robot capable of performing some useful task related to first aid is referred to as a First Aid Mobile Robot (FAMR). One challenge which to the author's knowledge has not been solved is how such a FAMR can find a fallen person's pose within an environment, recognising locations of points of interest for first aid such as the mouth, nose, chin, chest and hands on a map. To overcome the challenge, a new approach is introduced based on leveraging a robot's capabilities (multiple sensors and mobility), called AHBL. AHBL comprises four steps: Anomaly detection, Human detection, Body part recognition, and Localisation on a map. It was broken down into four steps for modularity (e.g., a different way of detecting anomalies can be slipped in without changing the other modules) and because it was not clear which step is hardest to implement. As a result of evaluating AHBL, a FAMR developed for this work was able to find the pose of a fallen person (a mannequin) in a known environment with an average success rate of 83%, and an average localisation discrepancy of 1.47cm between estimated body part locations and ground truth. The presented approach can be adapted for use in other robots and contexts, and can act as a starting point toward designing systems for autonomous robotic first aid.

Norteado pela necessidade de evolução do mercado agrícola, o desenvolvimento da agricultura de precisão atinge o nível de gerenciamento escalar de uma única planta, utilizando robôs agrícolas autônomos, os quais deverão trabalhar por longos períodos, ser ambientalmente corretos, atender às necessidades dos clientes, e ainda, com qualidade, confiabilidade e segurança. Este trabalho tem como objetivos pesquisar, discutir e apresentar os requisitos da qualidade em robôs agrícolas, focando a satisfação do usuário final. Tais objetivos serão atingidos por meio do detalhamento da aplicação de ferramentas utilizadas durante o desenvolvimento do produto, e da avaliação de um robô existente, quanto ao atendimento dos requisitos definidos pelo usuário final. O estudo conclui que, a melhor metodologia a ser utilizada para satisfazer as necessidades do usuário final de um robô agrícola, é aplicação da ferramenta QFD durante o desenvolvimento do projeto do produto. Quanto à avaliação do robô existente, a conclusão foi de que, por se tratar de um robô desenvolvido com finalidade experimental para execução de pequenas atividades e com recursos financeiros limitados, sua nota média obtida pode ser considerada apropriada. / Guided by agricultural market evolution demand, precision agriculture development reaches scalar management level of one only plant, through the usage of autonomous agricultural robots, which must work in long shifts, environmentally friendly, meet customer requirements, all this with quality, reliability and safety. This work aims the research, discussion and presentation of quality requirements of agricultural robots, focusing on the satisfaction of final user. These objectives are reached through the tools application detailing used during the product development and evaluation of an existent robot on the requirements defined by the final user. The study concludes that the best methodology to be used to satisfy agricultural robots final user needs is through the application of QFD tool during the product design. As for the evaluation on the existent robot, the conclusion was that, as a robot developed for an experimental execution of small activities and with limited budget, his average score may be considered appropriated.

Nesta dissertação é realizado um estudo comparativo entre controladores robustos projetados para sistemas lineares em espaço de estado sujeitos a incertezas paramétricas. O objetivo é resolver problemas de acompanhamento de trajetória de robôs. O estudo é realizado em um robô móvel com tração diferencial e em um quadricóptero. Para tal, é aplicado um Regulador Linear Quadrático Robusto no qual engloba em uma estrutura unificada todos os parâmetros de incerteza de entrada e saída de maneira recursiva, útil em aplicações em tempo real. A fim de demonstrar a eficiência do Regulador Robusto, resultados de simulações e de experimentos são empregados comparando-o com controle Η∞ não linear via teoria dos jogos e com um controle Proporcional-Derivativo mais torque calculado. / This work provides a comparative study between robust controllers for linear statespace systems subject to parametric uncertainties to solve trajectory tracking problems. The study is developed in a mobile robot with differential traction and in a quadricopter. A Robust Linear Quadratic Regulator is applied, which encompasses in a unified framework all input and output uncertain parameters, useful in online applications. In order to show the effectiveness of the robust regulator, simulations and experiments results allow the comparison with nonlinear Η∞ control via game theory and with a Proportional- Derivative control plus computed torque.

Este trabalho apresenta uma arquitetura de controle de movimento entre duas posturas distintas para um robô móvel sob rodas com acionamento diferencial em um ambiente estruturado e livre de obstáculos. O conceito clássico de eficiência foi utilizado para a definição das estratégias de controle: um robô se movimenta de forma eficiente quando realiza a tarefa determinada no menor tempo e utilizando menor quantidade energética. A arquitetura proposta é um recorte do modelo de Controle Hierárquico Aninhado (NHC), composto por três níveis de abstração: (i) Planejamento de Caminho, (ii) Planejamento de Trajetória e (iii) Rastreamento de Trajetória. O Planejamento de Caminho proposto suaviza uma geodésica Dubins - o caminho mais eficiente - por uma Spline Grampeada para que este caminho seja definido por uma curva duplamente diferenciável. Uma transformação do espaço de configuração do robô é realizada. O Planejamento de Trajetória é um problema de otimização convexa na forma de Programação Cônica de Segunda Ordem, cujo objetivo é uma função ponderada entre tempo e energia. Como o tempo de percurso e a energia total consumida pelo robô possui uma relação hiperbólica, um algoritmo de sintonia do coeficiente de ponderação entre estas grandezas é proposta. Por fim, um Rastreador de Trajetória de dupla malha baseado em linearização entrada-saída e controle PID é proposto, e obteve resultados satisfatórios no rastreamento do caminho pelo robô. / This work presents a motion control architecture between two different positions for a differential driven wheeled mobile robot in a obstacles free structured environment. The classic concept of efficiency was used to define the control strategies: a robot moves efficiently when it accomplishes the determined task in the shortest time and using less amount of energy. The proposed architecture is a clipping of the Nested Hierarchical Controller (NHC) model, composed of three levels of abstraction: (i) Path Planning, (ii) Trajectory Planning and (iii) Trajectory Tracking. The proposed Path Planning smoothes a geodesic Dubins - the most efficient path - by a Clamped Spline as this path is defined by a twice differentiable curve. A transformation of the robot configuration space is performed. The Trajectory Planning is a convex optimization problem in the form of Second Order Cone Programming, whose objective is a weighted function between time and energy. As the travel time and the total energy consumed by the robot has a hyperbolic relation, a tuning algorithm to the weighting is proposed. Finnaly, a dual-loop Trajectory Tracker based on input-output feedback linearization and PID control is proposed, which obtained satisfactory results in tracking the path by the robot.

Les robots industriels, bien connus pour être des systèmes de fabrication flexibles et agiles, atteignent leurs limites lorsqu'il s'agit d'effectuer des tâches sur des pièces de grande taille (par exemple: les pièces longues et minces de l'industrie aéronautique). Pour ce type des tâches, les solutions existantes sont à leurs limites: les bras manipulateurs à base fixe souffrent d'un espace de travail trop limité; les bras manipulateurs montés sur véhicule ne sont pas assez précis; les machines-outils conventionnelles doivent être conçus à méga-échelle (plusieurs dizaines de mètres). Dans la cadre de cette thèse de doctorat, nous avons proposé des solutions robotiques innovantes qui combinent la capacité de marcher (ou de grimper) sur la pièce (ou sur le montage d'usinage) avec la capacité d'usiner. De l'analyse de la topologie et de la mobilité à la modélisation géométrique et cinématique, ainsi que la proposition d'algorithmes de contrôle innovants, des robots ont été proposés et étudiés pour la réalisation des tâches d'usinage ainsi que des tâches de locomotion. Un prototype a été construit qui témoigne de la pertinence de ce concept innovant. Il repose sur une architecture parallèle à actionnement redondant (8 moteurs pour 6 degrés de liberté) et combine moteurs, freins, dispositifs de bridage et de nombreux capteurs de position. Le prototype peut se fixer sur le montage d'usinage, réaliser ses tâches de fabrication, puis modifier sa configuration pour devenir un robot marcheur capable d'atteindre la zone de travail suivante. / Industrial robots, well known as flexible and agile manufacturing systems, reach their limits when dealing with very large workpieces (e.g.: very long and slender parts found in aeronautics industry). For such tasks, existing solutions are at their limits: stationary manipulator arms suffer from a too limited workspace; manipulators mounted on a vehicle are not accurate enough; classical machine-tools must be designed at mega-scale (several tens of meters). This thesis work aims at offering an innovative robotic solution that combines the ability to walk (or climb) on the workpiece (or on the tooling that supports the workpieces) together with manufacturing ability. From the topology and mobility analysis to the geometrics and kinematics modeling, as well as innovative control algorithms proposition, the proposed mobile manufacturing robots have been studied for achieving both machining and locomotion tasks. A prototype has been built to show the concept effectiveness . It is based on a parallel mechanism with actuation redundancy (8 motors for 6 degrees-of-freedom), combining motors, brakes, clamping devices and numerous position sensors. The robot can clamp itself on the manufacturing tooling, and then change its configuration to become a walking robot able to reach the next working area.

Every year, one out of three adults over the age of 65 falls, and about 30% of the falls result in moderate to severe injuries. The high rate of fall-related hospitalizations and the fact that falls are a major source of morbidity and mortality in older adults have motivated extensive interdisciplinary clinical and engineering research with a focus on fall prevention. This research is aimed at developing a medical Cyber Physical System (CPS) composed of a human supervised mobile robot and ambient intelligence sensors to provide continuous evaluation of environmental risks in the home. As a preventive measure to avoid falls, we propose use of mobile robots to detect possible fall risks inside a house. As a step-up to that, we also define a control framework for intelligent, networked mobile robots to semi-autonomously perform assistive and preventive tasks. This framework is integrated in a smart home that provides monitoring and control capabilities of environmental conditions such as objects blocking pathways or uneven surfaces. The main outcome of this work is the realization of this system at Worcester Polytechnic Institute's (WPI) @Home testbed.