The emergence of cloud computing has transformed the potential of robotics by enabling multi-robotic teams to fulfil complex tasks in the cloud. This paradigm is known as “cloud robotics” and relieves robots from hardware and software limitations, as large amounts of available resources and parallel computing capabilities are available in the cloud. The introduction of cloud-enabled robots alleviates the need for computationally intensive robots to be built, as many, if not all, of the CPU-intensive tasks can be offloaded into the cloud, resulting in multi-robots that require much less power, energy consumption and on-board processing units. While the benefits of cloud robotics are clearly evident and have resulted in an increase in interest among the scientific community, one of the biggest challenges of cloud robotics is the inherent communication challenges brought about by disconnections between the multi-robotic system and the cloud. The communication delays brought about by the cloud disconnection results in robots not being able to receive and transmit data to the physical cloud. The unavailability of these robotic services in certain instances could prove fatal in a heterogeneous environment that requires multi-robotic teams to assist with the saving of human lives. This niche area is relatively unexplored in the literature. This work serves to assist with the challenge of disconnection in cloud robotics by proposing a survivable cloud multi-robotics (SCMR) framework for heterogeneous environments. The SCMR framework leverages the combination of a virtual ad hoc network formed by the robot-to-robot communication and a physical cloud infrastructure formed by the robot-to-cloud communications. The Quality of Service (QoS) on the SCMR framework is tested and validated by determining the optimal energy utilization and Time of Response (ToR) on drivability analysis with and without cloud connection. The experimental results demonstrate that the proposed framework is feasible for current multi-robotic applications and shows the survivability aspect of the framework in instances of cloud disconnection. / School of Computing / M.Sc. (Computer Science)

Agência Nacional do Petróleo, Gás Natural e Biocombustíveis (ANP); FINEP; Ministério da Ciência e Tecnologia (MCT) / Este trabalho consiste no desenvolvimento de um sistema estabilizador da adesão de um robô escalador com rodas magnéticas. O projeto deste robô surge da necessidade em automatizar o processo de inspeção de tanques de armazenamento de derivados de petróleo, o qual e atualmente realizado de modo manual. O robô vem sendo desenvolvido no Laboratório de Automação e Sistemas de Controle Avençado (LASCA) da Universidade Tecnológica Federal do Paraná (UTFPR). Primeiramente foi realizada uma análise teórica completa do protótipo, englobando um estudo da estrutura do robô, seus requisitos e as análises de cinemática e dinâmica. Realizou-se então um estudo das rodas magnéticas do robô e das características do campo magnético enquanto ocorre descolamento da roda em superfícies ferromagnéticas. Os dados do campo magnético são adquiridos por meio do magnetômetro presente na unidade de navegação inercial do robô. Implementou-se então uma rede neural artificial do tipo Perceptron Multi-Camadas com o intuito de interpretar os dados do campo magnético e estimar a forca de adesão entre o robô e a superfície. Por fim a quantificação da forca de adesão e utilizada para implementar um sistema de controle de adesão para o robô escalador. / This work consists in the design of an adhesion stabilization system of a climbing robot with magnetic wheels. The robot’s design comes from the need to automatize the inspection process of industrial storage tanks for petroleum products, which is currently performed manually. The robot is being developed in the Laboratory of Automation and Advanced Control Systems (LASCA) of the Federal Technological University of Paraná (UTFPR). First, a complete a theoretical analysis of the prototype was carried out including a study of the robot’s structure, its requirements and the kinematics and dynamics analyses. Then, a study of the robot’s magnetic wheels and the characteristics of the magnetic field in the occurancy of detachment between the magnetic wheel and the ferro-magnetic surfaces was carried out. The magnetic field data is acquired through the magnetometer of the inertial measurement unit sensor of the robot. Then a multilayer perceptron artificial neural network was implemented in order to interpret the magnetic field data and estimate the adhesion force between robot and surface. Finally the adhesion force quantification is used to implement an adhesion control system for the robot.

O presente trabalho tem por objetivo realizar um estudo sobre a arquitetura Baars-Franklin, a qual define um modelo de consciência artificial, e aplicá-la a uma tarefa da navegação em um robô móvel autônomo. A inserção de robôs móveis em ambientes dinâmicos acarreta uma alta complexidade nas tarefas de navegação, visto que para lidar com a constante mudança no ambi-ente, é essencial que o robô seja capaz de se adaptar a este dinamismo. A abordagem utilizada neste trabalho é de realizar a execução destas tarefas de uma maneira mais próxima da utilizada por seres humanos quando reagem às mesmas condições, por meio de um modelo de cons-ciência computacional. A arquitetura LIDA (Learning Intelligent Distribution Agent) é uma proposta de sistema cognitivo que procura modelar alguns dos aspectos cognitivos humanos, desde as percepções sensoriais (aspectos cognitivos de baixo nível) até o processo de tomada de decisão, os mecanismos de atenção e a memória episódica (considerados aspectos cogniti-vos de alto nível). Neste trabalho é utilizada uma implementação computacional da arquitetura LIDA, sendo apresentada a realização de um estudo de caso que visa avaliar a aplicabilidade e o desempenho de uma proposta de navegação cognitiva a robô móvel em ambientes dinâmicos e desconhecidos. São realizados experimento utilizando tanto um ambiente virtual (simulação) quanto um ambiente e robô reais. Este estudo concluiu que pode se obter benefícios na utili-zação de modelos cognitivos conscientes na tarefa de navegação de robôs móveis, apontando pontos positivos e negativos desta abordagem. / This work presents a study about a the Baars-Franklin architecture, which defines a model of computational consciousness, and use it in a mobile robot navigation task. The insertion of mobile robots in dynamic environments carries a high complexity in navigation tasks, in order to deal with the constant environment changes, it is essential that the robot can adapt to this dynamism. The approach utilized in this work is to make the execution of these tasks closer to how human beings react to the same conditions by means of a model of computational consci-ousness. The LIDA architecture (Learning Intelligent Distribution Agent) is a cognitive system that seeks tomodel some of the human cognitive aspects, from low-level perceptions to decision making, as well as attention mechanism and episodic memory. In the present work, a computa-tional implementation of the LIDA architecture was evaluated by means of a case study, aiming to evaluate the capabilities of a cognitive approach to navigation of a mobile robot in dynamic and unknown environments, using experiments both with virtual environments (simulation) and a real robot in a realistic environment. This study concluded that it is possible to obtain benefits by using conscious cognitive models in mobile robot navigation tasks, presenting the positive and negative aspects of this approach.

O presente trabalho tem por objetivo realizar um estudo sobre a arquitetura Baars-Franklin, a qual define um modelo de consciência artificial, e aplicá-la a uma tarefa da navegação em um robô móvel autônomo. A inserção de robôs móveis em ambientes dinâmicos acarreta uma alta complexidade nas tarefas de navegação, visto que para lidar com a constante mudança no ambi-ente, é essencial que o robô seja capaz de se adaptar a este dinamismo. A abordagem utilizada neste trabalho é de realizar a execução destas tarefas de uma maneira mais próxima da utilizada por seres humanos quando reagem às mesmas condições, por meio de um modelo de cons-ciência computacional. A arquitetura LIDA (Learning Intelligent Distribution Agent) é uma proposta de sistema cognitivo que procura modelar alguns dos aspectos cognitivos humanos, desde as percepções sensoriais (aspectos cognitivos de baixo nível) até o processo de tomada de decisão, os mecanismos de atenção e a memória episódica (considerados aspectos cogniti-vos de alto nível). Neste trabalho é utilizada uma implementação computacional da arquitetura LIDA, sendo apresentada a realização de um estudo de caso que visa avaliar a aplicabilidade e o desempenho de uma proposta de navegação cognitiva a robô móvel em ambientes dinâmicos e desconhecidos. São realizados experimento utilizando tanto um ambiente virtual (simulação) quanto um ambiente e robô reais. Este estudo concluiu que pode se obter benefícios na utili-zação de modelos cognitivos conscientes na tarefa de navegação de robôs móveis, apontando pontos positivos e negativos desta abordagem. / This work presents a study about a the Baars-Franklin architecture, which defines a model of computational consciousness, and use it in a mobile robot navigation task. The insertion of mobile robots in dynamic environments carries a high complexity in navigation tasks, in order to deal with the constant environment changes, it is essential that the robot can adapt to this dynamism. The approach utilized in this work is to make the execution of these tasks closer to how human beings react to the same conditions by means of a model of computational consci-ousness. The LIDA architecture (Learning Intelligent Distribution Agent) is a cognitive system that seeks tomodel some of the human cognitive aspects, from low-level perceptions to decision making, as well as attention mechanism and episodic memory. In the present work, a computa-tional implementation of the LIDA architecture was evaluated by means of a case study, aiming to evaluate the capabilities of a cognitive approach to navigation of a mobile robot in dynamic and unknown environments, using experiments both with virtual environments (simulation) and a real robot in a realistic environment. This study concluded that it is possible to obtain benefits by using conscious cognitive models in mobile robot navigation tasks, presenting the positive and negative aspects of this approach.

Orientador: João Maurício Rosário, Didier Dumur / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia / Made available in DSpace on 2018-08-20T08:06:43Z (GMT). No. of bitstreams: 1 LaraMolina_FabianAndres_D.pdf: 6567422 bytes, checksum: 5d5531b99af8de161a3f8f390bcac8cf (MD5) Previous issue date: 2012 / Resumo: Este trabalho visa o desenvolvimento, síntese e aplicação de um controlador baseado em controle preditivo generalizado para rastreamento de trajetórias de robôs paralelos. A finalidade é melhorar o desempenho dinâmico do robô paralelo através do desenvolvimento de controladores avançados que considerem características do robô tais como não-linearidades da dinâmica, incertezas paramétricas e distúrbios externos. Inicialmente é revisada a formulação do modelo dinâmico do robô paralelo que envolve: modelo geométrico, cinemático e dinâmico. À continuação é realizado o projeto dos controladores de posição no espaço das juntas: controladores de torque computado com PID na forma RST, controlador preditivo generalizado e robustificação com os parâmetros de Youla. A seguir, a dinâmica do robô paralelo e os controladores desenvolvidos são simulados no ambiente MATLAB/Simulink. Finalmente, é realizada a implementação experimental e validação dos controladores no robô Orthoglide no laboratório de robótica do IRCCyN, École Centrale de Nantes. O controlador preditivo generalizado robustificado melhora a resposta dinâmica em relação ao controlador de torque computado que tem sido amplamente utilizado nesta classe de robôs. Os resultados obtidos através da implementação experimental da lei de controle preditiva robustificada no robô Orthoglide e testes experimentais indicam que o desempenho dinâmico do robô é melhorado em termos das seguintes caraterísticas: precisão no rastreamento de trajetórias típicas para usinagem no espaço de trabalho, estas trajetórias são executadas com diferentes acelerações máximas; robustez a variação dos parâmetros do robô tais como mudança da carga na plataforma móvel, obtendo desta forma uma melhor regulação; e finalmente, atenuação do efeito do ruído de medição nos sensores no sinal de controle dos atuadores durante a execução de um movimento. Os resultados experimentais mostraram que o controlador preditivo generalizado robustificado aplicado no robô Orthoglide é eficiente frente as incertezas paramétricas e restrições no domínio do tempo, melhorando assim o desempenho dinâmico do robô com um custo computacional equivalente ao controle de torque computado / Abstract: This thesis addresses the development and application of a controller based on generalized predictive control to track a desired trajectory using parallel robots. The main purpose of this thesis is to improve the dynamical behavior with an advanced controller which considers the proper characteristics of the parallel robot such as no linear dynamics, parameters uncertainties and external disturbances. This work is divided into four parts. A first part formulates the complete dynamical model of the parallel robot, considering the geometrical, kinematic and dynamic modelling. Then, the joint space control is performed for the parallel robot using the computed torque controller in the RST form and the robustified generalized predictive control via Youla parameterization. A third part shows the simulation of the dynamic of the robot with the controllers in MATLAB/Simulink to establish a comparison between controllers. Finally, the controllers are implemented in the prototype and some experiments are performed on the Orthoglide robot at the laboratory of robotics, IRCCyN, Ecole Centrale de Nantes to assess the dynamic performance of the controllers. The experimental results show that the robustification of the generalized predictive control against parametric uncertainties including time domain constraints improves the dynamical behavior of the parallel robots. The experimental results shows that the the robustified generalized predictive control enhances the dynamic performance of is in terms of: tracking accuracy of trajectories used in milling process; robustness to parameters variation such as payload changing (on the end effector), therefore, a better regulation is obtained; and finally, attenuation of noise due to sensor measurement in control. Additionally, the robustification of the generalized predictive control applied on the Orthoglide robot improves the dynamical behavior compared to controllers widely used in parallel robots such as computed torque control with and equivalent computational cost / Doutorado / Mecanica dos Sólidos e Projeto Mecanico / Doutor em Engenharia Mecânica

This dissertation investigates high-level decision making for agents that are both goal and utility driven. We develop a partially observable Markov decision process (POMDP) planner which is an extension of an agent programming language called DTGolog, itself an extension of the Golog language. Golog is based on a logic for reasoning about action—the situation calculus. A POMDP planner on its own cannot cope well with dynamically changing environments and complicated goals. This is exactly a strength of the belief-desire-intention (BDI) model: BDI theory has been developed to design agents that can select goals intelligently, dynamically abandon and adopt new goals, and yet commit to intentions for achieving goals. The contribution of this research is twofold: (1) developing a relational POMDP planner for cognitive robotics, (2) specifying a preliminary BDI architecture that can deal with stochasticity in action and perception, by employing the planner. / Computing / M. Sc. (Computer Science)

Robotics has been the subject of academic study from as early as 1948. For much of this time, study has focused on very specific applications in very well controlled environments. For example, the first commercial robots (1961) were introduced in order to improve the efficiency of production lines. The tasks undertaken by these robots were simple, and all that was required of a control algorithm was speed, repetitiveness and reliability in these environments. Now however, robots are being used to move around autonomously in increasingly unpredictable environments, and the need for robotic control algorithms that can successfully react to such conditions is ever increasing. In addition to this there is an ever-increasing array of robots available, the control algorithms for which are often incompatible. This can result in extensive redesign and large sections of code being re-written for use on different architectures. The thesis presented here is that a new generic approach can be created that provides robust high quality smooth paths and time-optimal path tracking to substantially increase applicability and efficiency of autonomous motion plans. The control system developed to support this thesis is capable of producing high quality smooth paths, and following these paths to a high level of accuracy in a robust and near time-optimal manner. The system can control a variety of robots in environments that contain 2D obstacles of various shapes and sizes. The system is also resilient to sensor error, spatial drift, and wheel-slip. In achieving the above, this system provides previously unavailable functionality by generically creating and tracking high quality paths so that only minor and clear adjustments are required between different robots and also be being capable of operating in environments that contain high levels of perturbation. The system is comprised of five separate novel component algorithms in order to cater for five different motion challenges facing modern robots. Each algorithm provides guaranteed functionality that has previously been unavailable in respect to its challenges. The challenges are: high quality smooth movement to reach n-dimensional goals in regions without obstacles, the navigation of 2D obstacles with guaranteed completeness, high quality smooth movement for ground robots carrying out 2D obstacle navigation, near time-optimal path tracking, and finally, effective wheel-slip detection and compensation. In meeting these challenges the algorithms have tackled adherence to non-holonomic constraints, applicability to a wide range of robots and tasks, fast real-time creation of paths and controls, sensor error compensation, and compensation for perturbation. This thesis presents each of the above algorithms individually. It is shown that existing methods are unable to produce the results provided by this thesis, before detailing the operation of each algorithm. The methodology employed is varied in accordance with each of the five core challenges. However, a common element of methodology throughout the thesis is that of gradient descent within a new type of potential field, which is dynamic and capable of the simultaneous creation of high-quality paths and the controls required to execute them. By relating global to local considerations through subgoals, this methodology (combined with other elements) is shown to be fully capable of achieving the aims of the thesis. It is concluded that the produced system represents a novel and significant contribution as there is no other system (to the author’s knowledge) that provides all of the functionality given. For each component algorithm there are many control systems that provide one or more of its features, but none that are capable of all of the features. Applications for this work are wide ranging as it is comprised of five component algorithms each applicable in their own right. For example, high quality smooth paths may be created and followed in any dimensionality of space if time optimality and obstacle avoidance are not required. Broadly speaking, and in summary, applications are to ground-based robotics in the areas of smooth path planning, time optimal travel, and compensation for unpredictable perturbation.

Made available in DSpace on 2014-06-11T19:30:51Z (GMT). No. of bitstreams: 0 Previous issue date: 2006-08-30Bitstream added on 2014-06-13T20:47:24Z : No. of bitstreams: 1 ribeiro_jms_me_ilha.pdf: 1485185 bytes, checksum: 5ab0628a95f1aed7502862f70ee550ce (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Este trabalho apresenta três novas estratégias de controle discreto. O enfoque principal do trabalho foi dado ao Controle Discreto com Modos Deslizantes (CDMD) aplicados em sistemas que possuem atraso no processamento do sinal de controle. As novas estratégias de controle objetivam a elaboração de leis de fácil implementação prática e que ao mesmo tempo sejam robustas a incertezas da planta. Uma característica destas novas abordagens para controle discreto com atraso no tempo é a utilização de um Controle com Modos Deslizantes sem a necessidade de predição do sinal de controle. Os métodos de projeto propostos podem ser aplicados no controle de plantas estáveis ou instáveis com atraso no sinal de controle. Uma das estratégias foi elaborada para realizar controle apenas em sistemas discretos que não possuem atraso no sinal de controle, enquanto que as demais são utilizadas para controle em sistemas com atraso. São apresentadas simulações e resultados de implementações práticas, sobre uma planta estável de Controle Automático da Geração (CAG) e sobre um Sistema Pêndulo Invertido, que caracteriza bem uma planta instável. Os resultados comprovam a eficácia dos novos controladores. / This work presents three new strategies of discrete-time control. The main focus of the work was given to the Sliding Mode Control (SMC) applied in systems that present delay in the processing of the control sign. The new control strategies provide laws of control of easy practical implementation and that at the same time are robust to uncertainties of the plant. A characteristic of these new approaches, for discrete-time control with delay-time, is the use of a Sliding Mode Control without the need of prediction of the control signal. The proposed design methods can be applied in the control of stable or unstable plants, with delay in the control signal. One of the strategies was elaborated to accomplish control just in discrete-time system without delay-time in the control sign, while the others are used for control in systems with delay-time. Simulations and experimental results are shown on a stable plant of Automatic Generation Control (AGC) and on Inverted Pendulum System, that is an unstable plant. The results prove the controllers' effectiveness.

A pesquisa em visão computacional ainda está distante de replicar a adaptabilidade e o desempenho do Sistema Visual Humano. Grande parte das técnicas consolidadas são válidas apenas em cenas estáticas e condições restritivas. Cabeças robóticas representam um avanço em flexibilidade, pois carregam câmeras que podem ser movimentadas livremente para a exploração dos arredores. A observação artificial de um ambiente dinâmico exige a solução de pelo menos dois problemas: determinar quais informações perceptuais relevantes extrair dos sensores e como controlar seu movimento para mudar e manter a fixação de alvos com forma e movimento arbitrários. Neste trabalho, um sistema de controle de fixação binocular geral é proposto, e o subsistema responsável pela seleção de alvos e fixação de deslocamentos laterais é projetado, experimentado e avaliado em uma cabeça robótica com quatro graus de liberdade. O subsistema emprega um popular modelo de atenção visual de baixo nível para detectar o ponto mais saliente da cena e um controlador proporcional-integral gera um movimento conjuntivo das duas câmeras para centralizá-lo na imagem da câmera esquerda, assumida como dominante. O desenvolvimento do sistema envolveu primeiramente a modelagem física detalhada do mecanismo de pan e tilt das câmeras. Então, a estrutura linearizada obtida foi ajustada por mínimos quadrados aos dados experimentais de entrada-saída. Por fim, os ganhos do controlador foram sintonizados por otimização e ajuste manual. A implementação em C++ com a biblioteca OpenCV permitiu operação em tempo real a 30 Hz. Experimentos demonstram que o sistema é capaz de fixar alvos estáticos e altamente salientes sem conhecimento prévio ou fortes suposições. Alvos em movimento harmônico são perseguidos naturalmente, embora com defasamento. Em cenas visualmente densas, onde múltiplos alvos em potencial competem pela atenção, o sistema pode apresentar comportamento oscilatório, exigindo o ajuste fino dos pesos do algoritmo para operação suave. A adição de um controlador para o pescoço e de um controlador de vergência para a compensação de deslocamentos em profundidade são os próximos passos rumo a um observador artificial genérico. / Computer vision research is still far from replicating the adaptability and performance of the Human Visual System. Most of its consolidated techniques are valid only over static scenes and restrictive conditions. Robot heads represent an advance in terms of flexibility by carrying cameras that can be freely moved to explore the surroundings. Artificial observation of dynamic environments requires the solution of at least two problems: to determine what is the relevant perceptual information to be extracted from the sensors and how to control their movement in order to shift and hold gaze on targets featuring arbitrary shapes and motions. In this work, a general binocular gaze control system is proposed, and the subsystem responsible for targeting and following lateral displacements is designed, tested and assessed in a four degrees-of-freedom robot head. The subsystem employs a popular low-level visual attention model to detect the most salient point in the scene, and a proportional-integral controller generates a conjunctive movement of the cameras to center it in the left camera image, assumed to be dominant. The development started with a detailed physical modeling of the pan and tilt mechanism that drives the cameras. Then, the linearized structure obtained was fitted via least squares estimation to experimental input-output data. Finally, the controller gains were tuned by optimization and manual adjustment. The OpenCV-based implementation in C++ allowed real-time execution at 30 Hz. Experiments demonstrate that the system is capable of fixating highly salient and static targets without any prior knowledge or strong assumptions. Targets describing harmonic motion are naturally pursued, albeit with a phase shift. In cluttered scenes, where multiple potential targets compete for attention, the system may present oscillatory behavior, requiring fine adjustment of algorithm weights for smooth operation. The addition of a controller for the neck and a vergence controller to compensate for depth displacements are the next steps towards a generic artificial observer.

This dissertation investigates high-level decision making for agents that are both goal and utility driven. We develop a partially observable Markov decision process (POMDP) planner which is an extension of an agent programming language called DTGolog, itself an extension of the Golog language. Golog is based on a logic for reasoning about action—the situation calculus. A POMDP planner on its own cannot cope well with dynamically changing environments and complicated goals. This is exactly a strength of the belief-desire-intention (BDI) model: BDI theory has been developed to design agents that can select goals intelligently, dynamically abandon and adopt new goals, and yet commit to intentions for achieving goals. The contribution of this research is twofold: (1) developing a relational POMDP planner for cognitive robotics, (2) specifying a preliminary BDI architecture that can deal with stochasticity in action and perception, by employing the planner. / Computing / M. Sc. (Computer Science)