The ability of a robot to navigate itself in the environment is a crucial step towards its autonomy. Navigation as a subtask of the development of autonomous robots is the subject of this thesis, focusing on the development of a method for simultaneous localization an mapping (SLAM) of mobile robots in six degrees of freedom (DOF). As a part of this research, a platform for 3D range data acquisition based on a continuously inclined laser rangefinder was developed. This platform is presented, evaluating the measurements and also presenting the robotic equipment on which the platform can be fitted. The localization and mapping task is equal to the registration of multiple 3D images into a common frame of reference. For this purpose, a method based on the Iterative Closest Point (ICP) algorithm was developed. First, the originally implemented SLAM method is presented, focusing on the time-wise performance and the registration quality issues introduced by the implemented algorithms. In order to accelerate and improve the quality of the time-demanding 6DOF image registration, an extended method was developed. The major extension is the introduction of a factorized registration, extracting 2D representations of vertical objects called leveled maps from the 3D point sets, ensuring these representations are 3DOF invariant. The extracted representations are registered in 3DOF using ICP algorithm, allowing pre-alignment of the 3D data for the subsequent robust 6DOF ICP based registration. The extended method is presented, showing all important modifications to the original method. The developed registration method was evaluated using real 3D data acquired in different indoor environments, examining the benefits of the factorization and other extensions as well as the performance of the original ICP based method. The factorization gives promising results compared to a single phase 6DOF registration in vertically structured environments. Also, the disadvantages of the method are discussed, proposing possible solutions. Finally, the future prospects of the research are presented.

Exploration is of interest for autonomous mapping and rescue applications using unmanned vehicles. The objective is to, without any prior information, explore all initially unmapped space. We present a system that can perform fast and efficient exploration of large scale arbitrary 3D environments. We combine frontier exploration planning (FEP) as a global planning strategy, together with receding horizon planning (RH-NBVP) for local planning. This leads to plans that incorporate information gain along the way, but do not get stuck in already explored regions. Furthermore, we make the potential information gain estimation more efficient, through sparse ray-tracing, and caching of already estimated gains. The worked carried out in this thesis has been published as a paper in Robotand Automation letters and presented at the International Conference on Robotics and Automation in Montreal 2019.

No description available.

No description available.

No description available.

The inherited rotation in a caster wheel allows movement in any direction, but pays at the expense of reaction torques. When implemented in a mobile robot, these forces have a negative impact in its performance. One approach is to restrict rotations on the spot by attaching a filter to the output of the motion planner. However, this formulation compromises the navigation’s completion in critical scenarios, such as parking, taking curves in narrow corridors or navigating at the presence of a high density of obstacles. Therefore, in this thesis we consider the influence of caster wheels in the motion planning stage, commonly presented as local planning. This work proposes a Model Predictive Control (MPC) based local planner that integrates the caster wheel physics into the motion planning stage. A caster wheel aware term is combined with a reference tracking based navigation, which leads to the formulation of the Caster Wheel Aware Local Planner (CWAWLP). Since this method requires knowing the caster wheel’s state and there is no sensor that provides this information, a caster wheel state observer is also formulated. In order to evaluate the impact of the caster wheel aware term, CWAWLP is compared to a Caster Wheel based Agnostic Local Planner (CWAGLP) and a Caster Wheel based Agnostic Planner Local Planner with Path Filter (CWPFLP). After running simulations for three case studies in a virtual framework, two experimental case studies are conducted in an intra-logistics robot. These are evaluated according to the navigation’s quality, motor torque usage and energy consumption. According to the patterns observed in the evaluation, CWAWLP covers a longer distance than CWAGLP wihout decreasing the navigation’s quality. At the same time, its motor torques are similar to the ones of CWPFLP. Therefore, CWAWLP is capable of considering caster wheel physics without sacrificing navigation capabilities. The formulated caster wheel aware term is compatible with any MPC based navigation algorithm and inherits the derivation of an observer capable of estimating caster wheel rotation angles and rolling speeds. Even if the caster wheel awareness has been implemented in a differential driven robot, this approach is also applicable to vehicles with an alternative drivetrain, such as car-like robots. / Den ärvda rotationen i ett hjul möjliggör rörelse i vilken riktning som helst, men fås på bekostnad av reaktionsmoment. När de implementeras i en mobil robot har dessa krafter en negativ inverkan på dess prestanda. Ett tillvägagångssätt är att begränsa rotationer på plats genom att applicera ett filter på rörelseplannerns utgång. Denna formulering komprometterar dock navigeringens slutförande i kritiska scenarier, såsom parkering, kurvor i smala korridorer eller navigering i närheten av höga hinder. Därför beaktar vi i denna avhandling påverkan av hjul på hjulplaneringen, som ofta presenteras som lokal planering. Detta arbete föreslår en Model Predictive Control (MPC) -baserad lokal planerare som integrerar svängbara länkhjuls fysik i rörelseplaneringsstadiet. En kugghjulmedveten term kombineras med en referensspårningsbaserad navigering, vilket leder till formuleringen av Caster Wheel Aware Local Planner (CWAWLP). Eftersom denna metod kräver kunskap om svängbara länkhjuls tillstånd och det inte finns någon sensor som ger denna information, formuleras också en hjulhjulstillståndsobservatör. För att utvärdera effekten av det medvetna begreppet svängbara änkhjul jämförs CWAWLP med en Caster Wheel-baserad Agnostic Local Planner (CWAGLP) och en Caster Wheel-baserad Agnostic Planner Local Planner with Path Filter (CWPFLP). Efter att ha kört simuleringar för tre fallstudier i ett virtuellt ramverk genomförs två experimentella fallstudier i en intra-logistikrobot. Dessa utvärderas enligt navigeringens kvalitet, vridmomentanvändning och energiförbrukning. Enligt de mönster som observerats i utvärderingen når CWAWLP ett längre avstånd än CWAGLP utan att sänka navigeringens kvalitet. Samtidigt liknar motorns vridmoment dem som CWPFLP. Därför kan CWAWLP ta hänsyn till svängbara länkhjuls fysik utan att offra navigationsfunktionerna. Den formulerade medhjulningsmedveten termen är kompatibel med vilken MPC-baserad navigationsalgoritm som helst och ärver härledningen av en observatör som kan uppskatta hjulets rotationsvinklar och rullningshastigheter. Även om hjulhjälpmedvetenheten har implementerats i en differentierad robot, är detta tillvägagångssätt också tillämpligt på fordon med ett alternativt drivsystem, såsom billiknande robotar.

Achieving robust and reliable autonomous operation even in complex unstructured environments is a central goal of field robotics. As the environments and scenarios to which robots are applied have continued to grow in complexity, so has the challenge of properly defining preferences and tradeoffs between various actions and the terrains they result in traversing. These definitions and parameters encode the desired behavior of the robot; therefore their correctness is of the utmost importance. Current manual approaches to creating and adjusting these preference models and cost functions have proven to be incredibly tedious and time-consuming, while typically not producing optimal results except in the simplest of circumstances. This thesis presents the development and application of machine learning techniques that automate the construction and tuning of preference models within complex mobile robotic systems. Utilizing the framework of inverse optimal control, expert examples of robot behavior can be used to construct models that generalize demonstrated preferences and reproduce similar behavior. Novel learning from demonstration approaches are developed that offer the possibility of significantly reducing the amount of human interaction necessary to tune a system, while also improving its final performance. Techniques to account for the inevitability of noisy and imperfect demonstration are presented, along with additional methods for improving the efficiency of expert demonstration and feedback. The effectiveness of these approaches is confirmed through application to several real world domains, such as the interpretation of static and dynamic perceptual data in unstructured environments and the learning of human driving styles and maneuver preferences. Extensive testing and experimentation both in simulation and in the field with multiple mobile robotic systems provides empirical confirmation of superior autonomous performance, with less expert interaction and no hand tuning. These experiments validate the potential applicability of the developed algorithms to a large variety of future mobile robotic systems.

Este trabalho propõe uma nova classe de algoritmos que permite o uso de heurísticas para aceleração do aprendizado por reforço. Esta classe de algoritmos, denominada \"Aprendizado Acelerado por Heurísticas\" (\"Heuristically Accelerated Learning\" - HAL), é formalizada por Processos Markovianos de Decisão, introduzindo uma função heurística H para influenciar o agente na escolha de suas ações, durante o aprendizado. A heurística é usada somente para a escolha da ação a ser tomada, não modificando o funcionamento do algoritmo de aprendizado por reforço e preservando muitas de suas propriedades. As heurísticas utilizadas nos HALs podem ser definidas a partir de conhecimento prévio sobre o domínio ou extraídas, em tempo de execução, de indícios que existem no próprio processo de aprendizagem. No primeiro caso, a heurística é definida a partir de casos previamente aprendidos ou definida ad hoc. No segundo caso são utilizados métodos automáticos de extração da função heurística H chamados \"Heurística a partir de X\" (\"Heuristic from X\"). Para validar este trabalho são propostos diversos algoritmos, entre os quais, o \"Q-Learning Acelerado por Heurísticas\" (Heuristically Accelerated Q-Learning - HAQL), que implementa um HAL estendendo o conhecido algoritmo Q-Learning, e métodos de extração da função heurística que podem ser usados por ele. São apresentados experimentos utilizando os algoritmos acelerados por heurísticas para solucionar problemas em diversos domínios - sendo o mais importante o de navegação robótica - e as heurísticas (pré-definidas ou extraídas) que foram usadas. Os resultados experimentais permitem concluir que mesmo uma heurística muito simples resulta em um aumento significativo do desempenho do algoritmo de aprendizado de reforço utilizado. / This work presents a new class of algorithms that allows the use of heuristics to speed up Reinforcement Learning (RL) algorithms. This class of algorithms, called \"Heuristically Accelerated Learning\" (HAL) is modeled using a convenient mathematical formalism known as Markov Decision Processes. To model the HALs a heuristic function that influences the choice of the actions by the agent during its learning is defined. As the heuristic is used only when choosing the action to be taken, the RL algorithm operation is not modified and many proprieties of the RL algorithms are preserved. The heuristic used in the HALs can be defined from previous knowledge about the domain or be extracted from clues that exist in the learning process itself. In the first case, the heuristic is defined from previously learned cases or is defined ad hoc. In the second case, automatic methods for the extraction of the heuristic function H called \"Heuristic from X\" are used. A new algorithm called Heuristically Accelerated Q-Learning is proposed, among others, to validate this work. It implements a HAL by extending the well-known RL algorithm Q-Learning. Experiments that use the heuristically accelerated algorithms to solve problems in a number of domains - including robotic navigation - are presented. The experimental results allow to conclude that even a very simple heuristic results in a significant performance increase in the used reinforcement learning algorithm.

O emprego de sistemas computacionais na Agricultura de Precisão (AP) fomenta a automação de processos e tarefas aplicadas nesta área, precisamente voltadas à inspeção e análise de culturas agrícolas, e locomoção guiada/autônoma de robôs móveis. Neste contexto, no presente trabalho foi proposta a aplicação de técnicas de visão computacional nas tarefas citadas, desenvolvidas em abordagens distintas, a serem aplicadas em uma plataforma de robô móvel agrícola, em desenvolvimento no NEPAS/EESC/USP. Para o problema de locomoção do robô (primeira abordagem), foi desenvolvida uma arquitetura de aquisição, processamento e análise de imagens com o objetivo de segmentar, classificar e reconhecer padrões de navegação das linhas de plantio, como referências de guiagem do robô móvel, entre plantações de laranja, milho e cana. Na segunda abordagem, tais técnicas de processamento de imagens são aplicadas também na inspeção e localização das culturas laranja (primário) e milho (secundário), para análise de suas características naturais, localização e quantificação. Para as duas abordagens, a estratégia adotada nas etapas de processamento de imagens abrange: filtragem no domínio espacial das imagens adquiridas; pré-processamento nos espaços de cores RGB e HSV; segmentação não supervisionada JSEG customizada à quantização de cores em regiões não homogêneas nestes espaços de cores; normalização e extração de características dos histogramas das imagens pré-processadas para os conjuntos de treinamento e teste através da análise das componentes principais; reconhecimento de padrões e classificação cognitiva e estatística. A metodologia desenvolvida contemplou bases de dados para cada abordagem entre 700 e 900 imagens de cenas naturais sob condições distintas de aquisição, apresentando resultados significativos quanto ao algoritmo de segmentação nas duas abordagens, mas em menor grau em relação à localização de gramíneas, sendo que os milhos requerem outras técnicas de segmentação, que não aplicadas apenas em quantização de regiões não homogêneas. A classificação estatística, Bayes e Bayes Ingênuo, mostrou-se superior à cognitiva RNA e Fuzzy nas duas abordagens, e posterior construção dos mapas de classe no espaço de cores HSV. Neste mesmo espaço de cores, a quantificação e localização de frutos apresentaram melhores resultados que em RGB. Com isso, as cenas naturais nas duas abordagens foram devidamente processadas, de acordo com os materiais e métodos empregados na segmentação, classificação e reconhecimento de padrões, fornecendo características intrínsecas e distintas das técnicas de visão computacional propostas a cada abordagem. / The use of computer systems in Precision Agriculture (PA) promotes the processes automation and its applied tasks, specifically the inspection and analysis of agricultural crops, and guided/autonomous locomotion of mobile robots. In this context, it was proposed in the present work the application of computer vision techniques on such mentioned tasks, developed in different approaches, to be applied in an agricultural mobile robot platform, under development at NEPAS/EESC/USP. For agricultural mobile robot locomotion, an architecture for the acquisition, image processing and analysis was built, in order to segment, classify and recognize patterns of planting rows, as references way points for guiding the mobile robot. In the second approach, such image processing techniques were applied also in the inspection and location of the orange crop (primary) and maize crop (secondary) aiming its natural features, location and quantification. For both mentioned approaches, the adopted image processing steps include: filtering in the spatial domain for acquired images; pre-processing in RGB and HSV color spaces; JSEG unsupervised segmentation algorithm, applied to color quantization in non-homogeneous regions; normalization and histograms feature extraction of preprocessed images for training and test sets, fulfilled by the principal components analysis (PCA); pattern recognition and cognitive and statistical classification. The developed methodology includes sets of 700 and 900 images databases for each approach of natural scenes under different conditions of acquisition, providing great results on the segmentation algorithm, but not as appropriate as in the location of maize grass, considering other segmentation techniques, applied not only in the quantization of non-homogeneous regions. Statistical classification, Bayes and Naive Bayes, outperforms the cognitives Fuzzy and ANN on two approaches and subsequent class maps construction in HSV color space. Quantification and localization of fruits had more accurate results in HSV than RGB. Thus, natural scenes in two approaches were properly processed, according to the materials and methods employed in segmentation, classification and pattern recognition, providing intrinsic and different features of the proposed computer vision techniques to each approach.

Graças aos avanços tecnológicos nas áreas da computação, eletrônica embarcada e mecatrônica a robótica está cada vez mais presente no cotidiano da pessoas. Nessas últimas décadas, uma infinidade de ferramentas e métodos foram desenvolvidos no campo da Robótica Móvel. Um exemplo disso são os sistemas inteligentes embarcados nos veículos de passeio. Tais sistemas auxiliam na condução através de sensores que recebem informações do ambiente e algoritmos que analisam os dados e tomam decisões para realizar uma determinada tarefa, como por exemplo estacionar um carro. Este trabalho tem por objetivo apresentar estudos realizados no desenvolvimento de um controlador inteligente capaz de estacionar um veículo simulado em vagas paralelas, na qual seja possível entrar com uma única manobra. Para isso, foi necessário realizar estudos envolvendo a modelagem de ambientes, cinemática veicular e sensores, os quais foram implementados em um ambiente de simulação desenvolvido em C# com o Visual Studio 2008. Em seguida é realizado um estudo sobre as três etapas do estacionamento, que consistem em procurar uma vaga, posicionar o veículo e manobrá-lo. Para realizar a manobra foi adotada a trajetória em S desenvolvida e muito utilizada em outros trabalhos encontrados na literatura da área. A manobra consiste em posicionar corretamente duas circunferências com um raio de esterçamento do veículo. Sendo assim, foi utilizado um controlador robusto baseado em aprendizado supervisionado utilizando Redes Neurais Artificiais (RNA), pois esta abordagem apresenta grande robustez com relação à presença de ruídos no sistema. Este controlador recebe dados de dois sensores laser (um fixado na frente do veículo e o outro na parte traseira), da odometria e de orientação de um sensor inercial. Os dados adquiridos desses sensores e a etapa da manobra em que o veículo está, servem de entrada para o controlador. Este é capaz de interpretar tais dados e responder a esses estímulos de forma correta em aproximadamente 99% dos casos. Os resultados de treinamento e de simulação se mostraram muito satisfatórios, permitindo que o carro controlador pela RNA pudesse estacionar corretamente em uma vaga paralela. / Thanks to technological advances in the fields of computer science, embedded electronics and mechatronics, robotics is increasingly more present in people\'s lives. On the past few decades a great variety of tools and methods were developed in the Mobile Robotics field, e.g. the passenger vehicles with smart embedded systems. Such systems help drivers through sensors that acquire information from the surrounding environment and algorithms which process this data and make decisions to perform a task, like parking a car. This work aims to present the studies performed on the development of a smart controller able to park a simulated vehicle in parallel parking spaces, where a single maneuver is enough to enter. To accomplish this, studies involving the modeling of environments, vehicle kinematics and sensors were conducted, which were implemented in a simulated environment developed in C# with Visual Studio 2008. Next, a study about the three stages of parking was carried out, which consists in looking for a slot, positioning the vehicle and maneuvering it. The \"S\" trajectory was adopted and developed to maneuver the vehicle, since it is well known and highly used in related works found in the literature of this field. The maneuver consists in the correct positioning of two circumferences with the possible steering radius of the vehicle. For this task, a robust controller based on supervised learning using Artificial Neural Networks (ANN) was employed, since this approach has great robustness regarding the presence of noise in the system. This controller receives data from two laser sensors (one attached on the front of the vehicle and the other on the rear), from the odometry and from the inertial orientation sensor. The data acquired from these sensors and the current maneuver stage of the vehicle are the inputs of the controller, which interprets these data and responds to these stimuli in a correct way in approximately 99% of the cases. The results of the training and simulation were satisfactory, allowing the car controlled by the ANN to correctly park in a parallel slot.