The use of micro controllers in automotive application have exploded during the last half century. What was initially a set of mechanical systems that formed a vehicle have now become a collection of computers on wheels. The reason is quite obvious: micro controllers use several inputs to optimize the performance of systems; for example an engine control or an active safety system.The different inputs and outputs to these electronic units (electronic control unit, ECU) are of interest to other such units thereby justifying the need of inter-ECU communications. The Controller Area Network (CAN) bus has been developed to facilitate this communication. It is a message based protocol and is very resilient. It is however relatively slow and limited in terms of security. Security is assured only by trying to keep the message identification tags confidential and the bus physically separated to other network. A couple of decades ago our society embraced the Information Technology (IT) revolution. It allowed people to have extensive access to information. From a technology point of view, IT is based on the use of the Internet, which has been initially designed by the US military for robust applications. It is fast and its security is sufficiently high that we use it to communicate with our banks where we keep all our life savings.The aim of this thesis has been to combine these technologies such that a vehicle with a CAN bus could offer services (just like a bank does) over the Internet. The goal then is to transform a CAN bus to become a service provider over the Internet. The services are the broadcasted CAN messages made available to authorized interested parties and can post information and actuations to the ECUs connected to the CAN bus. A vehicle in that case becomes a cyber physical system. To make this transformation possible, we use the open source Arrowhead Framework, which is based on a Service Oriented Architecture (SOA). The available services are made known via a Service Registry and Orchestration service prosumers. Concretely, the work in this thesis project has been to develop (i.e., to design and implement) a CAN service prosumer that is Arrowhead Framework compliant. It has been successfully tested with another service prosumer, which is an Arrowhead Framework compliant data logger. The driving motivation for the thesis project are construction equipment machines, such as wheel loaders and excavators, which are vehicles with booms or arms. The aspiration is that they not only drive autonomously but also dig autonomously. This ambition shall require large amount of data to be exchanged, something that a CAN bus cannot handle.

Este trabalho teve por objetivo o desenvolvimento de um sistema de controle de navegação para um veículo autônomo utilizando lógica difusa. Atribui-se o nome de SNAT (Sistema de navegação-autônoma para um triciclo). O sistema é responsável pela automatização do processo de navegação de um veículo de testes monitorado e controlado de uma base remota mediante enlace de telemetria de dados. O usuário do sistema, pela tela principal da aplicação indica os pontos a seguir, cada um destes é referenciado pela sua latitude e longitude no mapa. Uma vez iniciada a navegação, o sistema de controle recebe periodicamente pacotes de dados da posição e direção do veículo; estes dados são processados pelo controlador difuso que gera os comandos para atuação sobre o veículo. O controlador difuso traduz as expressões qualitativas, comuns na comunicação humana em valores numéricos que representam a direção e a velocidade para manter ou corrigir a navegação do veículo de testes pelo rumo desejado. Nesta dissertação são apresentados diversos aspectos do desenvolvimento do controlador de navegação difusa, os mecanismos de comunicação e acionamento do veículo de uma base remota e os testes realizados que mostram os resultados do SNAT controlando automaticamente a navegação do veículo de testes. / This work had as a goal the development of a fuzzy logic based navigation control system for an autonomous vehicle. The developed control system was named SNAT (from the equivalent in portuguese of autonomous navigation system for a tricycle). The system controls and monitors the navigation of the vehicle from a remote base station using a telemetry data link. The user indicates, using a developed application, the navigation waypoints, referencing them by their latitude and longitude coordinates in a map. When the navigation starts, the system receives periodically data packets indicating the position and direction of the vehicle, these data are processed by the fuzzy control which returns commands to actuate over the vehicle. The fuzzy control translates qualitative expressions, common in human communication, into numerical values that represent the speed and the direction to keep the vehicle as near as possible to the desired navigation route. Many development aspects of the fuzzy controller and of the communication and actuation over the vehicle from the remote base are presented. Also are presented some results of the control system over navigation of the vehicle, which demonstrate that the system operates in a quite satisfactory manner.

Este trabalho aborda o controle de um veículo aéreo não tripulado (VANT) com carga pendular acoplada. Veículos autônomos apresentam desafios de controle dadas suas características como não linearidades, acoplamento de movimentos, dinâmicas desconhecidas, distúrbios ambientais e ser um sistema do tipo subatuado. O veículo aqui estudado apresenta seis graus de liberdade relativos ao movimento de corpo livre do robô e dois graus de liberdade adicionados pela carga pendular acoplada. Seu modelo matemático é deduzido através das equações de Lagrange, linearizado em torno do ponto de operação e validado através de simulações. O projeto de controle é baseado nos controladores lineares dos tipos PID, LQR e H? para sistemas multivariáveis. Uma vez obtidos os controladores, são apresentadas as simulações para três cenários distintos considerando estabilização a partir de condições iniciais e perturbações e incertezas. Os controladores resultantes das sínteses são simulados com a planta linear e não linear e verificados conforme seu desempenho. / The present work is focused on the stabilization control of Unmanned Aerial Vehicles (UAV) connected with a slung load. UAV Control is a challenging subject due its characteristics such as non-linearities, coupling dynamics, unknown dynam-ics, environmental disturbances which they are subjected and their underactuated nature. The vehicle presents six degrees of freedom relative to its free body configu-ration and two additional degrees of freedom for it slung load coupling. The mathe-matical model is derived for this configuration through the Lagrange approach, further linearized around its operation point and validated through simulations. The Control Design is based on three different linear controllers, PID, LQR and H? for multivariate systems. Once designed, they are simulated with the linear-ized plant and the non-linearized plant considering three different scenarios for stabi-lization. Finally, the controllers are tested and simulated on a virtual model and the results are presented and discussed.

Este trabalho teve por objetivo o desenvolvimento de um sistema de controle de navegação para um veículo autônomo utilizando lógica difusa. Atribui-se o nome de SNAT (Sistema de navegação-autônoma para um triciclo). O sistema é responsável pela automatização do processo de navegação de um veículo de testes monitorado e controlado de uma base remota mediante enlace de telemetria de dados. O usuário do sistema, pela tela principal da aplicação indica os pontos a seguir, cada um destes é referenciado pela sua latitude e longitude no mapa. Uma vez iniciada a navegação, o sistema de controle recebe periodicamente pacotes de dados da posição e direção do veículo; estes dados são processados pelo controlador difuso que gera os comandos para atuação sobre o veículo. O controlador difuso traduz as expressões qualitativas, comuns na comunicação humana em valores numéricos que representam a direção e a velocidade para manter ou corrigir a navegação do veículo de testes pelo rumo desejado. Nesta dissertação são apresentados diversos aspectos do desenvolvimento do controlador de navegação difusa, os mecanismos de comunicação e acionamento do veículo de uma base remota e os testes realizados que mostram os resultados do SNAT controlando automaticamente a navegação do veículo de testes. / This work had as a goal the development of a fuzzy logic based navigation control system for an autonomous vehicle. The developed control system was named SNAT (from the equivalent in portuguese of autonomous navigation system for a tricycle). The system controls and monitors the navigation of the vehicle from a remote base station using a telemetry data link. The user indicates, using a developed application, the navigation waypoints, referencing them by their latitude and longitude coordinates in a map. When the navigation starts, the system receives periodically data packets indicating the position and direction of the vehicle, these data are processed by the fuzzy control which returns commands to actuate over the vehicle. The fuzzy control translates qualitative expressions, common in human communication, into numerical values that represent the speed and the direction to keep the vehicle as near as possible to the desired navigation route. Many development aspects of the fuzzy controller and of the communication and actuation over the vehicle from the remote base are presented. Also are presented some results of the control system over navigation of the vehicle, which demonstrate that the system operates in a quite satisfactory manner.

Les systèmes cyber-physiques sont une classe de systèmes complexe, de grande échelle, souvent critiques de sûreté, qui apparaissent dans des applications industrielles variées. Des approches de vérification formelle sont capable de fournir des garanties pour la performance et la sûreté de ces systèmes. Elles nécessitent trois éléments : un modèle formel, une méthode de vérification, ainsi qu’un ensemble de spécifications formelles. En revanche, les modèles industriels sont typiquement informels, ils sont analysés dans des environnements de simulation informels et leurs spécifications sont décrits dans un langage naturel informel. Dans cette thèse, nous visons à faciliter l’intégration de la vérification formelle dans le processus industriel de la conception basé sur modèle.Notre première contribution clé est une méthodologie de transformation de modèle. A partir d’un modèle de simulation standard, nous le transformons en un modèle de vérification équivalent, plus précisément en un réseau d’automates hybrides. Le processus de transformation prend en compte des différences de syntaxes, sémantique et d’autres aspects de la modélisation. Pour cette classe de modèle formel, des algorithmes d’atteignabilité peuvent être appliqués pour vérifier des propriétés de sûreté. Un obstacle est que des algorithmes d’atteignabilité se mettent à l’échelle pour des modèles affines par morceaux, mais pas pour des modèles non linéaires. Pour obtenir des surapproximations affines par morceaux des dynamiques non linéaires, nous proposons une technique compositionnelle d’hybridisation syntaxique. Le résultat est un modèle très compact qui retient la structure modulaire du modèle d’origine de simulation, tout en évitant une explosion du nombre de partitions.La seconde contribution clé est une approche pour encoder des spécifications formelles riches de façon à ce qu’elles peuvent être interprétées par des outils d’atteignabilité. Nous prenons en compte des spécifications exprimées sous forme d’un gabarit de motif (pattern template), puisqu’elles sont proche au langage naturel et peuvent être compris facilement par des utilisateurs non experts. Nous fournissons (i) des définitions formelles pour des motifs choisis, qui respectent la sémantique des automates hybrides, et (ii) des observateurs qui encodes les propriétés en tant qu’atteignabilité d’un état d’erreur. En composant ces observateurs avec le modèle formel, les propriétés peuvent être vérifiées par des outils standards de vérification qui sont automatisés.Finalement, nous présentons une chaîne d’outils semi-automatisée ainsi que des études de cas menées en collaboration avec des partenaires industriels. / Cyber-Physical Systems form a class of complex, large-scale systems of frequently safety-critical nature in various industrial applications. Formal verification approaches can provide performance and safety guarantees for these systems. They require three elements: a formal model, a formal verification method, and a set of formal specifications. However, industrial models are typically non-formal, they are analyzed in non-formal simulation environments, and their specifications are described in non-formal natural language. In this thesis, we aim to facilitate the integration of formal verification into the industrial model-based design process.Our first key contribution is a model transformation methodology. Starting with a standard simulation model, we transform it into an equivalent verification model, particularly a network of hybrid automata. The transformation process addresses differences in syntax, semantics, and other aspects of modeling. For this class of formal models, so-called reachability algorithms can be applied to verify safety properties. An obstacle is that scalable algorithms exist for piecewise affine (PWA) models, but not for nonlinear ones. To obtain PWA over-approximations of nonlinear dynamics, we propose a compositional syntactic hybridization technique. The result is a highly compact model that retains the modular structure of the original simulation model and largely avoids an explosion in the number of partitions.The second key contribution is an approach to encode rich formal specifications so that they can be interpreted by tools for reachability. Herein, we consider specifications expressed by pattern templates since they are close to natural language and can be easily understood by non-expert users. We provide (i) formal definitions for select patterns that respect the semantics of hybrid automata, and (ii) monitors which encode the properties as the reachability of an error state. By composing these monitors with the formal model under study, the properties can be checked by off-the-shelf fully automated verification tools.Furthermore, we provide a semi-automated toolchain and present results from case studies conducted in collaboration with industrial partners.

Este trabalho aborda o controle de um veículo aéreo não tripulado (VANT) com carga pendular acoplada. Veículos autônomos apresentam desafios de controle dadas suas características como não linearidades, acoplamento de movimentos, dinâmicas desconhecidas, distúrbios ambientais e ser um sistema do tipo subatuado. O veículo aqui estudado apresenta seis graus de liberdade relativos ao movimento de corpo livre do robô e dois graus de liberdade adicionados pela carga pendular acoplada. Seu modelo matemático é deduzido através das equações de Lagrange, linearizado em torno do ponto de operação e validado através de simulações. O projeto de controle é baseado nos controladores lineares dos tipos PID, LQR e H? para sistemas multivariáveis. Uma vez obtidos os controladores, são apresentadas as simulações para três cenários distintos considerando estabilização a partir de condições iniciais e perturbações e incertezas. Os controladores resultantes das sínteses são simulados com a planta linear e não linear e verificados conforme seu desempenho. / The present work is focused on the stabilization control of Unmanned Aerial Vehicles (UAV) connected with a slung load. UAV Control is a challenging subject due its characteristics such as non-linearities, coupling dynamics, unknown dynam-ics, environmental disturbances which they are subjected and their underactuated nature. The vehicle presents six degrees of freedom relative to its free body configu-ration and two additional degrees of freedom for it slung load coupling. The mathe-matical model is derived for this configuration through the Lagrange approach, further linearized around its operation point and validated through simulations. The Control Design is based on three different linear controllers, PID, LQR and H? for multivariate systems. Once designed, they are simulated with the linear-ized plant and the non-linearized plant considering three different scenarios for stabi-lization. Finally, the controllers are tested and simulated on a virtual model and the results are presented and discussed.

<p>Connected and autonomous vehicle (CAV) technologies provide disruptive and transformational opportunities for innovations toward intelligent transportation systems. Compared with human driven vehicles (HDVs), the CAVs can reduce reaction time and human errors, increase traffic mobility and will be more knowledgeable due to vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. CAVs’ potential to reduce traffic accidents, improve vehicular mobility and promote eco-driving is immense. However, the new characteristics and capabilities of CAVs will significantly transform the future of transportation, including the dissemination of traffic information, traffic flow dynamics and network equilibrium flow. This dissertation seeks to realize and enhance the application of CAVs by specifically advancing the research in three connected topics: (1) modeling and controlling information flow propagation within a V2V communication environment, (2) designing a real-time deployable cooperative control mechanism for CAV platoons, and (3) modeling network equilibrium flow with a mix of CAVs and HDVs. </p> <p>Vehicular traffic congestion in a V2V communication environment can lead to congestion effects for information flow propagation due to full occupation of the communication channel. Such congestion effects can impact not only whether a specific information packet of interest is able to reach a desired location, but also the timeliness needed to influence traffic system performance. This dissertation begins with exploring spatiotemporal information flow propagation under information congestion effects, by introducing a two-layer macroscopic model and an information packet relay control strategy. The upper layer models the information dissemination in the information flow regime, and the lower layer model captures the impacts of traffic flow dynamics on information propagation. Analytical and numerical solutions of the information flow propagation wave (IFPW) speed are provided, and the density of informed vehicles is derived under different traffic conditions. Hence, the proposed model can be leveraged to develop a new generation of information dissemination strategies focused on enabling specific V2V information to reach specific locations at specific points in time.</p> <p>In a V2V-based system, multiclass information (e.g., safety information, routing information, work zone information) needs to be disseminated simultaneously. The application needs of different classes of information related to vehicular reception ratio, the time delay and spatial coverage (i.e., distance it can be propagated) are different. To meet the application needs of multiclass information under different traffic and communication environments, a queuing strategy is proposed for each equipped vehicle to disseminate the received information. It enables control of multiclass information flow propagation through two parameters: 1) the number of communication servers and 2) the communication service rate. A two-layer model is derived to characterize the IFPW under the designed queuing strategy. Analytical and numerical solutions are derived to investigate the effects of the two control parameters on information propagation performance in different information classes. </p> <p>Third, this dissertation also develops a real-time implementable cooperative control mechanism for CAV platoons. Recently, model predictive control (MPC)-based platooning strategies have been developed for CAVs to enhance traffic performance by enabling cooperation among vehicles in the platoon. However, they are not deployable in practice as they require anembedded optimal control problem to be solved instantaneously, with platoon size and prediction horizon duration compounding the intractability. Ignoring the computational requirements leads to control delays that can deteriorate platoon performance and cause collisions between vehicles. To address this critical gap, this dissertation first proposes an idealized MPC-based cooperative control strategy for CAV platooning based on the strong assumption that the problem can be solved instantaneously. It then develops a deployable model predictive control with first-order approximation (DMPC-FOA) that can accurately estimate the optimal control decisions of the idealized MPC strategy without entailing control delay. Application of the DMPC-FOA approach for a CAV platoon using real-world leading vehicle trajectory data shows that it can dampen the traffic oscillation effectively, and can lead to smooth deceleration and acceleration behavior of all following vehicles.</p> <p>Finally, this dissertation also develops a multiclass traffic assignment model for mixed traffic flow of CAVs and HDVs. Due to the advantages of CAVs over HDVs, such as reduced value of time, enhanced quality of travel experience, and seamless situational awareness and connectivity, CAV users can differ in their route choice behavior compared to HDV users, leading to mixed traffic flows that can significantly deviate from the single-class HDV traffic pattern. However, due to a lack of quantitative models, there is limited knowledge on the evolution of mixed traffic flows in a traffic network. To partly bridge this gap, this dissertation proposes a multiclass traffic assignment model. The multiclass model captures the effect of knowledge level of traffic conditions on route choice of both CAVs and HDVs. In addition, it captures the characteristics of mixed traffic flow such as the difference in value of time between HDVs and CAVs and the asymmetry in their driving interactions, thereby enhancing behavioral realism in the modeling. New solution algorithms will be developed to solve the multiclass traffic assignment model. The study results can assist transportation decision-makers to design effective planning and operational strategies to leverage the advantages of CAVs and manage traffic congestion under mixed traffic flows.</p> <p>This dissertation deepens our understanding of the characteristics and phenomena in domains of traffic information dissemination, traffic flow dynamics and network equilibrium flow in the age of connected and autonomous transportation. The findings of this dissertation can assist transportation managers in designing effective traffic operation and planning strategies to fully exploit the potential of CAVs to improve system performance related to traffic safety, mobility and energy consumption. </p>

Autonomous vehicles have increasingly become an attractive field due its promising capabilities of improvements regarding safety, comfort, traffic flow etc. A required attribute for those vehicles is the ability of autonomously compute its path towards a destination point. The path must be planned considering the constructive aspects of the vehicle in order to guarantee the maneuver feasibility. This work consists on computing a feasible path for autonomous vehicles with non-holonomic constraints. Piecewise linear continuouscurvature paths constituted of clothoids, circular arcs, and straight lines are used for this purpose, providing passenger\'s comfort. The road network is modeled from GPS (Global Positioning System) vehicle trajectories by defining lanes, roundabouts and intersections. GPS points are used later to parameterize lanes using clothoids and to extract roundabout centers and radii. This approach provides a sparse road network model since GPS points are replaced by parameterized curves. The information about connections between roads coming from the model is used by a global path planner, which computes a minimal length route from the vehicle current position to the destination point. After that, path planners compute intersection and roundabout paths depending on the nature of connections between roads. Also, lanes changes are performed to obey traffic rules. These three path planners that connects adjacent roads use clothoids, circular arc, and straight lines as interpolating curves whose curvature is constrained to that the vehicle can perform: the intersection path planner uses only a minimal amount of steering to perform the maneuver, increasing the comfort level; the roundabout path planner takes the roundabout center and radius as well as parameters that defines the entrance and exit maneuvers to compute the path; the lane change path planner connects lanes belonging to the same road with a prescribed longitudinal traveled distance depending on whether this maneuver is required. In the end, an global continuous-curvature path is generated. As the result of this work, a real urban scenario is modeled and the proposed approaches are validated. / Veículos autônomos têm cada vez mais se tornado um campo atraente de pesquisa devido às suas capacidades promissoras de melhorias em segurança, conforto, fluxo de tráfego, etc. Um atributo necessário para esses veículos é a capacidade de calcular, de forma autônoma, o seu caminho para um ponto de destino. O percurso deve ser planejado considerando os aspectos construtivos do veículo para que a viabilidade das manobras a serem executadas seja garantida. Este trabalho consiste no planejamento de trajetória para veículos autônomos com restrições não-holonômicas. Utilizam-se, para esse efeito, trajetórias cuja curvatura seja contínua e linear por partes, constituídas por clotóides, arcos de circunferência e retas, de forma a proporcionar conforto aos passageiros. A topologia de vias é modelada a partir de trajetórias definidas por pontos de GPS (Sistema de Posicionamento Global), definindo pistas, rotatórias e cruzamentos. Pontos de GPS são usados posteriormente para parametrizar as pistas usando clotóides a para extrair centros e raios das rotatórias. Essa abordagem proporciona um modelo esparso de topologia de vias uma vez que pontos de GPS são substituídos por curvas parametrizadas. A informação a cerca das conexões entre vias advinda do modelo é usada por um planejador de caminho global, o qual calcula a rota mais curta da posição atual do veículo até seu ponto de destino. Após essa etapa, planejadores calculam caminhos em cruzamentos e rotatórias dependendo do tipo de conexão entre as vias. Também, trocas de faixa devem ser executadas para obedecer regras de trânsito. Esses três planejadores de caminho usam clotóides, arcos de circunferência e retas como curvas interpoladoras, cuja curvatura é restrita a valores que o veículo é capaz de executar: o planejador de caminho em cruzamentos usa apenas um mínimo de velocidade de rotação do volante do veículo para executar a manobra, melhorando o nível de conforto; o planejador de caminho em rotatórias requer as coordenadas do centro e o raio da rotatória, bem como parâmetros que definem as manobras na entrada e na saída da rotatória para calcular o caminho; o planejador de caminho para troca de faixa conecta pistas pertencentes à mesma via com uma distância longitudinal do caminho previamente determinada. Ao final, um caminho com curvatura globalmente contínua é gerado. Como resultado deste trabalho, um cenário urbano real é modelado e os métodos propostos são validados.

A aquisição de dados das variáveis químicas e físicas da água de lagos e reservatórios é de extrema importância. Monitorando a qualidade da água distribuída e consumida em nossas cidades estamos protegendo o nosso recurso natural mais valioso e conseqüentemente nossas próprias vidas. Esse monitoramento na atualidade ainda se realiza de forma bastante convencional e trabalhosa. Esta dissertação apresenta o desenvolvimento de um sistema de telemetria de dados e vídeo completo entre uma plataforma autônoma para coleta de dados hidrológicos e uma estação de trabalho em terra. Este sistema fará uma composição com outros projetos já desenvolvidos nesta área de pesquisa, como a embarcação convencional utilizada como plataforma autônoma com seus motores, sensores e atuadores; a sonda de coleta de dados, responsável pela aquisição das variáveis químicas e físicas da água; sistema de posicionamento, que utiliza um GPS e bússola eletrônica para orientação, atuando e coletando dados dos sensores da embarcação; e sistema de gerenciamento, responsável por definir e orientar quais os pontos de coletas a serem pesquisados. Foram desenvolvidos algoritmos de comunicação entre os dispositivos de hardware existentes, efetivou-se a comunicação da plataforma autônoma e do microcomputador na estação terrestre através de um enlace de rádio freqüência, desenvolveu-se um programa visual que permite o acompanhamento do estado dos sensores/atuadores do sistema em terra em tempo mínimo e habilita para o usuário um controle remoto de navegação da embarcação autônoma de forma manual e completa se ocorrer a falha de algum equipamento de posicionamento. O programa armazena todas as variáveis referentes ao processo de coleta em um banco de dados, permitindo a análise e comparação das diferentes medições realizadas em diferentes períodos. / The data acquisition of the water chemical and physical variables in lakes and reservoirs is of extreme importance. Monitoring the quality of water supplied and consumed in our cities we are protecting the most valuable of our natural resources, and consequently our own lifes. Monitoring data quality, still in our days, is done in a conventional and hard manner. This work presents the development of a data and video telemetry system between an autonomous platform for water monitoring and a ground base. This system will complement the following already developed projects in this area, the autonomous platform constructed from a conventional boat with its engines, sensors and actuators; the data collecting probe, responsible for the acquisition of the water chemical and physical variables; the positioning system based on GPS and an electronic compass, responsible for navigation to the data collecting points in the reservoir. Communication algorithms between all the hardware were developed, radio frequency links were used to transmit data between the ground and the autonomous platform. A visual software application, that allows to visualize the state off the system variables, was developed. A remote control mode of the platform allows full manual navigation control of the platform, being of extreme importance in case of system crash. The visual software application developed allows to store all the important research variables in a data bank, allowing further analysis of the collected data.

Autonomous vehicles have increasingly become an attractive field due its promising capabilities of improvements regarding safety, comfort, traffic flow etc. A required attribute for those vehicles is the ability of autonomously compute its path towards a destination point. The path must be planned considering the constructive aspects of the vehicle in order to guarantee the maneuver feasibility. This work consists on computing a feasible path for autonomous vehicles with non-holonomic constraints. Piecewise linear continuouscurvature paths constituted of clothoids, circular arcs, and straight lines are used for this purpose, providing passenger\'s comfort. The road network is modeled from GPS (Global Positioning System) vehicle trajectories by defining lanes, roundabouts and intersections. GPS points are used later to parameterize lanes using clothoids and to extract roundabout centers and radii. This approach provides a sparse road network model since GPS points are replaced by parameterized curves. The information about connections between roads coming from the model is used by a global path planner, which computes a minimal length route from the vehicle current position to the destination point. After that, path planners compute intersection and roundabout paths depending on the nature of connections between roads. Also, lanes changes are performed to obey traffic rules. These three path planners that connects adjacent roads use clothoids, circular arc, and straight lines as interpolating curves whose curvature is constrained to that the vehicle can perform: the intersection path planner uses only a minimal amount of steering to perform the maneuver, increasing the comfort level; the roundabout path planner takes the roundabout center and radius as well as parameters that defines the entrance and exit maneuvers to compute the path; the lane change path planner connects lanes belonging to the same road with a prescribed longitudinal traveled distance depending on whether this maneuver is required. In the end, an global continuous-curvature path is generated. As the result of this work, a real urban scenario is modeled and the proposed approaches are validated. / Veículos autônomos têm cada vez mais se tornado um campo atraente de pesquisa devido às suas capacidades promissoras de melhorias em segurança, conforto, fluxo de tráfego, etc. Um atributo necessário para esses veículos é a capacidade de calcular, de forma autônoma, o seu caminho para um ponto de destino. O percurso deve ser planejado considerando os aspectos construtivos do veículo para que a viabilidade das manobras a serem executadas seja garantida. Este trabalho consiste no planejamento de trajetória para veículos autônomos com restrições não-holonômicas. Utilizam-se, para esse efeito, trajetórias cuja curvatura seja contínua e linear por partes, constituídas por clotóides, arcos de circunferência e retas, de forma a proporcionar conforto aos passageiros. A topologia de vias é modelada a partir de trajetórias definidas por pontos de GPS (Sistema de Posicionamento Global), definindo pistas, rotatórias e cruzamentos. Pontos de GPS são usados posteriormente para parametrizar as pistas usando clotóides a para extrair centros e raios das rotatórias. Essa abordagem proporciona um modelo esparso de topologia de vias uma vez que pontos de GPS são substituídos por curvas parametrizadas. A informação a cerca das conexões entre vias advinda do modelo é usada por um planejador de caminho global, o qual calcula a rota mais curta da posição atual do veículo até seu ponto de destino. Após essa etapa, planejadores calculam caminhos em cruzamentos e rotatórias dependendo do tipo de conexão entre as vias. Também, trocas de faixa devem ser executadas para obedecer regras de trânsito. Esses três planejadores de caminho usam clotóides, arcos de circunferência e retas como curvas interpoladoras, cuja curvatura é restrita a valores que o veículo é capaz de executar: o planejador de caminho em cruzamentos usa apenas um mínimo de velocidade de rotação do volante do veículo para executar a manobra, melhorando o nível de conforto; o planejador de caminho em rotatórias requer as coordenadas do centro e o raio da rotatória, bem como parâmetros que definem as manobras na entrada e na saída da rotatória para calcular o caminho; o planejador de caminho para troca de faixa conecta pistas pertencentes à mesma via com uma distância longitudinal do caminho previamente determinada. Ao final, um caminho com curvatura globalmente contínua é gerado. Como resultado deste trabalho, um cenário urbano real é modelado e os métodos propostos são validados.