Autonomous driving requires tactical decision-making while navigating in a dynamic shared space environment. The complexity and uncertainty in this process arise due to unknown and tightly-coupled interaction among traffic users. This thesis work formulates an unknown navigation problem as a Markov decision process (MDP), supported by models of traffic participants and userspace. Instead of modeling a traditional MDP, this work formulates a Multi-policy decision making (MPDM) in a shared space scenario with pedestrians and vehicles. The employed model enables a unified and robust self-driving of the ego vehicle by selecting a desired policy along the pre-planned path. Obstacle avoidance is coupled within the navigation module performing a detour off the planned path and obtaining a reward on task completion and penalizing for collision with others. In addition to this, the thesis work is further extended by analyzing the real-time constraints of the proposed model. The performance of the implemented framework is evaluated in a simulation environment on a typical construction (quarry) scenario. The effectiveness and efficiency of the elected policy verify the desired behavior of the autonomous vehicle.

Optimizing city logistics is a topic of great importance for big cities today. Even though the environmental- and economical consequences of the increasing goods transportation fleet has been present for quite some time, actions from affected stakeholders has not been taken until just recently.  In this brief 9 week project the aim has been to,  from a design point-of-view, in this complex topic, give a suggestion and raise a discussion onto how goods transportation in cities can be made in the future.  The basic idea is to get the consignments as close to the consignees and their travel patterns as possible. Public transportation networks are an existing grid where people are moving around and can potentially be used for combined transport of goods and people. The outcome of this concept is focusing on light parcel delivery towards private consignees, due to the increasing e-commerce trend. By using small transporter vehicles connected to buses, light parcels can be distributed throughout a city and easily accessible for consignees at the bus stops.  The transporter vehicle developed through this project aims to conceptualize connectivity and integration between mobility and parcel delivery services, to ease the every day life of urban citizens as well as decrease the environmental- and economical impacts which the distribution vehicle-fleet of today entails.  The design of the transporter vehicle is an interpretation of how a autonomous distribution vehicle can look like in a future city environment where the integration of public-utility-vehicles is of greater importance.

Os equipamentos robóticos foram inicialmente criados para atuarem em ambientes industriais fechados. Com o passar do tempo, melhorias foram conquistadas. Atualmente, não se limitam mais à realização de tarefas simples e repetitivas em locais especialmente preparados. Novos equipamentos, capazes de atuarem em ambientes abertos e de realizarem as mais diversas atividades, estão sendo desenvolvidos. Para tanto, é necessário que seus sistemas de controle realizem uma efetiva interação com o mundo onde estão inseridos. Fazem-se necessários, portanto, novos sistemas controladores com capacidade de uma contínua adaptação ao ambiente dinâmico onde operam. As redes neurais artificiais, devido a sua capacidade de tratamento de problemas não lineares – matematicamente difíceis de serem resolvidos, estão sendo empregadas no controle destes processos. O gerenciamento da trajetória de um veículo móvel em ambientes abertos ou fechados é um procedimento altamente não-linear, logo, a aplicação das redes neurais artificiais é bastante promissora. Apesar de sua grande versatilidade, as redes neurais artificiais têm sido utilizadas apenas como sistemas de mapeamento. A grande maioria delas necessita de uma fase de treinamento para que possam armazenar a diversidade de estados possíveis do sistema. Quando atuam, elas simplesmente mapeiam os seus valores de entrada (estado atual) nas soluções previamente armazenadas. Contudo, esta não é a melhor abordagem para os sistemas abertos, ou seja, para os processos cujas situações e possibilidades não podem ser totalmente enumeradas e que podem ser mutáveis no decorrer do tempo. Este trabalho apresenta uma metodologia de controle neural adaptativo para guiar um veículo móvel até o seu destino em ambientes contendo obstáculos fixos ou móveis. Diferentemente das abordagens tradicionais, não existe a necessidade de um treinamento prévio da rede. A rede neural artificial escolhida promove uma contínua adaptação do sistema enquanto atua. Neste processo, são utilizados sensores que fornecem subsídios para que a rede possa gerar, adaptativamente, soluções parciais que façam com que o veículo autônomo se aproxime cada vez mais do seu objetivo, até, finalmente, atingi-lo. / The robotic equipments were created initially to actuate in closed industrial environments. Improvements have been acquieved in this area. Nowadays, they are no longer limited to perform simple and repetitive tasks in controlled places. New equipments, capable of acting in open environments and doing the most several activities, are being developed. For so much, it is necessary that its control systems accomplish an effective interaction with the world where they are inserted. Therefore, new systems controllers with capacity of a continuous adaptation to the dynamic environments are essential. Artificial neural networks, due to their capacity of dealing wit non-linear problems – mathematically difficult to be solved – are being used to control these kind of processes. Guide a mobile vehicle through an open or controlled environments is a highly non-linear procedure; therefore, the use of an artificial neural nets is quite promising. In spite of its great versatility, they have just been used as mapping systems. Most of them need a training phase so that they can store the diversity of system’s possible states. When they actuate, they simply map their input values (current state) to the solutions previously stored. However, this is not the best approach for open systems, i.e. systems whose situations and possibilities cannot be totally enumerated and that can change in time. This work presents an adaptive neural control methodology to guide a mobile vehicle to its target in environments with fixed or mobile obstacles. Differently from the traditional approaches, the need of a previous training phase of the neural network doesn't exist. The chosen model of artificial neural net promotes a continuous adaptation of the system while it actuates. Sensors are used to provide informations to the net. This way it generates partial solutions that makes the autonomous vehicle gets closer of its goal, until, finally, reach it.

Os equipamentos robóticos foram inicialmente criados para atuarem em ambientes industriais fechados. Com o passar do tempo, melhorias foram conquistadas. Atualmente, não se limitam mais à realização de tarefas simples e repetitivas em locais especialmente preparados. Novos equipamentos, capazes de atuarem em ambientes abertos e de realizarem as mais diversas atividades, estão sendo desenvolvidos. Para tanto, é necessário que seus sistemas de controle realizem uma efetiva interação com o mundo onde estão inseridos. Fazem-se necessários, portanto, novos sistemas controladores com capacidade de uma contínua adaptação ao ambiente dinâmico onde operam. As redes neurais artificiais, devido a sua capacidade de tratamento de problemas não lineares – matematicamente difíceis de serem resolvidos, estão sendo empregadas no controle destes processos. O gerenciamento da trajetória de um veículo móvel em ambientes abertos ou fechados é um procedimento altamente não-linear, logo, a aplicação das redes neurais artificiais é bastante promissora. Apesar de sua grande versatilidade, as redes neurais artificiais têm sido utilizadas apenas como sistemas de mapeamento. A grande maioria delas necessita de uma fase de treinamento para que possam armazenar a diversidade de estados possíveis do sistema. Quando atuam, elas simplesmente mapeiam os seus valores de entrada (estado atual) nas soluções previamente armazenadas. Contudo, esta não é a melhor abordagem para os sistemas abertos, ou seja, para os processos cujas situações e possibilidades não podem ser totalmente enumeradas e que podem ser mutáveis no decorrer do tempo. Este trabalho apresenta uma metodologia de controle neural adaptativo para guiar um veículo móvel até o seu destino em ambientes contendo obstáculos fixos ou móveis. Diferentemente das abordagens tradicionais, não existe a necessidade de um treinamento prévio da rede. A rede neural artificial escolhida promove uma contínua adaptação do sistema enquanto atua. Neste processo, são utilizados sensores que fornecem subsídios para que a rede possa gerar, adaptativamente, soluções parciais que façam com que o veículo autônomo se aproxime cada vez mais do seu objetivo, até, finalmente, atingi-lo. / The robotic equipments were created initially to actuate in closed industrial environments. Improvements have been acquieved in this area. Nowadays, they are no longer limited to perform simple and repetitive tasks in controlled places. New equipments, capable of acting in open environments and doing the most several activities, are being developed. For so much, it is necessary that its control systems accomplish an effective interaction with the world where they are inserted. Therefore, new systems controllers with capacity of a continuous adaptation to the dynamic environments are essential. Artificial neural networks, due to their capacity of dealing wit non-linear problems – mathematically difficult to be solved – are being used to control these kind of processes. Guide a mobile vehicle through an open or controlled environments is a highly non-linear procedure; therefore, the use of an artificial neural nets is quite promising. In spite of its great versatility, they have just been used as mapping systems. Most of them need a training phase so that they can store the diversity of system’s possible states. When they actuate, they simply map their input values (current state) to the solutions previously stored. However, this is not the best approach for open systems, i.e. systems whose situations and possibilities cannot be totally enumerated and that can change in time. This work presents an adaptive neural control methodology to guide a mobile vehicle to its target in environments with fixed or mobile obstacles. Differently from the traditional approaches, the need of a previous training phase of the neural network doesn't exist. The chosen model of artificial neural net promotes a continuous adaptation of the system while it actuates. Sensors are used to provide informations to the net. This way it generates partial solutions that makes the autonomous vehicle gets closer of its goal, until, finally, reach it.

Recently, autonomous vehicles have received worldwide attentions from academic research, automotive industry and the general public. In order to achieve a higher level of automation, one of the most fundamental requirements of autonomous vehicles is the capability to respond to internal and external changes in a safe, timely and appropriate manner. Situational awareness and decision making are two crucial enabling technologies for safe operation of autonomous vehicles. This thesis presents a solution for improving the automation level of autonomous vehicles in both situational awareness and decision making aspects by utilising additional domain knowledge such as constraints and influence on a moving object caused by environment and interaction between different moving objects. This includes two specific sub-systems, model based target tracking in environmental perception module and motion planning in path planning module. In the first part, a rigorous Bayesian framework is developed for pooling road constraint information and sensor measurement data of a ground vehicle to provide better situational awareness. Consequently, a new multiple targets tracking (MTT) strategy is proposed for solving target tracking problems with nonlinear dynamic systems and additional state constraints. Besides road constraint information, a vehicle movement is generally affected by its surrounding environment known as interaction information. A novel dynamic modelling approach is then proposed by considering the interaction information as virtual force which is constructed by involving the target state, desired dynamics and interaction information. The proposed modelling approach is then accommodated in the proposed MTT strategy for incorporating different types of domain knowledge in a comprehensive manner. In the second part, a new path planning strategy for autonomous vehicles operating in partially known dynamic environment is suggested. The proposed MTT technique is utilized to provide accurate on-board tracking information with associated level of uncertainty. Based on the tracking information, a path planning strategy is developed to generate collision free paths by not only predicting the future states of the moving objects but also taking into account the propagation of the associated estimation uncertainty within a given horizon. To cope with a dynamic and uncertain road environment, the strategy is implemented in a receding horizon fashion.

Os equipamentos robóticos foram inicialmente criados para atuarem em ambientes industriais fechados. Com o passar do tempo, melhorias foram conquistadas. Atualmente, não se limitam mais à realização de tarefas simples e repetitivas em locais especialmente preparados. Novos equipamentos, capazes de atuarem em ambientes abertos e de realizarem as mais diversas atividades, estão sendo desenvolvidos. Para tanto, é necessário que seus sistemas de controle realizem uma efetiva interação com o mundo onde estão inseridos. Fazem-se necessários, portanto, novos sistemas controladores com capacidade de uma contínua adaptação ao ambiente dinâmico onde operam. As redes neurais artificiais, devido a sua capacidade de tratamento de problemas não lineares – matematicamente difíceis de serem resolvidos, estão sendo empregadas no controle destes processos. O gerenciamento da trajetória de um veículo móvel em ambientes abertos ou fechados é um procedimento altamente não-linear, logo, a aplicação das redes neurais artificiais é bastante promissora. Apesar de sua grande versatilidade, as redes neurais artificiais têm sido utilizadas apenas como sistemas de mapeamento. A grande maioria delas necessita de uma fase de treinamento para que possam armazenar a diversidade de estados possíveis do sistema. Quando atuam, elas simplesmente mapeiam os seus valores de entrada (estado atual) nas soluções previamente armazenadas. Contudo, esta não é a melhor abordagem para os sistemas abertos, ou seja, para os processos cujas situações e possibilidades não podem ser totalmente enumeradas e que podem ser mutáveis no decorrer do tempo. Este trabalho apresenta uma metodologia de controle neural adaptativo para guiar um veículo móvel até o seu destino em ambientes contendo obstáculos fixos ou móveis. Diferentemente das abordagens tradicionais, não existe a necessidade de um treinamento prévio da rede. A rede neural artificial escolhida promove uma contínua adaptação do sistema enquanto atua. Neste processo, são utilizados sensores que fornecem subsídios para que a rede possa gerar, adaptativamente, soluções parciais que façam com que o veículo autônomo se aproxime cada vez mais do seu objetivo, até, finalmente, atingi-lo. / The robotic equipments were created initially to actuate in closed industrial environments. Improvements have been acquieved in this area. Nowadays, they are no longer limited to perform simple and repetitive tasks in controlled places. New equipments, capable of acting in open environments and doing the most several activities, are being developed. For so much, it is necessary that its control systems accomplish an effective interaction with the world where they are inserted. Therefore, new systems controllers with capacity of a continuous adaptation to the dynamic environments are essential. Artificial neural networks, due to their capacity of dealing wit non-linear problems – mathematically difficult to be solved – are being used to control these kind of processes. Guide a mobile vehicle through an open or controlled environments is a highly non-linear procedure; therefore, the use of an artificial neural nets is quite promising. In spite of its great versatility, they have just been used as mapping systems. Most of them need a training phase so that they can store the diversity of system’s possible states. When they actuate, they simply map their input values (current state) to the solutions previously stored. However, this is not the best approach for open systems, i.e. systems whose situations and possibilities cannot be totally enumerated and that can change in time. This work presents an adaptive neural control methodology to guide a mobile vehicle to its target in environments with fixed or mobile obstacles. Differently from the traditional approaches, the need of a previous training phase of the neural network doesn't exist. The chosen model of artificial neural net promotes a continuous adaptation of the system while it actuates. Sensors are used to provide informations to the net. This way it generates partial solutions that makes the autonomous vehicle gets closer of its goal, until, finally, reach it.

La conduite autonome a attiré une attention croissante au cours des dernières décennies en raison de son potentiel impact socio-économique, notamment concernant la réduction du nombre d'accidents de la route et l'amélioration de l'efficacité du trafic. Grâce à l'effort de plusieurs instituts de recherche et d'entreprises, les véhicules autonomes ont déjà accumulé des dizaines de millions de kilomètres parcourus dans des conditions de circulation réelles. Cette thèse porte sur la conception d'une architecture de contrôle pour les véhicules autonomes et coopératifs dans l'optique de leur déploiement massif. La base commune des différentes architectures proposées dans cette thèse est le Contrôle-Commande Prédictif, reconnu pour son efficacité et sa polyvalence. Nous présentons tout d'abord une architecture classique de contrôle hiérarchique, qui utilise la commande prédictive pour planifier un déplacement (choix de trajectoire), puis déterminer un contrôle permettant de suivre cette trajectoire. Toutefois, comme nous le montrons dans un deuxième temps, cette architecture simple n'est pas capable de gérer certaines contraintes logiques, notamment liées aux règles de circulation et à l'existence de choix de trajectoires discrets. Nous proposons donc approche hybride de la commande prédictive, que nous utilisons pour développer une architecture de contrôle pour un véhicule autonome individuel. Nous étudions le problème de contrôler un ensemble de véhicules autonomes circulant en convoi, i.e. maintenir une formation prédéterminée sans intervention humaine. Pour ce faire, nous utilisons à nouveau une architecture hiérarchique basée sur la commande prédictive, composée d'un superviseur de convoi et de contrôleurs pour chaque véhicule individuel. Enfin, nous proposons encore une architecture pour le problème de coordonner un groupe de véhicules autonomes dans une intersection sans feux de circulation, en utilisant un contrôleur d'intersection et en adaptant les contrôleurs des véhicules individuels pour leur permettre de traverser l'intersection en toute sécurité. / Autonomous driving has been gaining more and more attention in the last decades, thanks to its positive social-economic impacts including the enhancement of traffic efficiency and the reduction of road accidents. A number of research institutes and companies have tested autonomous vehicles in traffic, accumulating tens of millions of kilometers traveled in autonomous driving. With the vision of massive deployment of autonomous vehicles, researchers have also started to envision cooperative strategies among autonomous vehicles. This thesis deals with the control architecture design of individual autonomous vehicles and cooperative autonomous vehicles. Model Predictive Control (MPC), thanks to its efficiency and versatility, is chosen as the building block for various control architectures proposed in this thesis. In more detail, this thesis first presents a classical hierarchical control architecture for individual vehicle control that decomposes the controller into a motion planner and a tracking controller, both using nonlinear MPC. In a second step, we analyze the inability of the proposed planner in handling logical constraints raised from traffic rules and multiple maneuver variants, and propose a hybrid MPC based motion planner that solves this issue. We then consider the convoy control problem of autonomous vehicles in which multiple vehicles maintain a formation during autonomous driving. A hierarchical formation control architecture is proposed composing of a convoy supervisor and local MPC based vehicle controllers. Finally, we consider the problem of coordinating a group of autonomous vehicles at an intersection without traffic lights. A hierarchical architecture composed of an intersection controller and multiple local vehicle controllers is proposed to allow vehicles to cross the intersection smoothly and safely.

With an imminent future of fully autonomous heavy duty vehicles in offroad applications, the need for advanced control system will increase accordingly. By implementing a raster map with tiles and pixels, to which a vehicle can record slope and position data while driving, it is possible to map earth's surface. By adding a heat parameter to every pixel, i.e. the number of passings through it historically, it is possible in future visits of the same are to generate a route prediction made up by the "hottest" pixels. By fetching the slope values in the hottest pixels, it is possible to generate a slope horizon that can be utilized by control systems, e.g. when planning gear shifts in hilly offroad terrain. To mange the incrementally growing map, a memory management system was implemented. It buffers the relevant map data from the database, i.e. the vehicles closest surroundings, which is then used for route prediction and horizon generation. As the vehicle moves into other areas, new data is read from the database, and the recently passed area is written back to the database, however updated from the recent passing. The system is implemented so that it runs through another application in the telematics electrical controller unit (ECU) in a Scania vehicle. The ECU contains a GNSS module from which the vehicle fetches satellite positioning data. Slope data is fetched from a slope sensor mounted on the truck. Due to implications during testing and debugging of the resulting application developed and implemented during this thesis project, the application's performance couldn't be assessed properly. However, it is concluded that the background the application is built on is reliable, although tweaks to get the application fit for usage in offroad terrain had to be made. Mainly, the horizon length and map building techniques should not be the same as in similar applications for onroad driving.

L'estimation de la pose (position et l'attitude) en temps réel est une fonction clé pour les véhicules autonomes routiers. Cette thèse vise à étudier des systèmes de localisation pour ces véhicules en utilisant des capteurs automobiles à faible coût. Trois types de capteurs sont considérés : des capteurs à l'estime qui existent déjà dans les automobiles modernes, des récepteurs GNSS mono-fréquence avec antenne patch et une caméra de détection de la voie regardant vers l’avant. Les cartes très précises sont également des composants clés pour la navigation des véhicules autonomes. Dans ce travail, une carte de marquage de voies avec une précision de l’ordre du décimètre est considérée. Le problème de la localisation est étudié dans un repère de travail local Est-Nord-Haut. En effet, les sorties du système de localisation sont utilisées en temps réel comme entrées dans un planificateur de trajectoire et un contrôleur de mouvement pour faire en sorte qu’un véhicule soit capable d'évoluer au volant de façon autonome à faible vitesse avec personne à bord. Ceci permet de développer des applications de voiturier autonome aussi appelées « valet de parking ». L'utilisation d'une caméra de détection de voie rend possible l’exploitation des informations de marquage de voie stockées dans une carte géoréférencée. Un module de détection de marquage détecte la voie hôte du véhicule et fournit la distance latérale entre le marquage de voie détecté et le véhicule. La caméra est également capable d'identifier le type des marquages détectés au sol (par exemple, de type continu ou pointillé). Comme la caméra donne des mesures relatives, une étape importante consiste à relier les mesures à l'état du véhicule. Un modèle d'observation raffiné de la caméra est proposé. Il exprime les mesures métriques de la caméra en fonction du vecteur d'état du véhicule et des paramètres des marquages au sol détectés. Cependant, l'utilisation seule d'une caméra a des limites. Par exemple, les marquages des voies peuvent être absents dans certaines parties de la zone de navigation et la caméra ne parvient pas toujours à détecter les marquages au sol, en particulier, dans les zones d’intersection. Un récepteur GNSS, qui est obligatoire pour le démarrage à froid, peut également être utilisé en continu dans le système de localisation multi-capteur du fait qu’il permet de compenser la dérive de l’estime. Les erreurs de positionnement GNSS ne peuvent pas être modélisées simplement comme des bruits blancs, en particulier avec des récepteurs mono-fréquence à faible coût travaillant de manière autonome, en raison des perturbations atmosphériques sur les signaux des satellites et les erreurs d’orbites. Un récepteur GNSS peut également être affecté par de fortes perturbations locales qui sont principalement dues aux multi-trajets. Cette thèse étudie des modèles formeurs de biais d’erreur GNSS qui sont utilisés dans le solveur de localisation en augmentant le vecteur d'état. Une variation brutale due à multi-trajet est considérée comme une valeur aberrante qui doit être rejetée par le filtre. Selon le flux d'informations entre le récepteur GNSS et les autres composants du système de localisation, les architectures de fusion de données sont communément appelées « couplage lâche » (positions et vitesses GNSS) ou « couplage serré » (pseudo-distance et Doppler sur les satellites en vue). Cette thèse étudie les deux approches. En particulier, une approche invariante selon la route est proposée pour gérer une modélisation raffinée de l'erreur GNSS dans l'approche par couplage lâche puisque la caméra ne peut améliorer la performance de localisation que dans la direction latérale de la route. / Estimating the pose (position and attitude) in real-time is a key function for road autonomous vehicles. This thesis aims at studying vehicle localization performance using low cost automotive sensors. Three kinds of sensors are considered : dead reckoning (DR) sensors that already exist in modern vehicles, mono-frequency GNSS (Global navigation satellite system) receivers with patch antennas and a frontlooking lane detection camera. Highly accurate maps enhanced with road features are also key components for autonomous vehicle navigation. In this work, a lane marking map with decimeter-level accuracy is considered. The localization problem is studied in a local East-North-Up (ENU) working frame. Indeed, the localization outputs are used in real-time as inputs to a path planner and a motion generator to make a valet vehicle able to drive autonomously at low speed with nobody on-board the car. The use of a lane detection camera makes possible to exploit lane marking information stored in the georeferenced map. A lane marking detection module detects the vehicle’s host lane and provides the lateral distance between the detected lane marking and the vehicle. The camera is also able to identify the type of the detected lane markings (e.g., solid or dashed). Since the camera gives relative measurements, the important step is to link the measures with the vehicle’s state. A refined camera observation model is proposed. It expresses the camera metric measurements as a function of the vehicle’s state vector and the parameters of the detected lane markings. However, the use of a camera alone has some limitations. For example, lane markings can be missing in some parts of the navigation area and the camera sometimes fails to detect the lane markings in particular at cross-roads. GNSS, which is mandatory for cold start initialization, can be used also continuously in the multi-sensor localization system as done often when GNSS compensates for the DR drift. GNSS positioning errors can’t be modeled as white noises in particular with low cost mono-frequency receivers working in a standalone way, due to the unknown delays when the satellites signals cross the atmosphere and real-time satellites orbits errors. GNSS can also be affected by strong biases which are mainly due to multipath effect. This thesis studies GNSS biases shaping models that are used in the localization solver by augmenting the state vector. An abrupt bias due to multipath is seen as an outlier that has to be rejected by the filter. Depending on the information flows between the GNSS receiver and the other components of the localization system, data-fusion architectures are commonly referred to as loosely coupled (GNSS fixes and velocities) and tightly coupled (raw pseudoranges and Dopplers for the satellites in view). This thesis investigates both approaches. In particular, a road-invariant approach is proposed to handle a refined modeling of the GNSS error in the loosely coupled approach since the camera can only improve the localization performance in the lateral direction of the road. Finally, this research discusses some map-matching issues for instance when the uncertainty domain of the vehicle state becomes large if the camera is blind. It is challenging in this case to distinguish between different lanes when the camera retrieves lane marking measurements.As many outdoor experiments have been carried out with equipped vehicles, every problem addressed in this thesis is evaluated with real data. The different studied approaches that perform the data fusion of DR, GNSS, camera and lane marking map are compared and several conclusions are drawn on the fusion architecture choice.

Le développement de véhicules autonomes capables de se déplacer sur les routes urbaines peuvent fournir des avantages importants en matière de réduction des accidents, en augmentant le confort et aussi, permettant des réductions de coûts. Les véhicules Intelligents par exemple fondent souvent leurs décisions sur les observations obtenues à partir de différents capteurs tels que les LIDAR, les GPS et les Caméras. En fait, les capteurs de la caméra ont reçu grande attention en raison du fait de qu’ils ne sont pas cher, facile à utiliser et fournissent des données avec de riches informations. Les environnements urbains représentent des scénarios intéressant mais aussi très difficile dans ce contexte, où le tracé de la route peut être très complexe,la présence d’objets tels que des arbres, des vélos, des voitures peuvent générer des observations partielles et aussi ces observations sont souvent bruyants ou même manquant en raison de occlusions complètes. Donc, le processus de perception par nature doit être capable de traiter des incertitudes dans la connaissance du monde autour de la voiture. Tandis que la navigation routière et la conduite autonome en utilisant une connaissance préalable de l’environnement ont démontré avec succès, la compréhension et la navigation des scénarios généraux du environnement urbain avec peu de connaissances reste un problème non résolu. Dans cette thèse, on analyse ce problème de perception pour la conduite dans les milieux urbains basée sur la connaissance de l’environnement pour aussi prendre des décisions dans la navigation autonome. Il est conçu un système de perception robotique, qui permettre aux voitures de se conduire sur les routes, sans la nécessité d’adapter l’infrastructure, sans exiger l’apprentissage précédente de l’environnement, et en tenant en compte la présence d’objets dynamiques tels que les voitures.On propose un nouveau procédé basé sur l’apprentissage par la machine pour extraire le contexte sémantique en utilisant une paire d’images stéréo qui est fusionnée dans une grille d’occupation évidentielle pour modéliser les incertitudes d’un environnement urbain inconnu,en utilisant la théorie de Dempster-Shafer. Pour prendre des décisions dans la planification des chemins, il est appliqué l’approche de tentacule virtuel pour générer les possibles chemins à partir du centre de référence de la voiture et sur cette base, deux nouvelles stratégies sont proposées. Première, une nouvelle stratégie pour sélectionner le chemin correct pour mieux éviter les obstacles et de suivre la tâche locale dans le contexte de la navigation hybride, et seconde, un nouveau contrôle en boucle fermée basé sur l’odométrie visuelle et tentacule virtuel est modélisée pour l’exécution du suivi de chemin. Finalement, un système complet automobile intégrant les modules de perception, de planification et de contrôle sont mis en place et validé expérimentalement dans des situations réelles en utilisant une voiture autonome expérimentale, où les résultats montrent que l’approche développée effectue avec succès une navigation locale fiable basée sur des capteurs de la caméra. / The development of autonomous vehicles capable of getting around on urban roads can provide important benefits in reducing accidents, in increasing life comfort and also in providing cost savings. Intelligent vehicles for example often base their decisions on observations obtained from various sensors such as LIDAR, GPS and Cameras. Actually, camera sensors have been receiving large attention due to they are cheap, easy to employ and provide rich data information. Inner-city environments represent an interesting but also very challenging scenario in this context,where the road layout may be very complex, the presence of objects such as trees, bicycles,cars might generate partial observations and also these observations are often noisy or even missing due to heavy occlusions. Thus, perception process by nature needs to be able to dea lwith uncertainties in the knowledge of the world around the car. While highway navigation and autonomous driving using a prior knowledge of the environment have been demonstrating successfully,understanding and navigating general inner-city scenarios with little prior knowledge remains an unsolved problem. In this thesis, this perception problem is analyzed for driving in the inner-city environments associated with the capacity to perform a safe displacement basedon decision-making process in autonomous navigation. It is designed a perception system that allows robotic-cars to drive autonomously on roads, with out the need to adapt the infrastructure,without requiring previous knowledge of the environment and considering the presenceof dynamic objects such as cars. It is proposed a novel method based on machine learning to extract the semantic context using a pair of stereo images, which is merged in an evidential grid to model the uncertainties of an unknown urban environment, applying the Dempster-Shafer theory. To make decisions in path-planning, it is applied the virtual tentacle approach to generate possible paths starting from ego-referenced car and based on it, two news strategies are proposed. First one, a new strategy to select the correct path to better avoid obstacles and tofollow the local task in the context of hybrid navigation, and second, a new closed loop control based on visual odometry and virtual tentacle is modeled to path-following execution. Finally, a complete automotive system integrating the perception, path-planning and control modules are implemented and experimentally validated in real situations using an experimental autonomous car, where the results show that the developed approach successfully performs a safe local navigation based on camera sensors.