Le véhicule autonome offre plusieurs avantages : le confort, la réduction du stress, et la réduction de la mortalité routière. Néanmoins, les accidents mortels impliquant sa responsabilité, ont mis en exergue ses limitations et ses imperfections. Ces accidents soulèvent des questions sur la fiabilité et des voix ont fait part d'une forte préoccupation pour la sécurité des usagers du véhicule autonome. En outre, les tâches de perception et de localisation des véhicules autonomes peuvent avoir des incohérences amenant à des erreurs qui nuiraient à la stabilité du véhicule. Les sources de ces incohérences peuvent être de natures différentes et agir à la fois sur le capteur lui-même (Hardware), ou bien sur le post-traitement de l'information (Software). Dans ce contexte, plusieurs difficultés doivent être surmontées pour arriver à sécuriser l'interaction des systèmes automatisés de conduite avec les conducteurs humains face à ces problèmes, l'adoption d'une stratégie de commande tolérante aux défauts est primordiale. Dans le cadre de cette thèse, des stratégies de détection et de tolérance aux fautes pour la perception et la localisation sont mise en œuvre. En outre, des stratégies de détection et d'estimation de défauts pour les capteurs proprioceptifs sont par ailleurs proposées. L'objectif est d'avoir une localisation fiable de défaut et assurer un fonctionnement avec des performances acceptables. Par ailleurs, vue l'imprédictibilité et la variété des scènes routières, une fusion tolérante aux fautes à base des algorithmes de vote est élaborée pour une meilleure perception. La fusion tire profit des technologies actuelles de détection d'obstacles (détection par radio, faisceaux lumineux ou par caméra) et l'algorithme de vote assure une sortie qui s'approche le plus de la réalité. Des tests avec des données réelles issues d'un véhicule démonstrateur sont utilisés pour valider les approches proposées dans cette thèse. / Driverless vehicle offers several advantages: comfort, reduced stress, and reduced road mortality. Nevertheless, fatal accidents involving its responsibility, have highlighted its limitations and imperfections. These accidents raise questions about autonomous vehicle reliability, and voices expressed a strong concern for the safety of users of the autonomous vehicle. Furthermore, the tasks of perception and localization of autonomous vehicles may have inconsistencies leading to errors that would affect the stability of the vehicle. The sources of these inconsistencies can be of different natures and act both on the sensor itself (Hardware), or on the post-processing of information (Software). In this context, several difficulties must be overcome to secure the interaction of automated driving systems with human drivers facing these problems, the adoption of a fault-tolerant control strategy is paramount. In this thesis, a fault detection and fault tolerant control strategies for perception and localization are implemented. In addition, fault estimation strategies for proprioceptive sensors are also proposed. The purpose is to have a reliable fault localization and ensure acceptable performance. Moreover, given the unpredictability and variety of road scenes, a fault-tolerant fusion based on voting algorithms is developed for a better perception. The fusion takes advantage of current obstacle detection technologies (radio, light beam or camera detection) and the voting algorithm provides an output that is closest to reality. Tests with real data from a demonstrator vehicle are used to validate the approaches proposed in this thesis.

<div> <div> <div> <p>For pedestrians and autonomous vehicles (AVs) to co-exist harmoniously and safely in the real-world, AVs will need to not only react to pedestrian actions, but also anticipate their intentions. In this thesis, we propose to use rich visual and pedestrian-environment interaction features to improve pedestrian crossing intention prediction from the ego-view. We do so by combining visual feature extraction, graph modeling of scene objects and their relationships, and feature encoding as comprehensive inputs for an LSTM encoder-decoder network. </p> <p>Pedestrians react and make decisions based on their surrounding environment, and the behaviors of other road users around them. The human-human social relationship has already been explored for pedestrian trajectory prediction from the bird’s eye view in stationary cameras. However, context and pedestrian-environment relationships are often missing in current research into pedestrian trajectory, and intention prediction from the ego-view. To map the pedestrian’s relationship to its surrounding objects we use a star graph with the pedestrian in the center connected to all other road objects/agents in the scene. The pedestrian and road objects/agents are represented in the graph through visual features extracted using state of the art deep learning algorithms. We use graph convolutional networks, and graph autoencoders to encode the star graphs in a lower dimension. Using the graph en- codings, pedestrian bounding boxes, and human pose estimation, we propose a novel model that predicts pedestrian crossing intention using not only the pedestrian’s action behaviors (bounding box and pose estimation), but also their relationship to their environment. </p> <p>Through tuning hyperparameters, and experimenting with different graph convolutions for our graph autoencoder, we are able to improve on the state of the art results. Our context- driven method is able to outperform current state of the art results on benchmark dataset Pedestrian Intention Estimation (PIE). The state of the art is able to predict pedestrian crossing intention with a balanced accuracy (to account for dataset imbalance) score of 0.61, while our best performing model has a balanced accuracy score of 0.79. Our model especially outperforms in no crossing intention scenarios with an F1 score of 0.56 compared to the state of the art’s score of 0.36. Additionally, we also experiment with training the state of the art model and our model to predict pedestrian crossing action, and intention jointly. While jointly predicting crossing action does not help improve crossing intention prediction, it is an important distinction to make between predicting crossing action versus intention.</p> </div> </div> </div>

Two controller performances are assessed for generalization in the path following task of autonomously backing up a tractor-trailer. Starting from random locations and orientations, paths are generated to loading docks with arbitrary pose using Dubins Curves. The combination vehicles can be varied in wheelbase, hitch length, weight distributions, and tire cornering stiffness. The closed form calculation of the gains for the Linear Quadratic Regulator (LQR) rely heavily on having an accurate model of the plant. However, real-world applications cannot expect to have an updated model for each new trailer. Finding alternative robust controllers when the trailer model is changed was the motivation of this research. Reinforcement learning, with neural networks as their function approximators, can allow for generalized control from its learned experience that is characterized by a scalar reward value. The Linear Quadratic Regulator and the Deep Deterministic Policy Gradient (DDPG) are compared for robust control when the trailer is changed. This investigation quantifies the capabilities and limitations of both controllers in simulation using a kinematic model. The controllers are evaluated for generalization by altering the kinematic model trailer wheelbase, hitch length, and velocity from the nominal case. In order to close the gap from simulation and reality, the control methods are also assessed with sensor noise and various controller frequencies. The root mean squared and maximum errors from the path are used as metrics, including the number of times the controllers cause the vehicle to jackknife or reach the goal. Considering the runs where the LQR did not cause the trailer to jackknife, the LQR tended to have slightly better precision. DDPG, however, controlled the trailer successfully on the paths where the LQR jackknifed. Reinforcement learning was found to sacrifice a short term reward, such as precision, to maximize the future expected reward like reaching the loading dock. The reinforcement learning agent learned a policy that imposed nonlinear constraints such that it never jackknifed, even when it wasn't the trailer it trained on.

This thesis discusses autonomous vehicles. At first it contains describing development of these type of vehicles, how they work and discuss their future development. Further it describe tools which can be used for create model of autonomous vehicle. The thesis includes design, description of the development and testing of the model in the UPPAAL Stratego verification environment. The resulting model is a system of intercommunicating timed automata. The analysis of the model properties is based on the method of statistical verification. The model allows us to investigate behavior of an autonomous vehicle in situations which correspond to regular traffic.

The study of this research has a challenge of learning data gathering sensor programming and design of electronic sensor circuit. The cost of autonomous vehicle development is expensive compared to purchasing an economy vehicle such as the Hyundai Elantra. Keeping the development cost down is critical to maintaining a competitive edge on vehicle pricing with newer technologies. Autonomous vehicle sensor integration was designed and then tested for the driving vision data-gathering system that requires the system to gather driving vision data utilizing area scan sensors, Lidar, ultrasonic sensor, and camera on real road scenarios. The project utilized sensors such as cheap cost LIDAR, which is that drone is used for on the road testing; other sensors include myRIO (myRIO Hardware), LabVIEW (LabVIEW software), LIDAR-Lite v3 (Garmin, 2019), Ultrasonic sensor, and Wantai stepper motor (Polifka, 2020). This research helps to reduce the price of usage of autonomous vehicle driving systems in the city. Due to resolution and Lidar detecting distance, the test environment is limited to within city areas. Lidar is the most expensive equipment on autonomous vehicle driving data gathering systems. This study focuses on replacing expensive Lidar, ultrasonic sensor, and camera to drone scale low-cost Lidar to real size vehicle. With this study, economic expense autonomous vehicle driving data acquisition is possible. Lowering the price of autonomous vehicle driving data acquisition increases involving new companies on the autonomous vehicle market. Multiple testing with multiple cars is possible. Since multiple testing at the same time is possible, collecting time reduces.

The human factor accounts for nine out of ten out of all traffic accidents, and because more vehicles are being deployed on the roads, the number of accidents will increase. Because of this, various automated functions have been implemented in vehicles in order to minimize the human factor in driving. In recent year, this development has accelerated and vehicles able to perform the complete driving task without any human assistance have begun to emerge from different projects around the world. However, the autonomous vehicle still has many barriers to overcome before safe driving in traffic becomes a reality. One of these barriers is the difficulty to visually perceive the surrounding. This is partly because of the fact that something can cover the camera sensors, but it is also problematic to translate the perceived data, that the sensors are collecting, into something valuable for the passenger. The situation could be improved if wireless communications were available to the autonomous vehicle. Instead of trying to understand the surrounding by the use of camera sensors, the autonomous vehicle could obtain the necessary data via wireless communication, which was the subject of this study. The study showed that wireless communication will be significant for the autonomous vehicle in the future. The conclusion is based on the fact that wireless communication was a solution in other transport systems that have had the similar barrier as for the autonomous vehicle. There are also plans on managing the barrier via wireless communication in pilot projects related to autonomous vehicles. / Den mänskliga faktorn står för nio av tio utav alla trafikolyckor, och eftersom att allt fler fordon kommer ut på vägarna så leder det till att olycksantalet ökar. På grund av detta så har olika automatiserade funktioner applicerats i fordonet för att undvika den mänskliga faktorn i körningen. Denna utveckling har accelererat och fordon som ska kunna utföra hela det dynamiska framförandet utan mänsklig assistans har börjat utvecklas i olika projekt runt om i världen. Dock så har det autonoma fordonet många barriärer kvar att övervinna, för säkert framförande, varav en av dessa barriärer är fordonets förmåga att visuellt uppfatta omgivningen. Dels genom att något kan täcka kamerasensorerna men även att kunna omsätta det sensorerna uppfattar till något värdefullt för passageraren. Situationen skulle dock kunna förbättras om trådlös kommunikation gjordes tillgänglig för det autonoma fordonet. Istället för att försöka uppfatta omgivningen via kamerasensorer, skulle det autonoma fordonet kunna få den information som behövs via trådlös kommunikation, vilket är vad denna studie behandlade. Studien visade att trådlös kommunikation kommer att ha en betydelse för det autonoma fordonet i framtiden. Slutsatsen grundar sig på att trådlös kommunikation varit en lösning inom andra transportsystem som haft en liknande barriär som för det autonoma fordonet. Man planerar dessutom på att hantera det autonoma fordonets barriär via trådlös kommunikation i pilotprojekt i dagsläget

No description available.

Autonomous vehicles rely on perceiving the environment using on-board sensor. These sensors have inherent limitations in terms of their effective range and risk occlusion due to their placement in the environment. These constraints limit the operational design domain of autonomous vehicles due to reliability and safety concerns. This report aims to show how an off-board sensor can be used as a complement to a vehicles on-board sensors. The goal of this sensor complement is to achieve an extension of the vehicle’s operational design domain and to relax constraints on the on-board sensors. Off-board sensors are less constrained in terms of sensor placement and allow for a more optimized location to perceive the environment. An autonomous vehicle is implemented and limitations in terms of sensing range and reliability is analyzed. An off-board camera based positioning system is also implemented and tested together with the autonomous vehicle in order to explore how an extension of the sensing range can be achieved. The extension of the operational design domain is tested by implementing a lane merge scenario which utilize both on and off-board sensor information. The lane merge scenario is also tested using different types of radio communication, namely 4G hotspot, 5G and wifi. The results of the lane merge scenario indicate that it is possible to achieve a range extension using an off-board sensor and thereby allow for a possible extension of the operational design domain of the autonomous vehicle. Although a range extension is possible, sending off-board sensor data over wireless radio raises questions on how applicable the solution is considering safety requirements in the automotive industry. / Autonoma fordon förlitar sig på att kunna uppfatta omgivningen med hjälp av sensorer ombord på fordonet. Dessa sensorer har begränsningar vid vilka avstånd de är tillförlitliga samt riskerar att bli ockluderade på grund av hur sensorn är placerad på fordonet. Dessa begränsningar försvårar fordonets användningsområde till följd av tillförlitlighet och säkerhetsaspekter. Denna rapport försöker visa hur en extern sensor kan användas för att komplettera sensorer ombord ett fordon. Målet med detta komplement är att åstadkomma en utökning av fordonets användningsområde samt minimera begränsningarna av fordonets förmåga att uppfatta omgivningen. Externa sensorer kan placeras med större frihet vilket möjliggör en mer optimal placering för att maximera förmågan att iaktta trafiken. Ett autonomt fordon implementeras och dess begränsningar i form av sensorkänslighet och pålitlighet analyseras. Ett externt kamera-baserat positioneringssystem är också utvecklat och testat tillsammans med det autonoma fordonet för att undersöka hur en utökning av användningsområdet kan genomföras. Utökningen av fordonets användningsområde testas genom att genomföra ett scenario där det autonoma fordonet ska dela körfält med en annan trafikant. I detta scenario används både sensorer ombord på det autonoma fordonet samt externa sensorer. Sensorinformationen delas genom olika typer av radiokommunikation, såsom, 4G hotspot, 5G och wifi för att se om nätverksfördröjningen har påverkan på resultaten. Resultatet tyder på att det är möjligt att uppfylla en utökning av det autonoma fordonets användningsområde genom att använda en extern sensor som utökar perceptionen av omgivningen. En utökning av användningsområdet är möjlig men väcker frågor om huruvida trådlös kommunikation kan uppfylla de krav och säkerhetsregulationer som finns inom bilindustrin.

En réponse aux problèmes croissants liés aux transports routiers - accidents, pollutions,congestions - les véhicules à faibles émissions, équipés de systèmes de transports intelligents (ITS)sont progressivement développés. Si la finalité de cette démarche est le véhicule entièrementautonome, on peut néanmoins s'attendre à voir d'abord sur nos routes des véhicules automatisés surdes phases de conduite spécifiques. C'est le cas du convoi automatisé, qui permet à plusieursvéhicules de rouler en convois de manière automatique et donc d'augmenter la capacité des voies decirculation tout en réduisant la consommation de carburant. La fiabilité de cet ITS repose surplusieurs briques technologiques, et en particulier sur la mesure de distance et la transmission dedonnées véhicule-véhicule (V2V).De nombreux systèmes permettent de réaliser ces deux fonctions vitales comme, par exemple, lesradars ou lidars pour la mesure de distance et la technologie IEEE 802.11p pour la communicationvéhiculaire. Si ces différents dispositifs présentent de très bonnes performances, ils sont néanmoinsparticulièrement sensibles aux interférences, qui ne cessent de se multiplier à mesure que le nombrede véhicules équipés augmente et que le trafic est dense. Pour pallier les dégradations deperformances induites par de telles situations, des technologies complémentaires pourraient donc êtreutiles. Le récent développement des diodes électroluminescentes (LED) blanches, en particulier pourl'éclairage automobile, a permis l'émergence des communications optiques visibles sans fil (VLC).Les phares à LED sont alors utilisés pour transmettre des données entre véhicules et avec lesinfrastructures. Malgré la puissance limitée de ces éclairages, plusieurs études ont montré qu'unetransmission de qualité est possible sur quelques dizaines de mètres, faisant de la VLC uncomplément particulièrement intéressant à l'IEEE 802.11p, en particulier pour les convoisautomatisés. Par analogie, on peut alors se demander si les phares ne pourraient pas être aussi utiliséspour mesurer la distance V2V.Le but de cette thèse est donc de proposer et évaluer un système dédié aux situations de convoisautomatisés qui, à partir des phares avant et arrière des véhicules, transmet des données et mesuresimultanément la distance V2V. Dans un premier temps, une étude détaillée de l'état de l'art de laVLC pour la communication V2V est effectuée afin de déterminer l'architecture de base de notresystème. La fonction de mesure de distance est ensuite ajoutée, après une revue des différentestechniques usuelles. Une fois l'architecture générale du système établie, elle est dans un premiertemps validée par des simulations avec le logiciel Simulink. En particulier, les différents paramètressont étudiés afin de déterminer leur impact sur la résolution de mesure de distance et les performancesen transmission de données, puis afin de les optimiser. Si ces simulations fournissent des indicateursimportants pour la compréhension du système, elles ne peuvent cependant remplacer les tests d'unprototype réel. L'implémentation de ce prototype est alors détaillée ainsi que les tests réalisés dansdifférentes configurations. Ces différents tests démontrent l'intérêt des solutions proposées pour lamesure de distance et la communication V2V en convois automatisés. / In response to the growing issues induced by road traffic - accidents, pollution, congestion- low-carbon vehicles equipped with intelligent transportation systems (ITS) are being developed.Although the final goal is full autonomy, the vehicles of the near future will most probably be selfdrivingin certain phases only, as in platooning. Platooning allows several vehicles to moveautomatically in platoons and thus to increase road capacity while reducing fuel consumption. Thereliability of this ITS is based on several core technologies and in particular on vehicle-to-vehicle(V2V) distance measurement and data transmission.These two vital functions can be implemented with several kinds of systems as, for instance, radars orlidars for range-finding and IEEE 802.11p-based devices for vehicular communication. Althoughthese systems provide good performances, they are very sensitive to interferences, which may be agrowing issue as the number of vehicles equipped will increase, especially in dense traffic scenario.In order to mitigate the performance degradation occurring in such situations, complementarysolutions may be useful. The recent developments of white light-emitting diodes (LED), especiallyfor the automotive lighting, has allowed the emergence of visible light communication (VLC). WithVLC, the vehicle headlamps and taillights are used to transmit data to other vehicles orinfrastructures. Despite the limited optical power available, several studies have shown thatcommunication over tens of meters are possible with a low bit error rate (BER). VLC could thus bean interesting complement to IEEE 802.11p, especially in platooning applications. By analogy, onecould wonder if the automotive lighting can also be used for V2V range-finding.The goal of this thesis is thus to propose and evaluate a system dedicated to platooning configurationsthat can perform simultaneously the V2V distance measurement and data transmission functionsusing the headlamps and taillights of the vehicles. The first step of this study is thus a detailed stateof-the art on VLC for V2V communication that will lead to a first basic architecture of our system.Then, the range-finding function is added, after a careful review of the classical techniques. Once thegeneral architecture of the system is drawn, it is validated through simulations in the Simulinkenvironment. The different degrees of freedom in the system design are especially studied, in orderfirst to evaluate their impact on the measurement resolution and the communication performances,and then to be optimized. Although these simulations provide crucial keys to understand the system,they cannot replace real prototype testing. The implementation of the prototype is thus fullydescribed, along with the results of the different experiments carried out. It is finally demonstratedthat the proposed solution has a clear interest for V2V range-finding and communication inplatooning applications.

This bachelor degree project presents an extension of a base optimization model for a transit line which can be used to evaluate the efficiency of different configurations of a platoon with different scenarios of berths. Furthermore, different levels of autonomous vehicles are studied, three cases are presented. The first case implies that every vehicle has a driver, the second, semi-autonomous vehicles are used in the platoon which has a leading vehicle with driver. Then, the fully autonomous vehicles represent the last studied case. A new method to compute the service time in the stops which differentiate the time that passengers are boarding or alighting from delays or time lost in queues that may appear with an increasing demand is added to the base model. It is introduced also a two-step non-linear approach to the crowding factor that consider the sharp deterioration when the load factor of the bus is almost one. In this project the bus capacity has been considered as a variable to see if there is an optimum vehicle size that cover different values of demand. Numerical results are provided and the result show that vehicle platooning with equal number of vehicles than stop berths is always competitive in high-demands. Moreover, if semi-autonomous case is found the bus platooning gain effectiveness and is competitive with lower demand values. In the case of fully autonomous vehicles the gain of bus platooning is not as high as in the semiautonomous but has still an improvement and is competitive with medium demand values.