<p dir="ltr">The rapid advancement of autonomous vehicles (AVs) introduces complex cybersecurity challenges within Vehicular Ad-hoc Networks (VANETs). Despite the adoption of Artificial Intelligence (AI) for anomaly detection, a critical gap remains in both the explainability of AI models and the robustness of VANET frameworks against cyber intrusions, which limits trust, transparency, and resilience. This thesis addresses these gaps by proposing a multi-faceted, end-to-end explainable AI (XAI) framework alongside innovative security mechanisms to safeguard AV networks from potential attackers. In the initial chapter, we present an XAI framework that applies novel feature selection methods based on Shapley Additive Explanations (SHAP) to improve transparency in anomaly detection for AVs. The framework integrates global and local XAI approaches, offering interpretability across six black-box models and demonstrating superior performance over state-of-the-art feature selection techniques. The framework’s efficacy is validated through application to two AV datasets, showcasing improvements in both efficiency and generalizability. The second chapter builds upon this by systematically evaluating the effectiveness of XAI methods—namely SHAP and Local Interpretable Model-agnostic Explanations (LIME)— across multiple metrics. Through a rigorous benchmarking process on two autonomous driving datasets, this chapter highlights the strengths and limitations of each XAI technique, offering a foundational framework for transparency in AV cybersecurity and encouraging further research through publicly available resources. In the third chapter, we explore a security framework for platoon-based AV networks, addressing the need for secure and efficient highway usage. This framework introduces a two-phase anomaly detection system, incorporating an authenticity scoring mechanism and an LSTM-based roadside unit (RSU) for network-wide monitoring. Enhanced by group-based signatures and dynamic channel-switching, this approach defends against man-in-the-middle (MITM) and denial-of-service (DoS) attacks, demonstrating resilience through extensive simulation results. The final chapter examines the security of decentralized, Directed Acyclic Graph (DAG) based AV networks, which, while promising for scalability, are susceptible to unique cyber threats. We propose and evaluate four targeted attack scenarios alongside corresponding defense strategies across five DAG structures. This analysis reveals the resilience of different DAG configurations under attack, advancing the understanding of structural cybersecurity for decentralized AV networks. In summary, this thesis develops comprehensive frameworks and methodologies to enhance the security and interpretability of AV networks, bridging critical gaps in XAI and cybersecurity for anomaly detection and intrusion defense in AV environments.</p>

Un des fondements de l’Ingénierie Système réside dans la compréhension et la formulation des exigences de différentes parties prenantes pour mieux maîtriser et contrôler la complexité du système à concevoir. L’évaluation des performances du système nécessite par ailleurs la prise en compte des expertises interdisciplinaires qui peuvent être incertaines, voire incomplètes. La prise en compte des interdépendances entre plusieurs domaines d’activité dans la conception et le déploiement d’un système de mobilité urbaine durable est un bon exemple, qui reflète la problématique de l’élicitation des connaissances pluridisciplinaires, puis de leur utilisation dans la définition d’une architecture distribuée. Le renouveau de la mobilité urbaine a en effet fait émerger des alternatives aux déplacements habituels, faisant place à la mobilité douce, à l’usage raisonnée des véhicules personnels, à la multimodalité et à l’inter-mobilité. Dans ce contexte, la convergence tend à s’opérer vers des plateformes numériques offrant des services variés, à la demande, adaptés aux besoins immédiats des usagers. Ces services sont généralement développés par des acteurs du secteur privé qui détiennent à la fois l’expertise et la technologie pour les déployer. Il s’agit donc, pour les pouvoirs publics considérés comme organe de contrôle et de régulation de la mobilité, de définir quelles infrastructures et quels services offrir et selon quelles modalités. Le travail de recherche effectué dans cette thèse vise à proposer puis valider, une démarche générale pour accompagner les décideurs des villes dans la conception et la mise en place des solutions de mobilité du futur. Un cadre méthodologique prenant en compte l’aide au choix de politiques et de partenaires cibles a pour cela été proposé, basé sur une méthode d’analyse multicritère, dans un cadre de décision collective et sous incertitude. Un méta-modèle d’un système de mobilité durable a ensuite été élaboré, à partir des connaissances élicitées d’un ensemble de standards et référentiels, de même qu’une architecture distribuée du système. Afin d’étudier la faisabilité de l’implémentation de cette architecture, en considérant le point de vue de l’aide à la décision, une roadmap de mise en œuvre a enfin été proposée, basée sur un système de recommandations visant à optimiser la réalisation de projets de mobilité nouveaux / One basics of System Engineering consists in understanding and formalizing the requirements ofdifferent stakeholders in order to better control and handle the complexity of the system to bedesigned. The evaluation of the system's performance also requires taking into accountinterdisciplinary expertise, which may be uncertain or ill-known. The consideration ofinterdependencies among several fields of activity in the design and deployment of a sustainableurban mobility system is a good example, which reflects the issue of the elicitation ofmultidisciplinary knowledge, then its use in the definition of a distributed architecture. The renewalof urban mobility has indeed given rise to alternatives to the usual forms of travel, leading to softmobility, rational use of personal vehicles, multi-modality and inter-mobility. In such a context,convergence is tending towards digital platforms offering various services, on demand adapted tothe immediate needs of end-users. These services are usually developed by private companieswho have both the expertise and the technology to deploy them. It is therefore a matter for thepublic authorities, considered as a regulating and controlling organism of the urban mobility, todefine which infrastructures and which services to offer and under which conditions. The presentresearch work aims at proposing and validating a general method to assist city decision-makers inthe design and implementation of mobility solutions for the future. A methodological frameworktaking into account a support in the choice of targeted policies and partners was proposed for thispurpose, based on a multi-criteria analysis method, within a group decision-making framework andunder uncertainty. A meta-model of a sustainable mobility system was then elaborated, based onthe knowledge elicited from a set of standards, as well as a distributed architecture of the system.In order to study the feasibility of implementing this architecture, from a decision support point ofview, a deployment roadmap was finally proposed, based on a system of recommendationsaiming at optimizing the implementation of new mobility projects.

<p dir="ltr">Path-tracking control is an integral part of motion planning in autonomous vehicles, in which the vehicle's lateral and longitudinal positions are controlled by a control system that will provide acceleration and steering angle commands to ensure accurate tracking of longitudinal and lateral movements in reference to a pre-defined trajectory. Extensive research has been conducted to address the growing need for efficient algorithms in this area. In this dissertation, a scenario and machine learning-based data-driven control approach is proposed for a path-tracking controller. Firstly, a Deep Reinforcement Learning model is developed to facilitate the control of longitudinal speed. A Deep Deterministic Policy Gradient algorithm is employed as the primary algorithm in training the reinforcement learning model. The main objective of this model is to maintain a safe distance from a lead vehicle (if present) or track a velocity set by the driver. Secondly, a lateral steering controller is developed using Neural Networks to control the steering angle of the vehicle with the main goal of following a reference trajectory. Then, a path-planning algorithm is developed using a hybrid A* planner. Finally, the longitudinal and lateral control models are coupled together to obtain a complete path-tracking controller that follows a path generated by the hybrid A* algorithm at a wide range of vehicle speeds. The state-of-the-art path-tracking controller is also built using Model Predictive Control and Stanley control to evaluate the performance of the proposed model. The results showed the effectiveness of both proposed models in the same scenario, in terms of velocity error, lateral yaw angle error, and lateral distance error. The results from the simulation show that the developed hybrid A* algorithm has good performance in comparison to the state-of-the-art path planning algorithms.</p>

<p dir="ltr">Cellular-Vehicle to Everything or C-V2X refers to vehicles connected to their surroundings using cellular based networks. With the rise of connected vehicles, C-V2X is emerging as one of the major standards for message transmission in automotive scenarios. The project aims to study the feasibility of C-V2X-based message transmission by building a prototype system, named <b>RampCast</b>, for transmitting traffic information from roadside message boards to vehicles. The RampCast framework would also implement geocasting-based algorithms to deliver messages to targeted vehicles. These algorithms focus on improving location-based message delivery using retransmission and prioritization strategies. The messages used for transmission are selected from the 511 web application built by INDOT, which contains the live traffic information for the state of Indiana which includes Travel Time information, Crash Alerts, Construction Alerts etc.</p><p dir="ltr">The major objectives of this project consist of building the RampCast prototype, a system implementing C-V2X networks using a Software Defined Radio(SDR). The RampCast system implements a Publisher-subscriber messaging architecture with the primary actors being a Road Side Unit(RSU) and a Vehicle Onboard Unit(OBU). A data store containing traffic messages sourced from the 511 API is set up to be the input to the RampCast system. An end-to-end message transmission pipeline is built that would implement message transmission algorithms on the RSU and OBU side. Finally, the performance of message transmission on the RampCast system is evaluated using a metrics-capturing module. The system was evaluated on a test track in Columbus, Indiana. The performance metrics of the system were captured and analyzed, and the system met the key performance indicators for Latency, Packet Delivery Rate, and Packet Inter-reception Rate. The results indicate the satisfactory performance of the C-V2X standard for message transmission in the RampCast traffic guidance scenarios.</p>