In the field of robotics, Artificial Intelligence based on Machine Learning and Deep Learning is a key enabling technology for robot navigation, interaction and task execution. Despite significant advances in AI, there remain notable hurdles in deploying AI algorithms in real-time safety-critical systems such as robotic systems, to achieve high levels of safety assurance in the presence of stringent hardware resource constraints. For Deep Learning-based perception based on computer vision, adversarial patch attacks have emerged as a potent technique for fooling classifiers by placing a patch on the input image, and defence techniques against such attacks is an active research topic. In this thesis, we address two research questions: RQ1: How do adversarial patch defence algorithms perform on different hardware platforms with varying computing capabilities? RQ2: How do heuristics-based adversarial defence algorithms perform with increasing patch sizes? To address RQ1, this thesis measures and compares among six well-known adversarial patch defence algorithms, including 14 models, on three different hardware platforms. Their performance in accuracy and processing time are compared and trade-offs are presented. To address RQ2, this thesis measures and compares accuracy and timing performance of a representative heuristics-based algorithm with increasing patch sizes, and compares the performance of masking-alone mitigation and Generative Adversarial Network (GAN)-based mitigation. The research results of this thesis aim to serve as a useful reference for the practical deployment of adversarial patch defence algorithms in robotic systems.

La politique criminelle est liée à un mode de fonctionnement particulier rattaché aux différences conceptuelles et structurelles des systèmes pénaux. Ainsi les solutions au phénomène criminel sont spécifiques à un mode de construction sociale dont la cohérence et l’efficience exigent la compatibilité de la conception de la politique criminelle avec le système pénal.La construction d’une justice pénale se distingue par sa configuration exclusive et par une lecture particulière des institutions qui la compose. Elle se réalise à travers un enchainement intellectuel spécifique qui intègre sa filiation historique, politique et sociale pour former un ensemble de références communes. / The conceptual and structural differences between penal systems and the operating mode of the criminal policies linked to these differences.The solutions to the criminal phenomenon are specific to a social construction model, which its consistency and efficiency require the compatibility of the criminal policy and the penal system.The construction of a criminal justice is distinguished by the exclusivity of its configuration and by a particular lecture of its institutions. It is performed throw an intellectual chaining that incorporates its historical, political and social filiations to realize a set of common references.

<p dir="ltr">Omnidirectional images are a way to visualize an environment in all directions. They have a spherical topology and require careful attention when represented by a computer. Namely, mapping the sphere to a plane introduces stretching of the spherical image content, and requires at least one seam in the image to be able to unwrap the sphere. Generative neural networks have shown impressive ability to synthesize images, but generating spherical images is still challenging. Without specific handling of the spherical topology, the generated images often exhibit distorted contents and discontinuities across the seams. We describe strategies for mitigating such distortions during image generation, as well as ensuring the image remains continuous across all boundaries. Our solutions can be applied to a variety of spherical image representations, including cube-maps and equirectangular projections.</p><p dir="ltr">A closely related problem in generative networks is 3D-aware scene generation, wherein the task involves the creation of an environment in which the viewpoint can be directly controlled. Many NeRF-based solutions have been proposed, but they generally focus on generation of single objects or faces. Full 3D environments are more difficult to synthesize and are less studied. We approach this problem by leveraging omnidirectional image synthesis, using the initial features of the network as a transformable foundation upon which to build the scene. By translating within the initial feature space, we correspondingly translate in the output omnidirectional image, preserving the scene characteristics. We additionally develop a regularizing loss based on epipolar geometry to encourage geometric consistency between viewpoints. We demonstrate the effectiveness of our method with a structure-from-motion-based reconstruction metric, along with comparisons to related works.</p>