pr\u00e9sentent<\/p>\n\n\n\n
Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en :<\/p>\n\n\n\n
le LUNDI 22 AVRIL 2024 \u00e0 14h30<\/p>\n\n\n\n
\u00e0<\/p>\n\n\n\n
Amphith\u00e9\u00e2tre 7
19 Place Marguerite Perey, 91120 Palaiseau<\/p>\n\n\n\n
Membres du jury :<\/strong><\/p>\n\n\n\n Mme Amel BOUZEGHOUB<\/strong>, Professeure, T\u00e9l\u00e9com SudParis, FRANCE – Directrice de th\u00e8se R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n La recherche effectu\u00e9e dans cette th\u00e8se concerne le domaine de la conduite urbaine s\u00fbre, en utilisant des m\u00e9thodes de fusion de capteurs et d’apprentissage par renforcement pour la perception et le contr\u00f4le des v\u00e9hicules autonomes (VA). L’\u00e9volution g\u00e9n\u00e9ralis\u00e9e des technologies d’apprentissage automatique ont principalement propuls\u00e9 la prolif\u00e9ration des v\u00e9hicules autonomes ces derni\u00e8res ann\u00e9es. Cependant, des progr\u00e8s substantiels sont n\u00e9cessaires avant d’atteindre une adoption g\u00e9n\u00e9ralis\u00e9e par le grand public. Pour accomplir son automatisation, les v\u00e9hicules autonomes n\u00e9cessitent l’int\u00e9gration d’une s\u00e9rie de capteurs co\u00fbteux (e.g. cam\u00e9ras, radars, LiDAR et capteurs \u00e0 ultrasons). En plus de leur fardeau financier, ces capteurs pr\u00e9sentent une sensibilit\u00e9 aux variations telles que la m\u00e9t\u00e9o, une limitation non partag\u00e9e par les conducteurs humains qui peuvent naviguer dans des conditions diverses en se fiant \u00e0 une vision frontale simple. Par ailleurs, l’av\u00e8nement des algorithmes neuronaux de prise de d\u00e9cision constitue l’intelligence fondamentale des v\u00e9hicules autonomes. Les solutions d’apprentissage profond par renforcement, facilitant l’apprentissage de la politique du conducteur de bout en bout, ont trouv\u00e9 application dans des sc\u00e9narios de conduite \u00e9l\u00e9mentaires, englobant des t\u00e2ches telles que le maintien dans la voie, le contr\u00f4le de la direction et la gestion de l’acc\u00e9l\u00e9ration. Cependant, il s’av\u00e8re que ces algorithmes sont co\u00fbteux en temps d’ex\u00e9cution et n\u00e9cessitent de large ensembles de donn\u00e9es pour un entra\u00eenement efficace. De plus, la s\u00e9curit\u00e9 doit \u00eatre prise en compte tout au long des phases de d\u00e9veloppement et de d\u00e9ploiement des v\u00e9hicules autonomes. La premi\u00e8re contribution de cette th\u00e8se am\u00e9liore la localisation des v\u00e9hicules en fusionnant les mesures des capteurs GPS et IMU avec une adaptation d’un filtre de Kalman, ES-EKF, et une r\u00e9duction du bruit des mesures IMU. L’algorithme est d\u00e9ploy\u00e9 et test\u00e9 en utilisant des donn\u00e9es de v\u00e9rit\u00e9 terrain sur un microcontr\u00f4leur. La deuxi\u00e8me contribution propose l’algorithme DPPO-IL (Dynamic Proximal Policy Optimization with Imitation Learning), con\u00e7u pour faciliter le stationnement automatis\u00e9 en accordant une attention toute particuli\u00e8re \u00e0 la s\u00e9curit\u00e9. Cet algorithme apprend \u00e0 ex\u00e9cuter des man\u0153uvres de stationnement optimales tout en naviguant entre des d’obstacles statiques et dynamiques gr\u00e2ce \u00e0 un entra\u00eenement complet int\u00e9grant des donn\u00e9es simul\u00e9es et r\u00e9elles. La troisi\u00e8me contribution est un framework de conduite urbaine de bout en bout appel\u00e9 Guided Hierarchical Reinforcement Learning (GHRL). Il int\u00e8gre des donn\u00e9es de vision et de localisation ainsi que des d\u00e9monstrations d’experts exprim\u00e9es avec des r\u00e8gles ASP (Answer Set Programming) pour guider la politique d’exploration de l’apprentissage par renforcement hi\u00e9rarchique et acc\u00e9l\u00e9rer la convergence de l’algorithme. Lorsqu’une situation critique se produit, le syst\u00e8me s’appuie \u00e9galement sur des r\u00e8gles li\u00e9es \u00e0 la s\u00e9curit\u00e9 pour faire des choix judicieux dans des conditions impr\u00e9visibles ou dangereuses. GHRL est \u00e9valu\u00e9 sur le jeu de donn\u00e9es NoCrash du simulateur Carla et les r\u00e9sultats montrent qu’en incorporant des r\u00e8gles logiques, GHRL obtient de meilleures performances que les algorithmes de l’\u00e9tat de l’art.<\/p>\n\n\n\n Abstract :<\/strong><\/p>\n\n\n\n The research conducted in this thesis is centered on the domain of safe urban driving, employing sensor fusion and reinforcement learning methodologies for the perception and control of autonomous vehicles (AV). The evolution and widespread integration of machine learning technologies have primarily propelled the proliferation of autonomous vehicles in recent years. However, substantial progress is requisite before achieving widespread adoption by the general populace. To accomplish its automation, autonomous vehicles necessitate the integration of an array of costly sensors, including cameras, radars, LiDARs, and ultrasonic sensors. In addition to their financial burden, these sensors exhibit susceptibility to environmental variables such as weather, a limitation not shared by human drivers who can navigate diverse conditions with a reliance on simple frontal vision. Moreover, the advent of decision-making neural network algorithms constitutes the core intelligence of autonomous vehicles. Deep Reinforcement Learning solutions, facilitating end-to-end driver policy learning, have found application in elementary driving scenarios, encompassing tasks like lane-keeping, steering control, and acceleration management. However, these algorithms demand substantial time and extensive datasets for effective training. In addition, safety must be considered throughout the development and deployment phases of autonomous vehicles. The first contribution of this thesis improves vehicle localization by fusing data from GPS and IMU sensors with an adaptation of a Kalman filter, ES-EKF, and a reduction of noise in IMU measurements. This method excels in urban environments marked by signal obstructions and elevated noise levels, effectively mitigating the adverse impact of noise in IMU sensor measurements, thereby maintaining localization accuracy and robustness. The algorithm is deployed and tested employing ground truth data on an embedded microcontroller. The second contribution introduces the DPPO-IL (Dynamic Proximal Policy Optimization with Imitation Learning) algorithm, designed to facilitate end-to-end automated parking while maintaining a steadfast focus on safety. This algorithm acquires proficiency in executing optimal parking maneuvers while navigating static and dynamic obstacles through exhaustive training incorporating simulated and real-world data.The third contribution is an end-to-end urban driving framework called GHRL. It incorporates vision and localization data and expert demonstrations expressed in the Answer Set Programming (ASP) rules to guide the hierarchical reinforcement learning (HRL) exploration policy and speed up the learning algorithm’s convergence. When a critical situation occurs, the system relies on safety rules, which empower it to make prudent choices amidst unpredictable or hazardous conditions. GHRL is evaluated on the Carla NoCrash benchmark, and the results show that by incorporating logical rules, GHRL achieved better performance over state-of-the-art algorithms.<\/p>\n","protected":false},"excerpt":{"rendered":" L’Ecole doctorale : Ecole Doctorale de l’Institut Polytechnique de Paris et le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, Mod\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Monsieur Mohamad ALBILANI Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en : […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[286,549],"tags":[],"class_list":["post-6548","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaire-acmes","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6548","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=6548"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6548\/revisions"}],"predecessor-version":[{"id":6549,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6548\/revisions\/6549"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6548"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6548"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6548"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
M. Fawzi NASHASHIBI<\/strong>, Directeur de recherche, Inria, FRANCE – Rapporteur
M. Lounis ADOUANE<\/strong>, Professeur, Universit\u00e9 de Technologie de Compi\u00e8gne, FRANCE – Rapporteur
Mme Maryline LAURENT<\/strong>, Professeure, T\u00e9l\u00e9com SudParis, FRANCE – Examinatrice
M. Philippe XU<\/strong>, Professeur, ENSTA Paris, FRANCE – Examinateur
M. Sascha HORNAUER<\/strong>, Ma\u00eetre de conf\u00e9rences, Mines Paris PSL, FRANCE – Examinateur<\/p>\n\n\n\n\u00ab Apprentissage par renforcement profond neuro-symbolique pour une conduite urbaine s\u00fbre \u00e0 l’aide de capteurs \u00e0 faible co\u00fbt. \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Monsieur Mohamad ALBILANI<\/h2>\n\n\n\n