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 MARDI 17 D\u00e9CEMBRE 2024 \u00e0 10h00<\/p>\n\n\n\n
\u00e0<\/p>\n\n\n\n
nouvelle salle E005<\/strong> Membres du jury :<\/strong><\/p>\n\n\n\n M. Titus ZAHARIA<\/strong>, Professeur, T\u00e9l\u00e9com SudParis, FRANCE – Directeur de these R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n Cette th\u00e8se \u00e9tudie l\u2019automatisation de machines industrielles de 25 tonnes, en se concentrant sur la mod\u00e9lisation, le contr\u00f4le et la supervision d’une pelleteuse. Les engins de terrassement utilis\u00e9s dans l’industrie sont souvent en mauvais \u00e9tat et manquent les capteurs n\u00e9cessaires pour un contr\u00f4le pr\u00e9cis, limitant le d\u00e9ploiement des syst\u00e8mes autonomes fonctionnels en laboratoire. Nous proposons d\u2019adapter les m\u00e9thodologies aux conditions industrielles pour surmonter ces limitations. Nous commen\u00e7ons par identifier la dynamique du bras de la pelleteuse avec un r\u00e9seau de neurones, d\u00e9pla\u00e7ant le d\u00e9fi de l’instrumentation vers celui de la mod\u00e9lisation. Notre approche combine les m\u00e9thodes de l’\u00e9tat de l’art pour entra\u00eener un mod\u00e8le capable de pr\u00e9dire le mouvement r\u00e9el du bras pendant plus d\u2019une minute. Ensuite, nous \u00e9tudions diff\u00e9rents contr\u00f4leurs : des r\u00e9gulateurs PID classiques, des contr\u00f4leurs pr\u00e9dictifs (MPC) et des algorithmes d\u2019apprentissage profond par renforcement (DRL). Nos r\u00e9sultats montrent le potentiel du DRL, en simulation, atteignant 25 cm d’erreur de suivi d\u2019une trajectoire de remplissage du godet \u00e0 50 cm\/s. Enfin, nous d\u00e9ployons un de nos contr\u00f4leurs sur une pelleteuse r\u00e9elle et dotons les op\u00e9rateurs de terrain d\u2019outils de supervision, dont une interface de t\u00e9l\u00e9-op\u00e9ration en r\u00e9alit\u00e9 virtuelle (VR). Ces outils permettent de g\u00e9rer une flotte de machines autonomes et notre \u00e9tude sur 12 participants d\u00e9montre que tout op\u00e9rateur, m\u00eame novice, peut efficacement t\u00e9l\u00e9-op\u00e9rer une pelleteuse sans endommager la machine. Ces travaux contribuent \u00e0 l’automatisation croissante des machines dans le domaine de la construction, ouvrant la voie \u00e0 des op\u00e9rations plus efficaces et rentables. This thesis studies the automation of 25-ton industrial machinery, focusing on modeling, control, and supervising an excavator. The earthmoving machines used in the industry are often in poor condition and lack the necessary sensors for precise control, limiting the deployment of functional autonomous systems in the laboratory. We propose adapting methodologies to industrial conditions to overcome these limitations. We begin by identifying the dynamics of the excavator arm using a neural network, shifting the challenge from instrumentation to modeling. Our approach combines state-of-the-art methods to train a model capable of predicting the real movement of the arm for over a minute. Next, we study different controllers: classical PID regulators, predictive controllers (MPC), and deep reinforcement learning (DRL) algorithms. Our results demonstrate the potential of DRL in simulation, achieving 25 cm tracking error for a bucket-filling trajectory at 50 cm\/s. Finally, we deploy one of our controllers on a real excavator and provide field operators with supervision tools, including a virtual reality (VR) teleoperation interface. These tools allow managing a fleet of autonomous machines, and our study involving 12 participants shows that any operator, even a novice, can effectively teleoperate an excavator without damaging the machine. This work contributes to the increasing automation of construction machinery, paving the way for more efficient and cost-effective operations.<\/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 Nicolas HOFFMANN 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":"open","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":[286,169],"tags":[],"class_list":["post-6717","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaires-armedia","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6717","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=6717"}],"version-history":[{"count":2,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6717\/revisions"}],"predecessor-version":[{"id":6736,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6717\/revisions\/6736"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6717"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6717"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6717"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
9 Rue Charles Fourier, b\u00e2timent ETOILE, 91011 Evry<\/p>\n\n\n\n
M. Bertrand DELEZOIDE<\/strong>, Professeur associ\u00e9, UNIVERSITE PARIS SACLAY, FRANCE – Rapporteur
M. Constantin VERTAN<\/strong>, Professeur, Universit\u00e9 Politehnica de Bucarest, ROUMANIE – Rapporteur
Mme Maria TROCAN<\/strong>, Professeure, ISEP Paris, FRANCE – Examinateur
M. Marius PREDA<\/strong>, Ma\u00eetre de conf\u00e9rences, T\u00e9l\u00e9com SudParis, FRANCE – Co-encadrant de these
M. Jean-Yves DIDIER<\/strong>, Professeur, Universit\u00e9 d’Evry Paris Saclay, FRANCE – Examinateur<\/p>\n\n\n\n\u00ab Mod\u00e9lisation et contr\u00f4le bas\u00e9s sur les donn\u00e9es pour l’automatisation des engins industriels faiblement instrument\u00e9es. \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Monsieur Nicolas HOFFMANN<\/h2>\n\n\n\n
Abstract :<\/strong><\/p>\n\n\n\n