[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120459-en":3,"doc-seo-120459-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120459,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Machine Learning in Feedback Systems - Provable Methods for Safe and Robust Autonomy","This dissertation investigates integrating machine learning into feedback control systems for autonomous navigation, focusing on safety and reliability in safety-critical settings. It addresses limitations of deep learning in handling uncertainty and the constraints of traditional control theory under complex environments with unknown uncertainties. It develops theoretical and practical methods that combine robust and optimal control with machine learning: finite-time data-driven controller design and perception-aware control using robust handling of state-dependent perception errors.","©Copyright 2024 Niyousha Rahimi  \nMachine Learning in Feedback Systems: Provable Methods for Safe and Robust Autonomy  \nNiyousha Rahimi  \nA dissertation  \nsubmitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nUniversity of Washington  \n2024  \nReading Committee:  \nMehran Mesbahi, Chair  \nBeh¸cet A¸cıkme¸se  \nKaren Leung  \nAmir Taghvaei  \nProgram Authorized to Offer Degree: Aeronautics and Astronautics Engineering  \nUniversity of Washington  \nAbstract  \nMachine Learning in Feedback Systems:  \nProvable Methods for Safe and Robust Autonomy  \nNiyousha Rahimi  \nChair of the Supervisory Committee:  \nMehran Mesbahi  \nWilliam E. Boeing Department of Aeronautics and Astronautics  \nThis dissertation explores the integration of machine learning into feedback control systems, addressing key challenges in the realm of control theory with a focus on autonomous navigation. Modern advances in sensing technologies and computational methods have enabled remarkable advancements in data-guided control. However, the reliability of machine learning, particularly deep learning, in safety-critical applications remains limited due to its inadequate handling of uncertainty. Furthermore, traditional methods in control theory impose limitations when the system is operating in complex environments with unknown uncertainties. This research seeks to bridge this gap by combining robust and optimal control techniques with machine learning to ensure reliable automated system behavior.  \nPart I of the dissertation establishes a theoretical framework for the data-driven design of optimal controllers inspired by autonomous physical systems. It investigates the online regulation of both linear and nonlinear systems that are possibly unstable and partially unknown. A significant contribution of this part is the introduction of the concept of“regularizability,” which characterizes the extent by which a system can be regulated in finite time, offering a new perspective on system behavior compared to traditional stabilizability and controllability. This theoretical exploration challenges conventional understandings and provides novel insights into finite time regulation versus asymptotic behavior.  \nPart II addresses the practical application of deep learning algorithms in processing high-dimensional data and generating a spectrum of outputs in automatic feedback control. The inherent challenge in this context is modeling uncertainties in the output, especially when these trained neural networks are employed as perception modules within control loops for autonomous navigation. To mitigate this, the dissertation introduces a novel approach utilizing a perception map as an approximate inverse. This perception-control loop demonstrates commendable attributes, provided that the controller is robustly designed to accommodate for the perception errors. The novelty of this part lies in developing methods to ensure robustness against state-dependent perception errors, thus contributing to more reliable machine learning applications in feedback control systems.  \nTable of Contents  \nPage  \nList of Figures ....................................... iv  \nGlossary ........................................... vii  \nChapter 1: Introduction ................................ 1  \n1.1 Statement of Contributions ........................... 1  \n1.2 Outline of Dissertation .............................. 2  \n1.3 Included Publications ............................... 4  \nChapter 2: Background ................................. 5  \n2.1 Linear Algebra .................................. 5  \n2.2 Optimal Control Problems ............................ 7  \n2.3 Linear Quadratic Regulator ........................... 9  \n2.4 Nonlinear Dynamical Systems .......................... 10  \n2.4.1 Quadratic Funnel Synthesis ....................... 12  \nChapter 3: Machine Learning in Feedback systems .................. 15  \n3.1 The Evolution of Learning in Feedback Systems ...","cbCaiauwFIGI8ceu","https://ap.wps.com/l/cbCaiauwFIGI8ceu","pdf",8923629,1,152,"English","en",105,"# Chapter 1: Introduction\n## 1.1 Statement of Contributions\n## 1.2 Outline of Dissertation\n## 1.3 Included Publications\n# Chapter 2: Background\n## 2.1 Linear Algebra\n## 2.2 Optimal Control Problems\n## 2.3 Linear Quadratic Regulator\n## 2.4 Nonlinear Dynamical Systems\n# Chapter 3: Machine Learning in Feedback systems\n## 3.1 The Evolution of Learning in Feedback Systems\n## 3.2 Deep Neural Networks as Perception Module\n## 3.3 Simulation Environments\n# Part I: Iterative Data-Driven Control\n# Chapter 4: Online Regulation of Unstable Linear Systems\n## 4.4 Data-Guided Regulation (DGR) Algorithm\n## 4.5 Boosting the Performance of DGR\n# Chapter 5: Data-Guided Regulator for Adaptive Nonlinear Control\n## 5.3 Rapidly-Regularizable Nonlinear Systems\n## 5.4 Data-Guided Regulator for Adaptive Nonlinear Control\n# Part II: Perception-Aware Trajectory Planning and Control\n# Chapter 6: Robust Controller Synthesis for Perception-Based Control\n## 6.2 Nonlinear System Model with State-Dependent Perception Error\n## 6.4 Robus","[{\"question\":\"What core problem does the dissertation target in machine learning for feedback control?\",\"answer\":\"It targets limited reliability of machine learning, especially deep learning, in safety-critical feedback control due to inadequate uncertainty handling, as well as traditional control limitations in complex environments with unknown uncertainties.\"},{\"question\":\"What contribution is introduced in Part I regarding system behavior?\",\"answer\":\"Part I introduces “regularizability,” a concept that characterizes how extensively a system can be regulated in finite time, offering a new viewpoint distinct from stabilizability and controllability.\"},{\"question\":\"How does Part II address uncertainty when neural networks are used in control loops?\",\"answer\":\"It introduces a perception map as an approximate inverse and emphasizes robust controller design to accommodate perception errors, including state-dependent perception errors.\"}]","Machine Learning in Feedback Systems - Provable Methods for Safe and Robust Autonomy | PDF",1785730209,383,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-in-feedback-systems-provable-methods-for-safe-and-robust-autonomy","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-in-feedback-systems-provable-methods-for-safe-and-robust-autonomy/120459/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What core problem does the dissertation target in machine learning for feedback control?","Question",{"text":75,"@type":76},"It targets limited reliability of machine learning, especially deep learning, in safety-critical feedback control due to inadequate uncertainty handling, as well as traditional control limitations in complex environments with unknown uncertainties.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What contribution is introduced in Part I regarding system behavior?",{"text":80,"@type":76},"Part I introduces “regularizability,” a concept that characterizes how extensively a system can be regulated in finite time, offering a new viewpoint distinct from stabilizability and controllability.",{"name":82,"@type":73,"acceptedAnswer":83},"How does Part II address uncertainty when neural networks are used in control loops?",{"text":84,"@type":76},"It introduces a perception map as an approximate inverse and emphasizes robust controller design to accommodate perception errors, including state-dependent perception errors.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]