[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123937-en":3,"doc-seo-123937-105":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":20,"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},123937,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Towards automated PCB routing - Leveraging machine learning and heuristic techniques - Doctoral dissertation","This dissertation advances automated printed circuit board (PCB) routing by combining machine learning with heuristic search. The research studies routing challenges and reviews existing escape, area, and complete routing approaches. It introduces an MCTS and deep reinforcement learning framework for routing via trained rollout policies, DRL backtracking, and path pruning, then evaluates performance on real-world circuits. A pad-focused routing algorithm further integrates polygon-based dynamic partitioning with MCTS, plus A*-based detailed routing, rip-up and reroute, and post-processing. Finally, the PCBench dataset and an RL environment enable benchmarking and learning-driven routing progress.","Towards automated PCB routing: Leveraging machine learning and heuristic techniques  \nby  \nYoubiao He  \nA thesis submitted to the graduate faculty  \nin partial fulfillment of the requirements for the degree of  \nDOCTOR OF PHILOSOPHY  \nMajor: Computer Science  \nProgram of Study Committee:  \nForrest Sheng Bao, Major Professor  \nSamik Basu  \nJin Tian  \nWensheng Zhang  \nMai Zheng  \nThe student author, whose presentation of the scholarship herein was approved by the program of study committee, is solely responsible for the content of this dissertation. The Graduate College will ensure this dissertation is globally accessible and will not permit alterations after a degree is conferred.  \nIowa State University  \nAmes, Iowa  \n2024  \nCopyright © Youbiao He, 2024 . All rights reserved.  \nii  \nTABLE OF CONTENTS  \nPage  \nLIST OF TABLES   iv  \nLIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v  \nABSTRACT ................................................ viii  \nCHAPTER 1 . GENERAL INTRODUCTION .............................. 1  \n1.1 Background ........................................... 1  \n1.1.1 Overview of PCB .................................... 1  \n1.1.2 PCB design ....................................... 2  \n1.1.3 PCB routing ...................................... 4  \n1.2 Challenges ............................................ 6  \n1.3 Overiew of Research Works .................................. 7  \n1.3.1 PCB routing using Monte Carlo tree search and deep reinforcement learning .... 7  \n1.3.2 A pad-focused PCB routing algorithm using polygon-based dynamic partitioning and MCTS .......................................... 8  \n1.3.3 PCBench: a dataset for printed circuit board routing ................. 8  \n1.4 Criteria Review ......................................... 9  \n1.4.1 Escape Routing ..................................... 9  \n1.4.2 Area Routing ...................................... 10  \n1.4.3 Complete PCB Routing Approaches .......................... 11  \n1.5 References ............................................ 12  \nCHAPTER 2. PCB ROUTING USING MONTE CARLO TREE SEARCH AND DEEP REINFORCEMENT LEARNING ..................................... 16  \n2.1 Abstract ............................................. 16  \n2.2 Introduction ........................................... 16  \n2.3 Background ........................................... 18  \n2.3.1 Deep reinforcement learning .............................. 19  \n2.3.2 Monte Carlo tree search ................................ 21  \n2.4 Problem Statement ....................................... 23  \n2.5 Methods ............................................. 23  \n2.5.1 Overview ........................................ 23  \n2.5.2 MCTS approach for routing .............................. 24  \n2.5.3 DRL-based rollout policy training ........................... 26  \n2.5.4 DRL-backtracking rollout ............................... 29  \n2.5.5 Path pruning ...................................... 30  \n2.5.6 DRL-MCTS algorithm ................................. 31  \niii  \n2.6 Experimental Results and Analysis ............................... 33  \n2.6.1 Our approach vs. baselines ............................... 33  \n2.6.2 On real-world circuits ................................. 36  \n2.6.3 Flexibility analysis ................................... 37  \n2.7 Conclusions ........................................... 41  \n2.8 References ............................................ 41  \nCHAPTER 3. A PAD-FOCUSED PCB ROUTING ALGORITHM USING POLYGON-BASED DYNAMIC PARTITIONING AND MCTS .............................. 44  \n3.1 Abstract ............................................. 44  \n3.2 Introduction ........................................... 44  \n3.3 Background and Related Work ................................. 47  \n3.4 Problem Formulation ...................................... 48  \n3.5 Methodology .......................................... 48  \n3.5.1 Overview ..............","cbCaikjMuKMWxkPa","https://ap.wps.com/l/cbCaikjMuKMWxkPa","pdf",1587971,1,100,"English","en",105,"# Table of contents\n## List of tables\n## List of figures\n## Abstract\n## CHAPTER 1 - General introduction\n### Background\n### Challenges\n### Overview of research works\n### Criteria review\n### References\n## CHAPTER 2 - PCB routing using Monte Carlo tree search and deep reinforcement learning\n### Introduction\n### Background\n### Problem statement\n### Methods\n### Experimental results and analysis\n### Conclusions\n### References\n## CHAPTER 3 - A pad-focused PCB routing algorithm using polygon-based dynamic partitioning and MCTS\n### Introduction\n### Background and related work\n### Problem formulation\n### Methodology\n### Experiments\n### Conclusions\n### References\n## CHAPTER 4 - PCBench: a dataset for printed circuit board routing\n### Introduction\n### Related work\n### Curating the PCBench dataset\n### Needing data for Machine Learning?\n### RL environment for PCB routing\n### Benchmarking the SOTA\n### Conclusion\n### References\n### Appendix: RL state transition and environment implementation\n## CHAPTER 5 - General conclusions\n### References","[{\"question\":\"What problem does this dissertation address?\",\"answer\":\"It addresses automated printed circuit board (PCB) routing, focusing on how to generate high-quality routing solutions efficiently despite routing complexity and constraints.\"},{\"question\":\"How does the thesis use Monte Carlo tree search and deep reinforcement learning?\",\"answer\":\"It presents a DRL-trained rollout policy integrated with MCTS, including DRL backtracking rollout and path pruning, to guide routing decisions and improve search effectiveness.\"},{\"question\":\"What is the PCBench dataset for?\",\"answer\":\"PCBench supplies data and representations (via a PCB Routing Description Language) together with an RL environment so that learning-based routing methods can be benchmarked and compared.\"}]","Towards automated PCB routing - Leveraging machine learning and heuristic techniques - Doctoral dissertation | PDF",1785819334,252,{"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},"towards-automated-pcb-routing-leveraging-machine-learning-and-heuristic-techniques-doctoral-dissertation","",{"@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/towards-automated-pcb-routing-leveraging-machine-learning-and-heuristic-techniques-doctoral-dissertation/123937/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does this dissertation address?","Question",{"text":75,"@type":76},"It addresses automated printed circuit board (PCB) routing, focusing on how to generate high-quality routing solutions efficiently despite routing complexity and constraints.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis use Monte Carlo tree search and deep reinforcement learning?",{"text":80,"@type":76},"It presents a DRL-trained rollout policy integrated with MCTS, including DRL backtracking rollout and path pruning, to guide routing decisions and improve search effectiveness.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the PCBench dataset for?",{"text":84,"@type":76},"PCBench supplies data and representations (via a PCB Routing Description Language) together with an RL environment so that learning-based routing methods can be benchmarked and compared.","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"]