[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122092-en":3,"doc-seo-122092-105":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},122092,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Utilizing Machine Learning in Collision-free Weld Path Planning - Case study of PEMA WeldControl Robotic Welding Software - Master’s thesis","This master’s thesis investigates how machine learning can be used for collision-free weld path planning for welding robots within Pemamek’s WeldControl software, a 3D weld planning and simulation tool for robot programming. The work emphasizes reinforcement learning algorithms, studied via literature review and experimental research inside WeldControl. Results indicate the approach is not practical in this case due to Windows-only software constraints, limited library availability, and simulation components unsuitable for reinforcement learning. The thesis proposes an integration method for Python ML libraries to support future research.","Noora Pöysti  \nUTILIZING MACHINE LEARNING IN COLLISION-FREE WELD PATH PLANNING  \nCase study of PEMA WeldControl Robotic Welding Software  \nMaster’s thesis  \nFaculty of Information Technology and Communication Sciences Examiners: Prof. Joni Kämäräinen  \nPhD Seppo Leppäjärvi December 2023  \ni  \nABSTRACT  \nNoora Pöysti: Utilizing Machine Learning in Collision-free Weld Path Planning Master’s thesis  \nTampere University  \nMaster’s Programme in Information Technology December 2023  \nThis thesis investigates the application of machine learning methods in collision-free weld path planning for welding robots in Pemamek’s WeldControl software, which is a 3D weld planning and simulation software for programming robots. The main focus is on reinforcement learning algorithms, which have had some success in robot arm motion control in recent years. The topic was investigated through a literature review and by conducting experimental research on the WeldControl software. It was found that the use of machine learning in this particular case is not practical due to several constraints: the software is limited to Windows operating systems, which limits the number of available machine learning software libraries, and the underlying simulation software isnot suitable for reinforcement learning. Additionally, there are inherent challenges with reinforcement learning algorithms, and other collision-free weld path planning approaches were found tobe more efficient. Despite these findings, the thesis presents a method for integrating existing Python machine learning libraries into the WeldControl simulation environment, which facilitates similar works in the future.  \nKeywords: weld path planning, machine learning, reinforcement learning, robotic welding The originality of this thesis has been checked using the Turnitin OriginalityCheck service.  \nii  \nTIIVISTELMÄ  \nNoora Pöysti: Koneoppimisen hyödyntäminen törmäämättömien hitsausratojen laskennassa Diplomityö  \nTampereen yliopisto Tietotekniikan DI-ohjelma Joulukuu 2023  \nTämä diplomityö tutkii koneoppimisen hyödyntämistä törmäämättömien hitsausratojen laskennassa. Työ tutkii aihetta Pemamek yrityksen WeldControl-ohjelmistossa, joka on hitsausrobottien ohjelmointiin tarkoitettu 3D hitsinluonti- ja simulointiohjelmisto. Pääpaino on vahvistusoppimisalgoritmeissa, jotka ovat viime vuosina olleet suosittu tutkimuskohde robottikäsivarsien liikeratojen ohjauksessa. Aihetta tutkittiin systemaattisen kirjallisuuskatsauksen menetelmiä käyttäen sekä tekemällä kokeellisia tutkimuksia WeldControl-ohjelmistolla. Kävi ilmi, että koneoppimisenkäyttö tässä tapauksessa ei ole käytännöllistä useiden rajoitteiden takia: ohjelmisto on rajoitettu Windows-käyttöjärjestelmiin, mikä rajoittaa saatavilla olevien koneoppimisohjelmistokirjastojen määrää, eikä taustalla oleva simulaatio-ohjelmisto sovellu vahvistusoppimiseen. Lisäksi vahvistusoppimisalgoritmeihin liittyy toistaiseksi ratkaisemattomia haasteita, ja muut lähestymistavat törmäämättömien hitsausratojen laskentaan osoittautuivat tehokkaammiksi. Näistä löydöksistä huolimatta, työ esittää menetelmän, jolla olemassa olevat Python koneoppimiskirjastot voidaan integroida WeldControl-simulaatioympäristöön, mikä mahdollistaa vastaavien tutkimuksien toteuttamisen tulevaisuudessa.  \nAvainsanat: hitsausratojen suunnittelu, koneoppiminen, vahvistusoppiminen, robottihitsaus  \nTämän julkaisun alkuperäisyys on tarkastettu Turnitin OriginalityCheck-ohjelmalla.  \niii  \nPREFACE  \nI would like to thank Pemamek Oy for providing me with an interesting thesis topic. Before starting this project, the field of robotics was a mystery to me, and now I can confidently say that I know a little bit about it. I also want to thank my co-workers for their assistance in answering my questions about robots and robotic welding  \nSpecial thanks to my friends and family for their support, and for continually motivating me throughout the past five years of my studies at Tampere University.  \nTampere,","cbCaiqs2jQiTKAi4","https://ap.wps.com/l/cbCaiqs2jQiTKAi4","pdf",3410310,1,64,"English","en",105,"# Introduction\n# Related Work\n## Sampling-based Path Planning Algorithms\n## Use of Machine Learning in Collision-free Path Planning\n## Popular Reinforcement Learning Methods in Path Planning\n## Reinforcement Learning Path Planning Challenges\n# Theoretical Background\n## Robot Manipulator Kinematics\n## Artificial Neural Networks\n## Reinforcement Learning\n# Case Pemamek\n## PEMA WeldControl Software\n## Constraints Imposed by the Existing Software\n# Methods\n## Integrating Python Machine Learning Libraries into WeldControl\n## Reinforcement Learning Approach to Weld Path Planning\n## Using Other 3D Simulation Software for Path Planning","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis studies applying machine learning to compute collision-free weld paths for welding robots using Pemamek’s WeldControl software.\"},{\"question\":\"Why was reinforcement learning not practical in this WeldControl case?\",\"answer\":\"Key constraints include the Windows-only environment limiting available ML libraries, and the underlying simulation setup not being suitable for reinforcement learning.\"},{\"question\":\"What solution does the thesis propose despite the limitations?\",\"answer\":\"It presents a method to integrate existing Python machine learning libraries into the WeldControl simulation environment to enable similar future research.\"}]","Utilizing Machine Learning in Collision-free Weld Path Planning - Case study of PEMA WeldControl Robotic Welding Software - Master’s thesis | PDF",1785808778,161,{"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},"utilizing-machine-learning-in-collision-free-weld-path-planning-case-study-of-pema-weldcontrol-robotic-welding-software-masters-thesis","",{"@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/utilizing-machine-learning-in-collision-free-weld-path-planning-case-study-of-pema-weldcontrol-robotic-welding-software-masters-thesis/122092/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis studies applying machine learning to compute collision-free weld paths for welding robots using Pemamek’s WeldControl software.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why was reinforcement learning not practical in this WeldControl case?",{"text":80,"@type":76},"Key constraints include the Windows-only environment limiting available ML libraries, and the underlying simulation setup not being suitable for reinforcement learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What solution does the thesis propose despite the limitations?",{"text":84,"@type":76},"It presents a method to integrate existing Python machine learning libraries into the WeldControl simulation environment to enable similar future research.","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"]