[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121221-en":3,"doc-seo-121221-105":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},121221,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Automatic Bucket Filling for Wheel Loaders - A Machine Learning Approach","The bucket filling task for wheel loaders is a highly repetitive cycle work that is also one of the most difficult for operators, typically requiring years of experience for efficient performance. With labor shortages approaching in the heavy-duty industry, automating bucket filling can lower the entry barrier for new operators through reduced training needs while improving productivity and potentially reducing fuel consumption. The thesis addresses the core challenge: interaction forces between pile and bucket are uncertain and hard to model. A machine learning approach learns these dynamics from expert-recorded data. The work investigates imitation learning, transfer learning, and reinforcement learning, plus a method to extract tasks from long time-series.","DANIEL ERIKSSON  \nAutomatic Bucket Filling for Wheel Loaders  \nA Machine Learning Approach  \nTampere University Dissertations 1100  \nTampere University Dissertations 1100  \nDANIEL ERIKSSON  \nAutomatic Bucket Filling for Wheel Loaders A Machine Learning Approach  \nACADEMIC DISSERTATION To be presented, with the permission of the Faculty of Engineering and Natural Sciences of Tampere University, for public discussion in the auditorium TB109 of the Tietotalo building, Korkeakoulunkatu 1, Tampere, on 1 November 2024, at 12 o’clock.  \nACADEMIC DISSERTATION  \nTampere University, Faculty of Engineering and Natural Sciences Finland  \nResponsible supervisor and Custos  \nSupervisors  \nPre-examiners  \nProfessor Reza Ghabcheloo Tampere University Finland  \nProfessor Marcus Geimer Karlsruhe Institute of Technology Germany  \nAssociate Professor Martin Servin Umeå University  \nSweden  \nDr. Manuel Bös  \nLiebherr-Werk Bischofshofen GmbH Austria  \nProfessor Ville Kyrki Aalto University Finland  \nOpponent Professor Rauno Heikkilä  \nUniversity of Oulu  \nFinland  \nThe originality of this thesis has been checked using the Turnitin OriginalityCheck service.  \nCopyright ©2024 Daniel Eriksson Cover design: Roihu Inc.  \nISBN 978-952-03-3619-6 (print)  \nISBN 978-952-03-3620-2 (pdf)  \nISSN 2489-9860 (print)  \nISSN 2490-0028 (pdf)  \n[http://urn.fi/URN:ISBN:978-952-03-3620-2](http://urn.fi/URN:ISBN:978-952-03-3620-2)  \nCarbon dioxide emissions from printing Tampere University dissertationshave been compensated.  \nPunaMusta Oy – Yliopistopaino Joensuu 2024  \nPREFACE  \nThe research presented in this thesis was funded by the MORE project, an EU project that connects academia and industry and trains tomorrows researchers with a focus on heavy-duty mobile machines. For me this meant that I spent most of my time at Liebherr in Austria, and I appreciate all the wonderful colleagues there who have helped with technical problems and taught me a lot.  \nI also want to give a big thanks my main supervisor Professor Reza Ghabcheloo, my second supervisor Professor Marcus Geimer, and finally my industry supervisor Dr. Manuel Bös. They have provided many insightful discussions and guidance during the process and steered my path to stay on track for finalizing the PhD. The path has not always been straight and there were many changes since the beginning of the project. I want to especially thank Reza and Marcus for resolving the issues that arose early in the project and the swift solution to them.  \nI am also grateful for the other PhD students in the MORE project, it has been interesting to learn about your work and getting to know all of you when we could finally meet after the pandemic.  \nFinally, I also want to thank all the amazing people I have met and the friends I have gained on this journey. I want to thank them for all the adventures, the hiking, the skiing, and me bothering them with reading my articles. And of course I also want to thank my family for all the support they have given me during the years. I would not have made it without them.  \nThis project received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 858101.  \nABSTRACT  \nThe bucket filling task for wheel loaders is one of the most common tasks, which is normally repeated in cycles during a work shift. It is also the most difficult task for the operator; they need years of experience to do it efficiently. These facts, combined with the impending labor shortage in the industry, make this task compelling for automation. Automating the bucket filling task will lower the barrier-of-entry for new operators by making them more efficient with less training. Additionally, automating the bucket filling task has the potential to increase productivity at a worksite and reduce fuel consumption.  \nThere are several reasons that make bucket filling a challenging automation problem. The biggest one is the interaction forces between the pile a","cbCainpvDINjhY3u","https://ap.wps.com/l/cbCainpvDINjhY3u","pdf",24445805,1,137,"English","en",105,"# Preface\n# Abstract\n## Bucket filling as an automation target\n## Key challenges and learning-based solution\n## Thesis goals and research methods\n## Summary of experimental results\n## Surrogate simulation for reinforcement learning\n# Conclusion","[{\"question\":\"Why is automating the bucket filling task for wheel loaders important?\",\"answer\":\"Bucket filling is common and highly repetitive, yet difficult for operators and requires extensive experience. Automation can reduce training effort for new operators, increase worksite productivity, and help reduce fuel consumption.\"},{\"question\":\"What makes bucket filling a challenging automation problem?\",\"answer\":\"The main difficulty is the interaction forces between the pile and the wheel loader’s bucket. These forces are hard to model due to uncertainties in material properties.\"},{\"question\":\"What machine learning approaches does the thesis use?\",\"answer\":\"The thesis investigates imitation learning, transfer learning, and reinforcement learning. It also develops an algorithm for extracting bucket filling from long time-series data and includes a surrogate simulator for reinforcement learning optimization.\"}]","Automatic Bucket Filling for Wheel Loaders - A Machine Learning Approach | PDF",1785734424,345,{"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},"automatic-bucket-filling-for-wheel-loaders-a-machine-learning-approach","",{"@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/automatic-bucket-filling-for-wheel-loaders-a-machine-learning-approach/121221/",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},"Why is automating the bucket filling task for wheel loaders important?","Question",{"text":75,"@type":76},"Bucket filling is common and highly repetitive, yet difficult for operators and requires extensive experience. Automation can reduce training effort for new operators, increase worksite productivity, and help reduce fuel consumption.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes bucket filling a challenging automation problem?",{"text":80,"@type":76},"The main difficulty is the interaction forces between the pile and the wheel loader’s bucket. These forces are hard to model due to uncertainties in material properties.",{"name":82,"@type":73,"acceptedAnswer":83},"What machine learning approaches does the thesis use?",{"text":84,"@type":76},"The thesis investigates imitation learning, transfer learning, and reinforcement learning. It also develops an algorithm for extracting bucket filling from long time-series data and includes a surrogate simulator for reinforcement learning optimization.","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"]