[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122281-en":3,"doc-seo-122281-105":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},122281,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Safety Assurance of Machine Learning for Autonomous Systems","Machine learning (ML) components are increasingly embedded in systems across healthcare, transport, and manufacturing, often reporting performance that matches or exceeds human expert capabilities. This shift can improve service quality, reduce costs, and enhance delivery effectiveness, particularly when expert resources are scarce. For safety-critical autonomous applications, adoption depends on establishing justified confidence in overall system safety. Building a safety case for ML is challenging because ML lifecycles differ from traditional software assurance, motivating a new methodology and evidence generation approach.","This is a repository copy of Safety assurance of Machine Learning for autonomous systems.  \nWhite Rose Research Online URL for this paper:  \n[https://eprints.whiterose.ac.uk/228098/](https://eprints.whiterose.ac.uk/228098/)  \n[Version: Accepted Version](Version: Accepted Version)  \nArticle:  \nPaterson, Colin [orcid.org/0000-0002-6678-3752](orcid.org/0000-0002-6678-3752) , Hawkins, Richard David [orcid.org/0000-](orcid.org/0000-)[ ](orcid.org/0000-)[0001-7347-3413](0001-7347-3413) , Picardi, Chiara et al. (3 more authors) (2025) Safety assurance of Machine Learning for autonomous systems. Reliability Engineering and System Safety.  \n111311. ISSN 0951-8320  \n[https://doi.org/10.1016/j.ress.2025.111311](https://doi.org/10.1016/j.ress.2025.111311)  \nReuse  \nThis article is distributed under the terms of the Creative Commons Attribution (CC BY) licence. This licence allows you to distribute, remix, tweak, and build upon the work, even commercially, as long as you credit the authors for the original work. More information and the full terms of the licence here: [https://creativecommons.org/licenses/](https://creativecommons.org/licenses/)  \nTakedown  \nIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by  \nemailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request.  \n[eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/)  \nSafety Assurance of Machine Learning for Autonomous Systems  \nColin Patersona , Richard Hawkinsa , Chiara Picardia , Yan Jiaa , Radu Calinescua , Ibrahim Hablia  \na Department of Computer Science, University of York, Heslington, York, YO10 5GH, United Kingdom  \nAbstract  \nMachine Learning (ML) components are increasingly incorporated into systems, with di􀀋erent degrees of autonomy, where model performance is reported as meeting, or exceeding, the capabilities of human experts. This promises to transform products and services, in diverse domains such as healthcare, transport and manufacturing, to better serve underrepresented groups, reduce costs, and increase delivery e􀀋ectiveness, especially where expert resources are scarce. The greatest potential for transformative impact lies in the development of autonomous systems for safety-critical applications where their acceptance, and subsequent deployment, is reliant on establishing justi􀀂ed con􀀂dence in system safety. Creating a compelling safety case for ML is challenging however, particularly since the ML development lifecycle is signi􀀂cantly di􀀋erent to that employed for traditional software systems. Typically ML development involves replacing detailed software speci􀀂cations with representative data sets from which models of behaviour is learnt. Indeed, ML’s strength lies in tackling problems which are challenging for traditional software development practices. This shift in development practices introduces challenges to established assurance processes which are crucial to developing the compelling safety case required for regulation and societal acceptance. In this paper we introduce the 􀀂rst methodology for the Assurance of Machine Learning for use in Autonomous Systems (AMLAS) . The AMLAS process describes how to systematically and attractively integrate safety assurance into the development of ML components and how to generate the evidence base for explicitly justifying the acceptable safety of these components when integrated into autonomous system applications. We describe the use of AMLAS by considering how a safety case may be constructed for an object detector for use in the perception pipeline of an autonomous driving application. We further discuss how AMLAS has been applied in several domains including healthcare, automotive and aerospace as well as supporting policy and industry guidance for defence, healthcare and automotive.  \nKeywords: Ma","cbCaikBDOtRDNDuI","https://ap.wps.com/l/cbCaikBDOtRDNDuI","pdf",653510,1,28,"English","en",105,"# Introduction\n## Background and motivation\n## Why traditional software assurance is insufficient\n# AMLAS methodology\n## Evidence generation for safety justification\n## Integrating safety assurance into ML development\n# Case study: object detector in autonomous driving\n## Constructing a safety case in the perception pipeline\n# Applications and guidance\n## Domains: healthcare, automotive, aerospace\n## Supporting policy and industry guidance","[{\"question\":\"Why is safety assurance critical for machine learning in autonomous systems?\",\"answer\":\"ML failures in safety-related roles can compromise system safety and cause accidents. Adoption therefore requires confidence that ML will be safe before deployment.\"},{\"question\":\"What makes ML safety assurance different from traditional software assurance?\",\"answer\":\"ML development replaces detailed specifications with representative datasets used to learn model behavior. This introduces challenges to established assurance processes that rely on traditional lifecycle artifacts.\"},{\"question\":\"What does the AMLAS methodology provide?\",\"answer\":\"AMLAS describes how to systematically and effectively integrate safety assurance into ML development and generate an evidence base to justify acceptable safety when ML components are used in autonomous system applications.\"}]","Safety Assurance of Machine Learning for Autonomous Systems | PDF",1785809806,71,{"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},"safety-assurance-of-machine-learning-for-autonomous-systems","",{"@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/safety-assurance-of-machine-learning-for-autonomous-systems/122281/",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},"Why is safety assurance critical for machine learning in autonomous systems?","Question",{"text":75,"@type":76},"ML failures in safety-related roles can compromise system safety and cause accidents. Adoption therefore requires confidence that ML will be safe before deployment.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes ML safety assurance different from traditional software assurance?",{"text":80,"@type":76},"ML development replaces detailed specifications with representative datasets used to learn model behavior. This introduces challenges to established assurance processes that rely on traditional lifecycle artifacts.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the AMLAS methodology provide?",{"text":84,"@type":76},"AMLAS describes how to systematically and effectively integrate safety assurance into ML development and generate an evidence base to justify acceptable safety when ML components are used in autonomous system applications.","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"]