[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86148-en":3,"doc-seo-86148-105":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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86148,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Comparison-Based Ordinal Learning for Proactive Driving Risk Assessment","Real-time driving risk assessment underpins proactive road safety by detecting and quantifying danger in ongoing traffic interactions before collisions occur. For automated vehicles, such risk evaluation can be integrated into decision-making and planning to generate risk-aware maneuvers. Because collision data and fine-grained frame-level risk labels are scarce, existing methods often use surrogate objectives that may misalign with true collision risk. This work proposes comparison-based ordinal risk learning from pairwise supervision, improving proactive collision warning effectiveness across datasets and settings.","Comparison-Based Ordinal Learning for Proactive Driving Risk Assessment  \nZhuoren Lia,1 , Yi Zhonga,1 , Weiqi Zhanga , Xinrui Zhanga , Lu Xionga , Chongfeng Weib and Bo Lenga,∗  \na College of Automotive and Energy Engineering, Tongji University, Shanghai, China b James Watt School of Engineering, University of Glasgow, Glasgow, UK  \narXiv :2607 . 11128v1 [ cs .RO] 13 Jul 2026  \nARTICLE INFO  \nKeywords:  \nDriving risk assessment Collision-related risk Ordinal risk learning Road safety  \nAB STRACT  \nReal-time driving risk assessment provides an essential basis for proactive safety by identifying and quantifying the danger of ongoing road interactions before adverse outcomes occur. In automated vehicles, such risk assessment can be further embedded into the decision-making and planning process to guide risk-aware maneuver generation. However, due to the scarcity of collision data and framelevel risk labels, existing driving risk assessment methods often rely on surrogate objectives, which may imperfectly align with true collision risk and not faithfully reflect the relative danger of driving interaction. This paper proposes a comparison-based ordinal risk learning framework that learns collision-relevant risk scores from pairwise supervision in driving data, directly modeling relative risk ordering without requiring numerical frame-level risk labels. We derive pairwise comparisons from three sources of event-structured driving data for such ordinal risk learning: temporal progression within safety-critical sequences, event-level contrast between dangerous and normal interactions, and physics-based counterfactual perturbations. On this basis, instantiations with three risk-scoring function parameterizations are implemented, including directly learning risk scores from comparison data, and aligning existing single or multiple surrogate-based risk models. The proposed framework is evaluated on the 100-Car and SHRP2 naturalistic driving datasets using a proactive collision warning task. Results show that the proposed framework improves high-recall risk discrimination, warning precision, and warning lead time over representative surrogate-based baselines across both in-distribution and out-of-distribution evaluations. These results suggest that the proposed framework can contribute to proactive safety research by providing more reliable risk assessment for automated driving systems and safety-critical driving interactions.  \n1. Introduction  \nRoad traffic crashes remain a major global public health challenge, causing approximately 1.19 million deaths annually worldwide (World Health Organization, 2023) . Unlike reactive safety analysis, which primarily explains crashes after they occur, proactive driving risk assessment aims to identify potentially dangerous traffic interactions in real time and support early intervention before they escalate into collisions (Wang et al., 2021) . These capabilities are essential fora wide range of applications, for example Advanced DriverAssistance Systems (ADAS), high-level autonomous driving systems, infrastructure design and operations (Jiao et al., 2026b; Jin et al., 2026) .  \nThe fundamental challenge is that collision risk is a latent, future-oriented quantity rather than a directly observable frame-level label. However, collision events are rare in naturalistic driving; even large-scale studies such as the 100-Car Naturalistic Driving Study (NDS) (Dingus et al., 2006) contain only a limited number of crashes and nearcrashes among millions of recorded miles. Consequently, assigning a reliable numerical risk score to every driving moment would require dense, fine-grained supervision that is generally unavailable in naturalistic datasets.  \n∗Corresponding author  \n [lengbo@tongji.edu.cn](lengbo@tongji.edu.cn) (B. Leng)  \n1These authors contributed equally to this work.  \nThese difficulties have led much of the research to rely on surrogate objectives that estimate collision risk indirectly. Existi","cbCaiefqq0qLoDyi","https://ap.wps.com/l/cbCaiefqq0qLoDyi","pdf",2215828,4,1,15,"English","en",105,"# Introduction\n## Motivation and problem setting\n## Limitations of surrogate objectives\n## Proposed comparison-based ordinal framework","[{\"question\":\"Why is proactive driving risk assessment important for automated driving systems?\",\"answer\":\"It identifies and quantifies potentially dangerous interactions in real time, enabling early intervention and guiding risk-aware maneuver generation before adverse outcomes occur.\"},{\"question\":\"What key challenge prevents direct learning of collision risk from naturalistic driving data?\",\"answer\":\"Collision events and near-crashes are rare, and reliable numerical risk scores for every moment would require dense frame-level supervision that naturalistic datasets typically lack.\"},{\"question\":\"How does the proposed comparison-based ordinal learning framework avoid needing numerical frame-level risk labels?\",\"answer\":\"It learns relative risk ordering from pairwise supervision derived from event-structured driving data sources, modeling comparison-based risk scores without requiring numerical frame-level labels.\"}]",1784208923,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"comparison-based-ordinal-learning-for-proactive-driving-risk-assessment","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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":20},"https://docshare.wps.com/document/comparison-based-ordinal-learning-for-proactive-driving-risk-assessment/86148/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",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},"Why is proactive driving risk assessment important for automated driving systems?","Question",{"text":75,"@type":76},"It identifies and quantifies potentially dangerous interactions in real time, enabling early intervention and guiding risk-aware maneuver generation before adverse outcomes occur.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What key challenge prevents direct learning of collision risk from naturalistic driving data?",{"text":80,"@type":76},"Collision events and near-crashes are rare, and reliable numerical risk scores for every moment would require dense frame-level supervision that naturalistic datasets typically lack.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed comparison-based ordinal learning framework avoid needing numerical frame-level risk labels?",{"text":84,"@type":76},"It learns relative risk ordering from pairwise supervision derived from event-structured driving data sources, modeling comparison-based risk scores without requiring numerical frame-level labels.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"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":20,"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"]