[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82978-en":3,"doc-seo-82978-105":29,"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":13,"seo_description":14,"update_tm":27,"read_time":28},82978,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Uncertainty Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba","Reliable localization in GNSS-denied environments remains a core requirement for intelligent vehicles because inertial navigation accumulates unbounded drift without external correction. Existing drift-correction methods rely on dedicated infrastructure, costly external sensors, or complex fusion, which hinders practical deployment. Evidential Velocity Correction using Mamba (EVC-Mamba) converts onboard sensor streams into a virtual velocity sensor for IMU drift correction. A Mamba-based selective state space model captures motion dynamics, while evidential learning with a Normal-Inverse-Gamma prior quantifies uncertainty. The result is fused as a virtual measurement into an Error-State EKF to reduce position drift, achieving localization within 10% of an external velocity sensor and supporting 40 Hz onboard real-time operation.","Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba  \nAbinav Kalyanasundaram 1 , Karthikeyan Chandra Sekaran 1 , Wolfgang Utschick3 and Michael Botsch 1  \narXiv :2607 .05669v 1 [ cs .RO] 6 Jul 2026  \nAbstract—Reliable localization in GNSS-denied environments remains a fundamental challenge for intelligent vehicles, as inertial navigation systems accumulate unbounded drift without external correction. Existing approaches provide drift correction through dedicated infrastructure, expensive external sensors, or complex multi-sensor fusion, each introducing practical deployment barriers. We propose Evidential Velocity Correction using Mamba (EVC-Mamba), a learningbased architecture that transforms onboard vehicle sensor data into a virtual velocity sensor for IMU drift correction without additional hardware. A Mamba-based selective state space model captures the temporal dynamics of vehicle motion, while evidential deep learning with a Normal-Inverse-Gamma distribution provides principled uncertainty quantification. The resulting uncertainty-aware velocity estimate is incorporated asa virtual correction measurement into an Error-State Extended Kalman Filter to reduce position drift. Evaluation on realworld vehicle data demonstrates that inertial navigation using the proposed velocity correction achieves localization accuracy within 10% of a dedicated external velocity sensor across different outage durations. The proposed architecture supports real-time onboard deployment at 40 Hz on edge hardware, enabling reliable localization during prolonged GNSS outages.  \nI. INTRODUCTION  \nAccurate localization is a key requirement for the safe and reliable operation of intelligent vehicles, enabling essential functions such as path planning, motion control, and automated driving [1] . In general, precise localization is achieved by fusing an Inertial Navigation System (INS) with Global Navigation Satellite System (GNSS) signals to compensate for drift [2] . However, in GNSS-denied indoor environments, such as parking structures and tunnels, position drift grows unbounded due to the absence of external corrections [3] .  \nLocalization methods for GNSS-denied environments are broadly classified into Radio Frequency (RF)-based, visionbased, multi-sensor fusion, and proprioceptive inertial navigation approaches [4] . RF-based techniques depend on dedicated infrastructure and suffer from signal attenuation and multipath effects [5] . Vision-based methods using cameras or LiDARs can achieve high accuracy, yet remain sensitive to illumination changes and occlusions [6] . Multi-sensor fusion improves robustness at the cost of increased system complexity and expense [7], [8] . In contrast, Inertial Measurement Unit (IMU)-based inertial navigation offers a low-cost, infrastructure-free solution but suffers from longterm drift due to noise and bias accumulation [9] . Recent  \n1AImotion Bavaria, Technische Hochschule Ingolstadt, Germany, [firstname.lastname@thi.de](firstname.lastname@thi.de)  \n3Technische Universitt M¨unchen, Germany, [utschick@tum.de](utschick@tum.de)  \nFig. 1: Overview of the test vehicle configuration and the proposed EVC-Mamba based velocity correction for proprioceptive localization using IMU.  \ndata-driven methods have improved IMU-based dead reckoning [3], [9], but their effectiveness remains limited to shorter outage durations [10] . For longer outages, additional hardware, such as Correvit sensors [11], is typically required, which can be costly [12] . Alternatively, readily available onboard vehicle sensor data, such as steering wheel angle and wheel speeds, can be leveraged to construct a virtual velocity sensor, analogous to vehicle sideslip angle estimation [13] . Building on this insight, this work introduces Evidential Velocity Correction using Mamba (EVC-Mamba), a learning-based architecture that leverages onboard vehicle sensors for precise velocity correction in IMU-bas","cbCaidWCu0owX0wf","https://ap.wps.com/l/cbCaidWCu0owX0wf","pdf",2221567,1,6,"English","en",105,"# Introduction\n## Problem setting and GNSS-denied drift\n## Related localization modalities\n# Related Works","[{\"question\":\"What problem does EVC-Mamba address in GNSS-denied environments?\",\"answer\":\"It targets localization drift caused by inertial navigation systems accumulating unbounded error when GNSS corrections are unavailable.\"},{\"question\":\"How does EVC-Mamba obtain velocity information without extra hardware?\",\"answer\":\"It uses a learning-based architecture to transform onboard vehicle sensor data into a virtual velocity sensor used for IMU drift correction.\"},{\"question\":\"How is the uncertainty handled and used for improving localization?\",\"answer\":\"EVC-Mamba employs evidential deep learning with a Normal-Inverse-Gamma distribution to quantify uncertainty, then fuses the uncertainty-aware velocity estimate as a virtual correction measurement in an Error-State EKF.\"}]",1784184426,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"uncertainty-aware-velocity-correction-for-proprioceptive-vehicle-localization-using-evidential-mamba","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/uncertainty-aware-velocity-correction-for-proprioceptive-vehicle-localization-using-evidential-mamba/82978/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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},"What problem does EVC-Mamba address in GNSS-denied environments?","Question",{"text":75,"@type":76},"It targets localization drift caused by inertial navigation systems accumulating unbounded error when GNSS corrections are unavailable.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does EVC-Mamba obtain velocity information without extra hardware?",{"text":80,"@type":76},"It uses a learning-based architecture to transform onboard vehicle sensor data into a virtual velocity sensor used for IMU drift correction.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the uncertainty handled and used for improving localization?",{"text":84,"@type":76},"EVC-Mamba employs evidential deep learning with a Normal-Inverse-Gamma distribution to quantify uncertainty, then fuses the uncertainty-aware velocity estimate as a virtual correction measurement in an Error-State EKF.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]