[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86302-en":3,"doc-seo-86302-105":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},86302,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Self-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry","Low-cost unmanned ground vehicles operating indoors often rely on painted floor lines for camera-based line following, yet guidance tracking can fail when the line is occluded, turns sharply, or leaves the field of view. This work introduces a lightweight two-stage recovery method that restores guideline tracking at runtime without LiDAR, GPS, or GPU. The controller turns in place with adaptive color checks, then uses monocular visual odometry to return to saved breadcrumb poses. Depth-gated HSV tracking, YOLOv8n obstacle detection, and a CPU-only 20 Hz implementation achieve 86.6% success and median 3.26 s recovery across 119 fault episodes.","arXiv :2607 . 11686v1 [ cs .RO] 13 Jul 2026  \nSelf-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry  \nJAKOB SOLBERG BERNTZEN 1,2, SAFIA FATIMA 1,2, AND LEON MOONEN 1 (Member, IEEE) 1 Simula Research Laboratory, Oslo, Norway  \n2 University of Oslo, Oslo, Norway  \nCorresponding author: Leon Moonen (e-mail: [leon@simula.no](leon@simula.no)).  \nThis work was supported in part by the Research Council of Norway through the cureIT project (grant \\#300461) .  \n ABSTRACT Low-cost unmanned ground vehicles are often used in indoor places like warehouses, inspection corridors, and farm rows, where painted floor lines guide the robot. Line following is useful because it only needs one camera and little computing power, but it can fail when the line is blocked or turns sharply and goes out of view. Sensor-rich platforms tolerate this through hardware redundancy (LiDAR, GPS, multiple cameras), but camera-only systems must recover at runtime with no additional infrastructure. This paper presents a lightweight, two-stage recovery approach that restores guideline tracking without LiDAR, GPS, or a GPU. When the line is lost, the robot first turns in place while slowly relaxing its color checks and waiting for confirmation across multiple frames (Stage 1) . If the line is still not found, monocular visual odometry moves the robot back to saved breadcrumb positions before it tries again (Stage 2) . The system uses a depth-gated HSV line tracker, a YOLOv8n obstacle detector, and a visual odometry breadcrumb mapper, and it runs at 20 Hz on CPU-only hardware. The controller embeds a complete MAPE-K loop within a single 50 ms control tick, with no external adaptation manager required. The approach is evaluated across  \n119 fault-injected episodes on three Webots simulation courses. The method was successful in 86.6% of cases, with a median recovery time of 3.26 seconds. These results demonstrate that reliable visual recovery is feasible on camera-only UGVs within practical cost and computational limits.  \n INDEX TERMS Autonomous ground vehicle, self-adaptive systems, line following, visual odometry, obstacle avoidance, fault tolerance, low-cost robotics, YOLOv8, depth-gated perception, Webots simulation.  \nI. INTRODUCTION  \nAUTONOMOUS ground vehicles (UGVs) are used in  \na growing range of applications, including logistics, industrial inspection, and small-scale agriculture, where continuous and unattended operation is valuable [1, 2] . Falling component costs and persistent labor shortages have moved these vehicles from laboratory prototypes into routine field use for tasks such as crop monitoring, transport, and inspection, where reliable operation must be maintained under real-world conditions [1, 2] . Section III examines this demand and the case for low-cost autonomy in more detail.  \nHigh-end UGVs deployed in demanding sectors such as space exploration, military reconnaissance, and precision agriculture rely on redundant sensor suites that may include LiDAR, RADAR, GPS, multiple cameras, and inertial measurement units, together with sophisticated sensorfusion architectures for localization and fault detection [2– 4]. These configurations deliver reliable navigation in dy-  \nnamic and unstructured environments, but their substantial acquisition cost, integration complexity, and maintenance requirements place them beyond the financial reach of many small-to-medium enterprises and developing-market operators [5, 6] .  \nMany sectors, including warehouse logistics, floorguided inspection, and small-scale agriculture, depend on repetitive, labor-intensive tasks that could benefit greatly from automation but cannot justify the cost of sensorrich platforms [5] . Guideline following is a navigation paradigm particularly well suited to these deployments, a painted or taped floor line provides a deterministic reference with minimal infrastructure cost, and a robot can track it using only a single camera and limited o","cbCaitbTlVWmCZwm","https://ap.wps.com/l/cbCaitbTlVWmCZwm","pdf",8656110,3,1,18,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"Why do camera-only line-following UGVs fail during indoor navigation?\",\"answer\":\"Failures occur when the painted line is occluded by obstacles or debris, when reflections and lighting changes degrade color segmentation, or when obstacle-avoidance actions shift the heading so the line leaves the camera’s field of view.\"},{\"question\":\"What are the two stages of the proposed self-healing recovery approach?\",\"answer\":\"Stage 1 turns in place while slowly relaxing the line color checks and confirming detection across multiple frames. If the line is still not found, Stage 2 uses monocular visual odometry to move the robot back to previously saved breadcrumb positions before retrying tracking.\"},{\"question\":\"How is the method evaluated and what performance results are reported?\",\"answer\":\"The approach is tested on 119 fault-injected episodes across three Webots simulation courses. It succeeds in 86.6% of cases with a median recovery time of 3.26 seconds, running at 20 Hz on CPU-only hardware.\"}]",1784210327,45,{"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},"self-healing-visual-recovery-for-autonomous-ground-vehicles-using-camera-only-visual-odometry","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/self-healing-visual-recovery-for-autonomous-ground-vehicles-using-camera-only-visual-odometry/86302/",4,{"url":51,"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","2026-07-26","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 do camera-only line-following UGVs fail during indoor navigation?","Question",{"text":75,"@type":76},"Failures occur when the painted line is occluded by obstacles or debris, when reflections and lighting changes degrade color segmentation, or when obstacle-avoidance actions shift the heading so the line leaves the camera’s field of view.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the two stages of the proposed self-healing recovery approach?",{"text":80,"@type":76},"Stage 1 turns in place while slowly relaxing the line color checks and confirming detection across multiple frames. If the line is still not found, Stage 2 uses monocular visual odometry to move the robot back to previously saved breadcrumb positions before retrying tracking.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the method evaluated and what performance results are reported?",{"text":84,"@type":76},"The approach is tested on 119 fault-injected episodes across three Webots simulation courses. It succeeds in 86.6% of cases with a median recovery time of 3.26 seconds, running at 20 Hz on CPU-only hardware.","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":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":52,"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"]