[{"data":1,"prerenderedAt":631},["ShallowReactive",2],{"method-yang2024lifelong":3},{"method":4,"reference":62,"equipment":82,"figures":97,"results":137},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":22,"limitations":29,"sensors":37,"platform":39,"estimator":43,"association":44,"timeModel":45,"deskew":46,"loopClosure":47,"globalOptimization":48,"mapRepresentation":49,"prior":50,"outputGeometry":51,"compute":52,"codeUrl":53,"codeLicense":45,"relatedVersions":54},"yang2024lifelong","Yang et al., 2024","Lifelong 3D Mapping Framework (hand-held & robot-mounted)","Lifelong 3D Mapping Framework for Hand-Held & Robot-Mounted LiDAR Mapping Systems",2024,"recent","C06","downstream_engineering_task","此框架針對手持與機器人搭載光達建圖系統，串接四個模組：以 OctoMap 為基礎，加入子地圖多平面 RANSAC 回填、K 近鄰投票與半徑搜尋後處理的動態點移除；以 PCA-SHOT 特徵配對與 RANSAC 粗對齊、再以 NDT 精配準的多時段地圖對齊（六個參數以網格搜尋並取 Chamfer 距離最小者）；先以 k 近鄰半徑搜尋區分共存、重疊與非重疊區域，再比較沿平面法向投影的 2D 俯視最大高度描述子，找出正負變化；最後以類似 Git 的版本控制只保存一張基準地圖、各時段正負差異與邊界點，可重建任一時段乾淨地圖並查詢任兩時段差異。","A modular, cloud-native lifelong mapping pipeline for handheld and robot LiDAR maps: OctoMap-based dynamic removal with plane refilling, PCA-SHOT+RANSAC then NDT map alignment with grid-searched parameters, change detection by radius-based overlap splitting plus comparison of 2D bird's-eye-view max-height descriptors, and Git-style map version control storing one base map, differences and session boundaries.","full_text_reviewed","peer_reviewed_published","main_body","以商用手持光達（XGrids）於戶外與室內停車場多時段測試（Sec. IV-B），並報告 LT-SLAM 因 Scan Context 無法在重複室內停車場辨識迴圈而失敗；作者也指出可選的高度濾波不一定適用於多樓層建築的手持建圖（Sec. III-B）。變化偵測的量化評估使用人工移動物件產生的模擬變化（Sec. IV-C）。此為手持設備重複掃描的直接證據，但非工地、亦無獨立參考量測（推論：適合檢驗營建重複巡檢與差異追蹤流程，仍需工地實測驗證）。",[20,21],"public_benchmark","cross_site",[23,24,25,26,27,28],"Works with commercial handheld (XGrids) and open-source robot SLAM outputs (abstract; Sec. IV)","Alignment needs no manual parameter tuning thanks to grid search (abstract; Sec. III-C)","Past session maps reconstructable without storing raw session maps (abstract; Sec. III-E)","Map version control storage is 40.1% to 94.2% smaller than storing all input maps, reaching 94.2% on 27 NCLT sessions over about 1.5 years (Table V)","Change detection mean precision 0.885 (PD) and 0.920 (ND) versus 0.711 and 0.739 for KNN and 0.654 and 0.692 for PCL-OC, with comparable recall (Table IV)","Occluded regions missing in a new session are kept from the base map rather than deleted (Sec. IV-C, Figs. 4 and 7)",[30,31,32,33,34,35,36],"Most parameter subsets fail at feature matching and are discarded, so alignment relies on exhaustive search (Sec. III-C)","(inference) Chamfer distance is used both to select the alignment and to report alignment quality, so the reported metric is not independent of the selection","(inference) Rigid whole-map alignment cannot correct intra-session drift or deformation, unlike pose-graph or BA approaches","About 1 to 3% of static points remain misclassified as dynamic because not all areas are revisited during mapping (Sec. III-B)","The optional height filter may not work for drone mapping or hand-held mapping in multi-storey buildings without additional consistency checks (Sec. III-B)","Rejection rate is roughly 3% lower than ERASOR on SemanticKITTI (Sec. IV-A, Table II)","Quantitative change detection uses manually introduced changes as ground truth; ND recall on XGrid-Outdoor (0.798) is below both baselines, and PD precision on MulRan DCC (0.769) is below KNN (0.836) (Sec. IV-C, Table IV)",[38],"3D LiDAR",[40,41,42],"handheld","vehicle","wheeled UGV","not_applicable (poses supplied by external SLAM or commercial device software)","PCA-SHOT keypoint descriptors with RANSAC for initial alignment, then NDT fine registration; grid search over six parameters selected by lowest Chamfer distance","not_applicable","not_reported","none (map-to-map rigid alignment)","none (rigid alignment of whole session maps)","clean static session maps; single base map plus stored positive\u002Fnegative changes and boundary points (version control)","previous session maps","clean static maps, aligned maps, positive\u002Fnegative change point sets, reconstructable past session maps","Dynamic removal takes approximately 1.5 h for the whole KITTI 00 sequence (4500 frames as printed) on the authors' PC with an AMD Ryzen 9 3900x CPU (no GPU mentioned), stated as 1.5 times faster than Ground-Octomap (Sec. IV-A); grid-searched alignment takes roughly 3 min for XGrid-Outdoor maps of about 10M points versus over 10 min for LT-SLAM (Sec. IV-B); change detection takes about 2 min on LT-ParkingLot with 0.8M points (Sec. IV-C); hardware for the last two timings not stated; cloud-native design (abstract)",null,[55,59],{"relation":56,"title":57,"doi_or_url":58},"preprint","arXiv 2501.18110 (posted 2025-01-30, after journal publication)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.18110",{"relation":56,"title":60,"doi_or_url":61},"SSRN posting with same title (author list differs)","10.2139\u002Fssrn.5109701",{"id":5,"kind":63,"shortName":7,"title":8,"authors":64,"year":9,"venue":69,"venueType":70,"publisher":71,"volumeIssuePages":72,"doi":73,"arxivId":74,"url":58,"firstPublicDate":75,"publicationStatus":16,"metadataStatus":76,"fulltextStatus":15,"era":10,"classicReason":45,"codeUrl":53,"cluster":11,"topics":77,"mdpi":78,"verification":79,"label":6,"fulltextRoute":80,"versionRead":81,"addedByCensus":78},"method",[65,66,67,68],"Liudi Yang","Sai Manoj Prakhya","Senhua Zhu","Ziyuan Liu","IEEE Robotics and Automation Letters","journal","IEEE","9(11):9446-9453","10.1109\u002Flra.2024.3417113","2501.18110","2024-06-20","metadata_verified",[11],false,"corrected","arXiv","arXiv v1 (2025-01-30), author manuscript headed 'IEEE Robotics and Automation Letters preprint version, accepted June 2024'; IEEE RA-L version of record 9(11):9446-9453 not read",[83,90],{"category":84,"model":85,"canonical":85,"role":86,"dataset":87,"specs":88,"locator":89},"mobile_scanner_device","XGrids hand-held LiDAR mapping device (model not reported)","method input","XGrid-Outdoor, XGrid-Parking","commercial hand-held LiDAR mapping device; session poses retrieved from XGrids proprietary software","Abstract; Sec. IV; Sec. IV-B",{"category":91,"model":92,"canonical":93,"role":94,"dataset":53,"specs":95,"locator":96},"compute","AMD Ryzen 9 3900x","AMD RYZEN 9 3900X","compute for runtime","CPU of the authors' PC used for the dynamic removal timing","Sec. IV-A",[98,109,119,128],{"refId":5,"refLabel":6,"fig":99,"whatZh":100,"license":101,"licenseUrl":102,"sourceUrl":103,"src":104,"width":105,"height":106,"thumb":107,"thumbWidth":105,"thumbHeight":106,"modified":108},"Fig. 1","系統概念圖：使用者上傳多時段三維地圖，經動態物件移除、多時段對齊、變化偵測與版本控制後，可取回任一時段乾淨地圖或查詢任兩時段差異","CC BY-NC-SA 4.0","https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-nc-sa\u002F4.0\u002F","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2501.18110v1\u002Fcloud.png","\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-1.webp",437,512,"\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-1.thumb.webp","converted to WebP",{"refId":5,"refLabel":6,"fig":110,"whatZh":111,"license":101,"licenseUrl":102,"sourceUrl":112,"src":113,"width":114,"height":115,"thumb":116,"thumbWidth":117,"thumbHeight":118,"modified":108},"Fig. 4","以 XGrid-Parking 手持光達資料說明完整流程：基準地圖初始化、新時段地圖的動態點移除與對齊，以及正負變化反映到更新後的基準地圖","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2501.18110v1\u002Fwhole_result_6.png","\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-4.webp",580,795,"\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-4.thumb.webp",480,658,{"refId":5,"refLabel":6,"fig":120,"whatZh":121,"license":101,"licenseUrl":102,"sourceUrl":122,"src":123,"width":124,"height":125,"thumb":126,"thumbWidth":117,"thumbHeight":127,"modified":108},"Fig. 5","LT-ParkingLot、XGrid-Parking、XGrid-Outdoor 與 NCLT 的多時段地圖對齊結果，以高度差區分不同時段軌跡","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2501.18110v1\u002Fmulti-sesson-map-alignment-1.png","\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-5.webp",1097,534,"\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-5.thumb.webp",234,{"refId":5,"refLabel":6,"fig":129,"whatZh":130,"license":101,"licenseUrl":102,"sourceUrl":131,"src":132,"width":133,"height":134,"thumb":135,"thumbWidth":117,"thumbHeight":136,"modified":108},"Fig. 7","XGrid-Outdoor、LT-ParkingLot 與合成資料的變化偵測視覺化：移除消失的樹與車、加入新物件，並保留被遮蔽區域","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2501.18110v1\u002Fmap_change_detection_result.png","\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-7.webp",705,376,"\u002Ffigure-files\u002Fyang2024lifelong\u002Ffig-7.thumb.webp",256,{"totalRows":138,"groupCount":139,"groups":140,"others":615},50,7,[141,321,506,580],{"slug":142,"group":143,"sourceId":5,"sourceLabel":6,"table":144,"selfRows":145,"metrics":146,"seqs":162,"entrants":181,"cells":189,"outcomes":315,"locators":316,"hardware":317,"wordings":318,"notes":319},"yang2024lifelong-table-iv","yang2024lifelong:Table IV","Table IV",20,[147,151,153,155,157,159,160,161],{"label":148,"unit":149,"statistic":46,"alignment":150},"PD precision","ratio","none",{"label":152,"unit":149,"statistic":46,"alignment":150},"PD recall",{"label":154,"unit":149,"statistic":46,"alignment":150},"ND precision",{"label":156,"unit":149,"statistic":46,"alignment":150},"ND recall",{"label":148,"unit":149,"statistic":158,"alignment":150},"mean",{"label":152,"unit":149,"statistic":158,"alignment":150},{"label":154,"unit":149,"statistic":158,"alignment":150},{"label":156,"unit":149,"statistic":158,"alignment":150},[163,167,170,173,177],{"dataset":164,"sequence":165,"environment":166},"XGrid-Outdoor","simulated changes","outdoor, commercial hand-held LiDAR",{"dataset":168,"sequence":165,"environment":169},"LT-ParkingLot","parking lot",{"dataset":171,"sequence":165,"environment":172},"XGrid-Parking","indoor car park, commercial hand-held LiDAR",{"dataset":174,"sequence":175,"environment":176},"MulRan","DCC","urban",{"dataset":178,"sequence":179,"environment":180},"Mean (four datasets)","mean over XGrid-Outdoor, LT-ParkingLot, XGrid-Parking, MulRan DCC","four datasets",[182,184,186],{"name":183,"methodId":53,"linkable":78,"proposed":78,"self":78},"KNN",{"name":185,"methodId":53,"linkable":78,"proposed":78,"self":78},"PCL-OC",{"name":187,"methodId":5,"linkable":188,"proposed":188,"self":188},"Ours",true,[190,194,197,200,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,281,282,284,286,288,290,293,296,298,300,302,304,306,308,310,311,313],[191,191,191,192,193,191,193,193,191],0,0.747,-1,[191,195,191,196,193,191,193,193,191],1,0.933,[191,198,191,199,193,191,193,193,191],2,0.738,[191,201,191,202,193,191,193,193,191],3,0.937,[195,191,191,204,193,191,193,193,191],0.559,[195,195,191,206,193,191,193,193,191],0.942,[195,198,191,208,193,191,193,193,191],0.59,[195,201,191,210,193,191,193,193,191],0.921,[198,191,191,212,193,191,193,193,191],0.968,[198,195,191,214,193,191,193,193,191],0.953,[198,198,191,216,193,191,193,193,191],0.909,[198,201,191,218,193,191,193,193,191],0.798,[191,191,195,220,193,191,193,193,191],0.735,[191,195,195,222,193,191,193,193,191],0.91,[191,198,195,224,193,191,193,193,191],0.947,[191,201,195,226,193,191,193,193,191],0.852,[195,191,195,228,193,191,193,193,191],0.624,[195,195,195,230,193,191,193,193,191],0.827,[195,198,195,232,193,191,193,193,191],0.882,[195,201,195,234,193,191,193,193,191],0.757,[198,191,195,236,193,191,193,193,191],0.982,[198,195,195,238,193,191,193,193,191],0.917,[198,198,195,240,193,191,193,193,191],0.952,[198,201,195,242,193,191,193,193,191],0.895,[191,191,198,244,193,191,193,193,191],0.524,[191,195,198,246,193,191,193,193,191],0.667,[191,198,198,248,193,191,193,193,191],0.555,[191,201,198,250,193,191,193,193,191],0.872,[195,191,198,252,193,191,193,193,191],0.739,[195,195,198,254,193,191,193,193,191],0.684,[195,198,198,256,193,191,193,193,191],0.731,[195,201,198,258,193,191,193,193,191],0.723,[198,191,198,260,193,191,193,193,191],0.819,[198,195,198,262,193,191,193,193,191],0.69,[198,198,198,264,193,191,193,193,191],0.945,[198,201,198,266,193,191,193,193,191],0.848,[191,191,201,268,193,191,193,193,191],0.836,[191,195,201,270,193,191,193,193,191],0.81,[191,198,201,272,193,191,193,193,191],0.717,[191,201,201,274,193,191,193,193,191],0.756,[195,191,201,276,193,191,193,193,191],0.695,[195,195,201,278,193,191,193,193,191],0.686,[195,198,201,280,193,191,193,193,191],0.564,[195,201,201,218,193,191,193,193,191],[198,191,201,283,193,191,193,193,191],0.769,[198,195,201,285,193,191,193,193,191],0.849,[198,198,201,287,193,191,193,193,191],0.875,[198,201,201,289,193,191,193,193,191],0.86,[191,291,291,292,193,191,193,193,191],4,0.711,[191,294,291,295,193,191,193,193,191],5,0.83,[191,297,291,252,193,191,193,193,191],6,[191,139,291,299,193,191,193,193,191],0.854,[195,291,291,301,193,191,193,193,191],0.654,[195,294,291,303,193,191,193,193,191],0.785,[195,297,291,305,193,191,193,193,191],0.692,[195,139,291,307,193,191,193,193,191],0.8,[198,291,291,309,193,191,193,193,191],0.885,[198,294,291,226,193,191,193,193,191],[198,297,291,312,193,191,193,193,191],0.92,[198,139,291,314,193,191,193,193,191],0.85,[],[144],[],[],[320],"Map change detection against manually introduced changes (relocated buildings, cars, trees); precision and recall for positive differences (PD, new data in session map) and negative differences (ND, data gone from base map); baselines are a k-d tree change detector (KNN) and the Point Cloud Library octree change detector (PCL-OC); a detected point counts as true if a ground truth change lies in its small radial neighbourhood",{"slug":322,"group":323,"sourceId":5,"sourceLabel":6,"table":324,"selfRows":325,"metrics":326,"seqs":336,"entrants":351,"cells":361,"outcomes":500,"locators":501,"hardware":502,"wordings":503,"notes":504},"yang2024lifelong-table-ii","yang2024lifelong:Table II","Table II",18,[327,329,331,333,334,335],{"label":328,"unit":149,"statistic":46,"alignment":150},"PR (preservation rate)",{"label":330,"unit":149,"statistic":46,"alignment":150},"RR (rejection rate)",{"label":332,"unit":149,"statistic":46,"alignment":150},"F1 score",{"label":328,"unit":149,"statistic":158,"alignment":150},{"label":330,"unit":149,"statistic":158,"alignment":150},{"label":332,"unit":149,"statistic":158,"alignment":150},[337,341,343,345,347,349],{"dataset":338,"sequence":339,"environment":340},"SemanticKITTI","00","urban driving, vehicle-mounted LiDAR",{"dataset":338,"sequence":342,"environment":340},"01",{"dataset":338,"sequence":344,"environment":340},"02",{"dataset":338,"sequence":346,"environment":340},"05",{"dataset":338,"sequence":348,"environment":340},"07",{"dataset":338,"sequence":350,"environment":340},"mean of sequences 00, 01, 02, 05, 07",[352,355,358,360],{"name":353,"methodId":354,"linkable":188,"proposed":78,"self":78},"ERASOR","erasor2021",{"name":356,"methodId":357,"linkable":188,"proposed":78,"self":78},"Removert","removert2020",{"name":359,"methodId":53,"linkable":78,"proposed":78,"self":78},"Ground-Octomap",{"name":187,"methodId":5,"linkable":188,"proposed":188,"self":188},[362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,453,454,456,457,459,461,463,465,466,468,470,472,474,476,478,480,482,484,486,488,489,491,493,495,497,498],[191,191,191,363,193,191,193,193,191],0.9172,[191,195,191,365,193,191,193,193,191],0.97,[191,198,191,367,193,191,193,193,191],0.9429,[195,191,191,369,193,191,193,193,191],0.9328,[195,195,191,371,193,191,193,193,191],0.7663,[195,198,191,373,193,191,193,193,191],0.8414,[198,191,191,375,193,191,193,193,191],0.7765,[198,195,191,377,193,191,193,193,191],0.9526,[198,198,191,379,193,191,193,193,191],0.8556,[201,191,191,381,193,191,193,193,191],0.9471,[201,195,191,383,193,191,193,193,191],0.9712,[201,198,191,385,193,191,193,193,191],0.959,[191,191,195,387,193,191,193,193,191],0.9193,[191,195,195,389,193,191,193,193,191],0.9463,[191,198,195,391,193,191,193,193,191],0.9326,[195,191,195,393,193,191,193,193,191],0.9579,[195,195,195,395,193,191,193,193,191],0.6688,[195,198,195,397,193,191,193,193,191],0.7877,[198,191,195,399,193,191,193,193,191],0.8475,[198,195,195,401,193,191,193,193,191],0.7337,[198,198,195,403,193,191,193,193,191],0.7865,[201,191,195,405,193,191,193,193,191],0.9425,[201,195,195,407,193,191,193,193,191],0.9528,[201,198,195,409,193,191,193,193,191],0.9477,[191,191,198,411,193,191,193,193,191],0.8108,[191,195,198,413,193,191,193,193,191],0.9911,[191,198,198,415,193,191,193,193,191],0.8919,[195,191,198,417,193,191,193,193,191],0.8531,[195,195,198,419,193,191,193,193,191],0.8222,[195,198,198,421,193,191,193,193,191],0.8374,[198,191,198,423,193,191,193,193,191],0.9479,[198,195,198,425,193,191,193,193,191],0.6277,[198,198,198,427,193,191,193,193,191],0.7553,[201,191,198,429,193,191,193,193,191],0.9421,[201,195,198,431,193,191,193,193,191],0.9035,[201,198,198,433,193,191,193,193,191],0.9224,[191,191,201,435,193,191,193,193,191],0.8698,[191,195,201,437,193,191,193,193,191],0.9788,[191,198,201,439,193,191,193,193,191],0.9211,[195,191,201,441,193,191,193,193,191],0.9223,[195,195,201,443,193,191,193,193,191],0.6757,[195,198,201,445,193,191,193,193,191],0.78,[198,191,201,447,193,191,193,193,191],0.6956,[198,195,201,449,193,191,193,193,191],0.939,[198,198,201,451,193,191,193,193,191],0.7992,[201,191,201,405,193,191,193,193,191],[201,195,201,383,193,191,193,193,191],[201,198,201,455,193,191,193,193,191],0.9566,[191,191,291,312,193,191,193,193,191],[191,195,291,458,193,191,193,193,191],0.9833,[191,198,291,460,193,191,193,193,191],0.9506,[195,191,291,462,193,191,193,193,191],0.8482,[195,195,291,464,193,191,193,193,191],0.5758,[195,198,291,278,193,191,193,193,191],[198,191,291,467,193,191,193,193,191],0.5396,[198,195,291,469,193,191,193,193,191],0.9081,[198,198,291,471,193,191,193,193,191],0.6769,[201,191,291,473,193,191,193,193,191],0.9768,[201,195,291,475,193,191,193,193,191],0.941,[201,198,291,477,193,191,193,193,191],0.9586,[191,201,294,479,193,191,193,193,191],0.8874,[191,291,294,481,193,191,193,193,191],0.9739,[191,294,294,483,193,191,193,193,191],0.9278,[195,201,294,485,193,191,193,193,191],0.9029,[195,291,294,487,193,191,193,193,191],0.7017,[195,294,294,403,193,191,193,193,191],[198,201,294,490,193,191,193,193,191],0.7614,[198,291,294,492,193,191,193,193,191],0.8322,[198,294,294,494,193,191,193,193,191],0.7747,[201,201,294,496,193,191,193,193,191],0.9502,[201,291,294,423,193,191,193,193,191],[201,294,294,499,193,191,193,193,191],0.9488,[],[324],[],[],[505],"Dynamic object removal on SemanticKITTI; point-wise labels, moving classes counted as dynamic; sequences and scan ranges follow the ERASOR setup; authors note ERASOR ran at a lower frame rate; baseline execution settings otherwise not stated",{"slug":507,"group":508,"sourceId":5,"sourceLabel":6,"table":509,"selfRows":294,"metrics":510,"seqs":514,"entrants":526,"cells":535,"outcomes":573,"locators":575,"hardware":576,"wordings":577,"notes":578},"yang2024lifelong-table-iii","yang2024lifelong:Table III","Table III",[511],{"label":512,"unit":513,"statistic":158,"alignment":150},"Chamfer distance after multi-session map alignment","not_reported (mean of squared nearest-neighbour distances)",[515,517,520,522,524],{"dataset":164,"sequence":516,"environment":166},"6 session maps",{"dataset":171,"sequence":518,"environment":519},"5 session maps","indoor car park with repetitive structure, commercial hand-held LiDAR",{"dataset":168,"sequence":521,"environment":169},"6 session maps, SC-LIO-SAM poses (row LT-ParkingLot-SC-LIO-SAM)",{"dataset":168,"sequence":523,"environment":169},"6 session maps, SC-A-LOAM poses (row LT-ParkingLot-SC-A-LOAM)",{"dataset":174,"sequence":525,"environment":176},"DCC, 3 session maps (row MulRan-SC-LIO-LOAM)",[527,528,531,533],{"name":187,"methodId":5,"linkable":188,"proposed":188,"self":188},{"name":529,"methodId":530,"linkable":188,"proposed":78,"self":78},"LT-SLAM","ltmapper2022",{"name":532,"methodId":53,"linkable":78,"proposed":78,"self":78},"ICP",{"name":534,"methodId":53,"linkable":78,"proposed":78,"self":78},"NDT",[536,538,540,542,544,546,547,548,550,552,554,556,558,560,562,564,566,568,570,571],[191,191,191,537,193,191,193,193,191],0.069,[195,191,191,539,193,191,193,193,191],0.0862,[198,191,191,541,193,191,193,193,191],0.1389,[201,191,191,543,193,191,193,193,191],0.1342,[191,191,195,545,193,191,193,193,191],0.0812,[195,191,195,53,191,191,193,193,191],[198,191,195,53,191,191,193,193,191],[201,191,195,549,193,191,193,193,191],0.1235,[191,191,198,551,193,191,193,193,191],0.0329,[195,191,198,553,193,191,193,193,191],0.0592,[198,191,198,555,193,191,193,193,191],0.1211,[201,191,198,557,193,191,193,193,191],0.1378,[191,191,201,559,193,191,193,193,191],0.0173,[195,191,201,561,193,191,193,193,191],0.0526,[198,191,201,563,193,191,193,193,191],0.1228,[201,191,201,565,193,191,193,193,191],0.1282,[191,191,291,567,193,191,193,193,191],0.1004,[195,191,291,569,193,191,193,193,191],0.2059,[198,191,291,53,191,191,193,193,191],[201,191,291,572,193,191,193,193,191],0.1231,[574],"failed",[509],[],[],[579],"Average Chamfer distance after aligning several session maps into one frame; poses from XGrids proprietary software (XGrid datasets) or SC-LIO-SAM and SC-A-LOAM (LT-ParkingLot, MulRan); outlier threshold tau 0.5; the proposed method also uses Chamfer distance to pick its alignment",{"slug":581,"group":582,"sourceId":5,"sourceLabel":6,"table":583,"selfRows":291,"metrics":584,"seqs":588,"entrants":598,"cells":600,"outcomes":609,"locators":610,"hardware":611,"wordings":612,"notes":613},"yang2024lifelong-table-v","yang2024lifelong:Table V","Table V",[585],{"label":586,"unit":587,"statistic":46,"alignment":150},"Ours (MB)","MB",[589,592,593,595],{"dataset":164,"sequence":590,"environment":591},"3 maps","multi-session map storage",{"dataset":171,"sequence":590,"environment":591},{"dataset":168,"sequence":594,"environment":591},"6 maps",{"dataset":596,"sequence":597,"environment":591},"NCLT","27 maps over about 1.5 years",[599],{"name":187,"methodId":5,"linkable":188,"proposed":188,"self":188},[601,603,605,607],[191,191,191,602,193,191,193,193,191],27.2,[191,191,195,604,193,191,193,193,191],31.9,[191,191,198,606,193,191,193,193,191],129.9,[191,191,201,608,193,191,193,193,191],430.7,[],[583],[],[],[614],"Memory to store all input downsampled session maps versus the map version control store (base map, positive and negative differences, boundaries); NCLT downsampled to 0.5 m, others to 0.2 m; the printed efficiency ratio (40.1%, 50.4%, 78.1%, 94.2%) equals one minus Ours over All maps and is not stored as separate rows",[616,621,626],{"group":617,"slug":618,"sourceLabel":6,"table":619,"selfRows":195,"datasets":620},"yang2024lifelong:Text Sec. IV-A","yang2024lifelong-text-sec-iv-a","Text Sec. IV-A",[338],{"group":622,"slug":623,"sourceLabel":6,"table":624,"selfRows":195,"datasets":625},"yang2024lifelong:Text Sec. IV-B","yang2024lifelong-text-sec-iv-b","Text Sec. IV-B",[164],{"group":627,"slug":628,"sourceLabel":6,"table":629,"selfRows":195,"datasets":630},"yang2024lifelong:Text Sec. IV-C","yang2024lifelong-text-sec-iv-c","Text Sec. IV-C",[168],1790510658588]