[{"data":1,"prerenderedAt":260},["ShallowReactive",2],{"method-lol2020":3},{"method":4,"reference":60,"equipment":81,"figures":105,"results":106},{"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":21,"limitations":26,"sensors":32,"platform":34,"estimator":36,"association":37,"timeModel":38,"deskew":39,"loopClosure":40,"globalOptimization":41,"mapRepresentation":42,"prior":43,"outputGeometry":44,"compute":45,"codeUrl":46,"codeLicense":47,"relatedVersions":48},"lol2020","Rozenberszki & Majdik, 2020","LOL","LOL: Lidar-only Odometry and Localization in 3D point cloud maps",2020,"recent","C04","localization_in_prior_map_or_bim","LOL 只用 LiDAR 在既有 3D 點雲地圖中做里程計與定位：以 LOAM 連續估計位姿，並把最近數幀點雲累積成局部地圖、切成片段，以 SegMatch 或 SegMap 描述子與預先切割描述的目標地圖片段比對。為減少誤匹配，只在里程計位置附近搜尋候選，再以質心平移一致性與 RANSAC 過濾；通過後先以匹配片段質心的平均位移做初值，再以 ICP 對齊片段點雲求出修正量，送入 SegMap 的增量位姿圖。它是在先驗地圖中定位，而不是線上迴圈閉合。","LiDAR-only odometry and localization in a prior point-cloud map: LOAM odometry plus SegMap\u002FSegMatch segment matching against a pre-segmented target map, with location-gated candidate search, centroid consistency and RANSAC filtering, and a centroid-shift prior refined by ICP; updates enter SegMap's incremental pose graph.","full_text_reviewed","peer_reviewed_published","background","在既有點雲地圖中定位的概念，與施工現場以先前掃描或 BIM 衍生點雲作為參考地圖相近，但這屬推論；論文只在 KITTI 市區與住宅區道路測試，目標地圖以 SegMap 的雷射 SLAM 工具建立，並非測量等級參考。一篇基礎設施非破壞檢測回顧的作者回報 LOL 無法完成軌跡估計 [ghadimzadeh2025slamnde]。",[20],"public_benchmark",[22,23,24,25],"With a minimum cluster size of 3 or more, the filtering produced at most one false-positive match per drive while keeping 14 to 70 true positives (Table I)","Trajectories on three long KITTI raw drives (about 2.2 to 4.1 km) are significantly better than LOAM alone and relocalization never lost tracking (Sec. III-D; Sec. IV; Figs. 2 and 4)","No IMU, wheel encoder or GPS required (Sec. I)","Open-source code released (Supplementary attachments)",[27,28,29,30,31],"Quantitative trajectory error is only shown as plots for Drive 18 (Fig. 4); no numeric trajectory table","Evaluated on three KITTI raw drives in residential and city areas only (Sec. IV)","Target maps were built with the SegMap laser SLAM tool, not an independent survey (Sec. IV)","Cluster size 2 still gives incidental false localizations and size 5 gives too few localizations (Sec. IV)","Needs an assumed start position before the first localization (Sec. III-A)",[33],"3D LiDAR only (KITTI raw drives; sensor model not named in the paper); no IMU, wheel encoder or GPS (Sec. I)",[35],"vehicle (KITTI raw drives 18, 27, 28)","LOAM odometry and mapping (mapping at one tenth of the odometry rate) supplies poses; relocalization updates from segment matches are inserted into SegMap's incremental pose-graph mapping module, modified to incorporate relocalization in the global map (Sec. III-A; Sec. III-B; Fig. 1)","SegMatch eigenvalue (1x7) or SegMap CNN (1x64) segment descriptors; target segments searched only within a distance threshold of the odometry position; pairwise centroid-translation consistency, RANSAC alignment of matched centroids, a mean centroid-shift prior and final ICP between matched segment point clouds (Sec. III-C; Sec. III-D)","discrete poses","not described (LOAM front end used as is)","not used; drift is cancelled by relocalization against the prior target map instead of loop closure in the online map (Sec. I)","SegMap incremental pose-graph mapping module receives the relocalization updates (Sec. III-A; Fig. 1)","LOAM map voxelized at 5 cm; online local cloud densified from the last k scans and segmented; offline target point cloud segmented and described into a segment database searchable by centroid position (Sec. III-A; Sec. III-B)","prior 3D point cloud target map (built with the laser SLAM tool released with SegMap in the experiments) and an assumed start position before the first localization (Sec. III-A; Sec. IV)","trajectory relocalized in the target map frame","Intel i7-6700K, 32 GB RAM, NVIDIA GeForce GTX 1080; mean times 372.7 ms segmentation, 0.40 ms description, 26.27 ms match recognition, 0.09 ms RANSAC filtering and 88.0 ms ICP alignment; the authors describe the system as real time (Sec. IV)","https:\u002F\u002Fgithub.com\u002FRozDavid\u002FLOL","not stated (no license file found at the repository root; README has no license statement)",[49,53,57],{"relation":50,"title":51,"doi_or_url":52},"preprint","LOL (arXiv v1, ICRA 2020 preprint version)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.01595",{"relation":54,"title":55,"doi_or_url":56},"accepted_manuscript","SZTAKI eprint 10046 (listed by OpenAlex; not opened)","http:\u002F\u002Feprints.sztaki.hu\u002F10046\u002F",{"relation":58,"title":59,"doi_or_url":46},"code_release","RozDavid\u002FLOL",{"id":5,"kind":61,"shortName":7,"title":8,"authors":62,"year":9,"venue":65,"venueType":66,"publisher":67,"volumeIssuePages":68,"doi":69,"arxivId":70,"url":71,"firstPublicDate":72,"publicationStatus":16,"metadataStatus":73,"fulltextStatus":15,"era":10,"classicReason":74,"codeUrl":46,"cluster":11,"topics":75,"mdpi":76,"verification":77,"label":6,"fulltextRoute":78,"versionRead":79,"addedByCensus":80},"method",[63,64],"Dávid Rozenberszki","András L. Majdik","2020 IEEE International Conference on Robotics and Automation (ICRA)","conference","IEEE","pp. 4379-4385","10.1109\u002Ficra40945.2020.9197450","2007.01595","https:\u002F\u002Fdoi.org\u002F10.1109\u002FICRA40945.2020.9197450","2020-05","metadata_verified","not_applicable",[11],false,"corrected","arXiv","arXiv v1 (2020-07-03), marked 'ICRA 2020 arXiv preprint version'; IEEE version of record not read",true,[82,89,95,101],{"category":83,"model":84,"canonical":84,"role":85,"dataset":86,"specs":87,"locator":88},"lidar","3D LiDAR of the KITTI raw recordings (model not named in the paper)","dataset sensor","KITTI raw drives 18, 27, 28","raw drives 18 (about 2200 m), 27 (about 3660 m) and 28 (about 4125 m)","Sec. IV; Fig. 2",{"category":90,"model":91,"canonical":91,"role":92,"dataset":86,"specs":93,"locator":94},"other","ground-truth target maps built with the laser SLAM tool released with SegMap","reference or ground truth","used as target maps and trajectory reference","Sec. IV",{"category":96,"model":97,"canonical":97,"role":98,"dataset":99,"specs":100,"locator":94},"compute","Intel i7-6700K","compute for runtime",null,"32 GB RAM",{"category":96,"model":102,"canonical":103,"role":98,"dataset":99,"specs":104,"locator":94},"Nvidia GeForce GTX 1080","NVIDIA GeForce GTX1080","GPU in the same system",[],{"totalRows":107,"groupCount":108,"groups":109,"others":259},41,2,[110,207],{"slug":111,"group":112,"sourceId":5,"sourceLabel":6,"table":113,"selfRows":114,"metrics":115,"seqs":124,"entrants":133,"cells":142,"outcomes":201,"locators":202,"hardware":203,"wordings":204,"notes":205},"lol2020-table-i","lol2020:Table I","Table I",36,[116,120,122],{"label":117,"unit":118,"statistic":119,"alignment":74},"number of filtered out matches","count","not_reported",{"label":121,"unit":118,"statistic":119,"alignment":74},"number of true positive matches",{"label":123,"unit":118,"statistic":119,"alignment":74},"number of false positive matches",[125,129,131],{"dataset":126,"sequence":127,"environment":128},"KITTI raw","Drive 18","vehicle, residential and city streets",{"dataset":126,"sequence":130,"environment":128},"Drive 27",{"dataset":126,"sequence":132,"environment":128},"Drive 28",[134,136,138,140],{"name":135,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL filtering, minimum cluster size 2",{"name":137,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL filtering, minimum cluster size 3",{"name":139,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL filtering, minimum cluster size 4",{"name":141,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL filtering, minimum cluster size 5",[143,147,150,151,153,154,155,157,159,160,162,164,165,167,168,169,171,173,174,176,178,179,180,181,182,184,186,187,189,191,192,194,196,197,198,200],[144,144,144,145,146,144,146,146,144],0,579,-1,[144,148,144,149,146,144,146,146,144],1,49,[144,108,144,108,146,144,146,146,144],[148,144,144,152,146,144,146,146,144],299,[148,148,144,114,146,144,146,146,144],[148,108,144,144,146,144,146,146,144],[108,144,144,156,146,144,146,146,144],8,[108,148,144,158,146,144,146,146,144],25,[108,108,144,144,146,144,146,146,144],[161,144,144,144,146,144,146,146,144],3,[161,148,144,163,146,144,146,146,144],22,[161,108,144,144,146,144,146,146,144],[144,144,148,166,146,144,146,146,144],756,[144,148,148,107,146,144,146,146,144],[144,108,148,161,146,144,146,146,144],[148,144,148,170,146,144,146,146,144],311,[148,148,148,172,146,144,146,146,144],32,[148,108,148,144,146,144,146,146,144],[108,144,148,175,146,144,146,146,144],14,[108,148,148,177,146,144,146,146,144],26,[108,108,148,144,146,144,146,146,144],[161,144,148,144,146,144,146,146,144],[161,148,148,175,146,144,146,146,144],[161,108,148,144,146,144,146,146,144],[144,144,108,183,146,144,146,146,144],694,[144,148,108,185,146,144,146,146,144],85,[144,108,108,161,146,144,146,146,144],[148,144,108,188,146,144,146,146,144],421,[148,148,108,190,146,144,146,146,144],70,[148,108,108,144,146,144,146,146,144],[108,144,108,193,146,144,146,146,144],158,[108,148,108,195,146,144,146,146,144],54,[108,108,108,148,146,144,146,146,144],[161,144,108,144,146,144,146,146,144],[161,148,108,199,146,144,146,146,144],30,[161,108,108,144,146,144,146,146,144],[],[113],[],[],[206],"Numbers of filtered-out, true-positive and false-positive SegMap matches for minimum cluster sizes 2-5 on three KITTI raw drives; validity judged against the ground-truth trajectory",{"slug":208,"group":209,"sourceId":5,"sourceLabel":6,"table":210,"selfRows":211,"metrics":212,"seqs":225,"entrants":229,"cells":240,"outcomes":252,"locators":253,"hardware":254,"wordings":256,"notes":257},"lol2020-text-sec-iv","lol2020:Text Sec. IV","Text Sec. IV",5,[213,217,219,221,223],{"label":214,"unit":215,"statistic":216,"alignment":74},"segmentation time, mean (std 7.2)","ms","mean",{"label":218,"unit":215,"statistic":216,"alignment":74},"description time, mean (std 0.26)",{"label":220,"unit":215,"statistic":216,"alignment":74},"match recognition in the reduced candidate pool time, mean (std 14.27)",{"label":222,"unit":215,"statistic":216,"alignment":74},"additional RANSAC geometric filtering time, mean (std 0.7)",{"label":224,"unit":215,"statistic":216,"alignment":74},"ICP alignment time, mean (std 37.2)",[226],{"dataset":126,"sequence":227,"environment":228},"drives 18, 27, 28","vehicle",[230,232,234,236,238],{"name":231,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL, segmentation",{"name":233,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL, description",{"name":235,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL, match recognition in the reduced candidate pool",{"name":237,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL, additional RANSAC geometric filtering",{"name":239,"methodId":5,"linkable":80,"proposed":80,"self":80},"LOL, ICP alignment",[241,243,245,247,249],[144,144,144,242,146,144,144,146,144],372.7,[148,148,144,244,146,144,144,146,144],0.4,[108,108,144,246,146,144,144,146,144],26.27,[161,161,144,248,146,144,144,146,144],0.09,[250,250,144,251,146,144,144,146,144],4,88,[],[94],[255],"Intel i7-6700K, 32 GB RAM, Nvidia GeForce GTX 1080",[],[258],"Mean (standard deviation) processing time of each module",[],1790510663080]