[{"data":1,"prerenderedAt":577},["ShallowReactive",2],{"method-artslam2022":3},{"method":4,"reference":60,"equipment":81,"figures":111,"results":112},{"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":27,"sensors":33,"platform":37,"estimator":40,"association":41,"timeModel":42,"deskew":43,"loopClosure":44,"globalOptimization":45,"mapRepresentation":46,"prior":47,"outputGeometry":48,"compute":49,"codeUrl":50,"codeLicense":51,"relatedVersions":52},"artslam2022","Frosi & Matteucci, 2022","ART-SLAM","ART-SLAM: Accurate Real-Time 6DoF LiDAR SLAM",2022,"recent","C04","full_slam_with_global_correction","ART-SLAM 是模組化的 LiDAR 圖式 SLAM，架構參考 hdl_graph_slam：點雲先降採樣並以八分區平行去除離群點，追蹤模組以完整點雲對最近關鍵影格配準（可選 ICP、GICP、VGICP 或 NDT），並可由多尺度預追蹤或外部里程計提供初值；地面偵測模組估計地面平面，加入高度與姿態約束。迴圈偵測分三步：先依累積距離與位置篩選候選，再以 Scan Context 保留最相似的少數候選，最後逐一配準取最佳結果，所有約束以 g2o 位姿圖最佳化。IMU 與 GPS 為選用輸入，IMU 可用於去除運動畸變。","Modular hdl_graph_slam-inspired LiDAR graph SLAM: filtered full-cloud scan-to-keyframe registration (ICP, GICP, VGICP or NDT) with an optional pre-tracker, floor-plane constraints, three-step loop closure with Scan Context, and g2o pose-graph optimization; IMU and GPS are optional.","full_text_reviewed","peer_reviewed_published","background","論文只在 KITTI 道路資料與智利地下礦坑資料上測試，礦坑測試以帶雜訊的真值作初值，不能視為一般地下工程的獨立驗證。施工相關證據來自其他研究：在 Hilti 2022 施工現場序列 Exp04 至 Exp06 上，ART-SLAM 在 Exp04 與 Exp05 的最終 ATE RMSE 約 1.0 與 1.1 m，在 Exp06 失去追蹤 [yarovoi2024review]。",[20,21],"public_benchmark","underground_or_tunnel",[23,24,25,26],"On KITTI 07 the IMU variant has the lowest ATE RMSE (0.366 m) and the LiDAR-only variant 0.777 m versus 1.253 m for HDL and 0.675 m for LIO-SAM (Table II)","On KITTI 00 the IMU variant has the lowest ATE RMSE (1.014 m) and the LiDAR-only variant 1.092 m versus 1.424 m for HDL, while LOAM, A-LOAM and LIO-SAM exceed 10 m (Table IV)","Scan Context halves loop detection time on KITTI 00 (9.380 ms versus 19.301 ms per frame) (Table V; Sec. III-A)","Modular, ROS-independent design with register-and-dispatch modules (Sec. I; Sec. II-A)",[28,29,30,31,32],"On the short KITTI raw sequence LIO-SAM is more accurate (RMSE 0.338 m versus 0.812 m) and ground truth is raw GPS (Table III; Sec. III-A)","The Scan Context variant can pick suboptimal loops and is slightly less accurate (Sec. III-A)","The Chilean mine test needed noisy ground truth as initial guess because scans were 30 to 40 m apart (Sec. III-A)","Moving objects are not removed; left to future work (Sec. IV)","ATE alignment method is not stated (Sec. III-A)",[34,35,36],"3D LiDAR point clouds (mandatory)","optional IMU for de-skewing in the pre-filterer and orientation constraints in the pose graph","optional GPS constraints and pre-computed odometry (Sec. II-A)",[38,39],"vehicle (KITTI)","static scan stations in an underground mine (Chilean underground mine dataset)","keyframe-based scan-to-keyframe registration of full filtered clouds with a user-selected method (ICP, GICP, VGICP or NDT), optionally seeded by a multi-scale pre-tracker or external odometry; g2o pose graph with odometry, floor-plane, loop and optional IMU and GPS constraints (Sec. II-C; Sec. II-D; Sec. II-G)","no feature extraction: downsampled and outlier-filtered full point clouds (octant-parallel filtering) are registered directly; floor plane by RANSAC on near-vertical-normal points or least-squares fitting on rough terrain (Sec. II-B; Sec. II-E)","discrete keyframe poses (motion always referred to the closest keyframe)","optional IMU-based de-skewing in the pre-filterer (ART-SLAM IMU variant); not described otherwise (Sec. II-A; Sec. III)","three steps: odometry-based candidate selection (far in accumulated distance, near in estimated position), Scan Context polar grids with a KD-tree to keep k candidates, then scan-to-scan matching and the best match added to the pose graph (Sec. II-F)","g2o pose-graph optimization (Sec. II-G)","keyframes storing point clouds, poses, timestamps and accumulated distance; 3D map assembled from keyframe clouds (Sec. II-C; Figs. 5-7)","none on KITTI; in the Chilean mine test the tracker received ground truth corrupted by uniform noise within plus or minus 1 cm as initial guess (Sec. III-A)","trajectory and 3D point cloud map (Figs. 5-7)","2021 XMG laptop with Intel Core i7-11800H at 2.30 GHz (8 cores); per frame about 18.6 ms pre-filtering (21.7 ms with IMU de-skewing), 39.5 ms tracking, 26.0 ms floor detection, 6.7-19.3 ms loop detection and 0.09-17.8 ms graph optimization; described as real time for 10 Hz data given the parallel modules (Sec. III; Table V)","https:\u002F\u002Fgithub.com\u002FMatteoF94\u002FARTSLAM","not stated (no LICENSE file; package.xml license tag is the placeholder 'TODO')",[53,57],{"relation":54,"title":55,"doi_or_url":56},"preprint","ART-SLAM (arXiv v1, 'currently under review'; uses KITTI and RADIATE and an older laptop, with different numbers from the published version)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2109.05483",{"relation":58,"title":59,"doi_or_url":50},"code_release","MatteoF94\u002FARTSLAM (artslam_laser_3d; ROS wrapper in MatteoF94\u002FARTSLAM_WRAPPER)",{"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":50,"cluster":11,"topics":75,"mdpi":76,"verification":77,"label":6,"fulltextRoute":78,"versionRead":79,"addedByCensus":80},"method",[63,64],"Matteo Frosi","Matteo Matteucci","IEEE Robotics and Automation Letters","journal","IEEE","7(2):2692-2699","10.1109\u002Flra.2022.3144795","2109.05483","https:\u002F\u002Fdoi.org\u002F10.1109\u002FLRA.2022.3144795","2021-09-12","metadata_verified","not_applicable",[11],false,"confirmed","NTU institutional (Chrome)","IEEE Xplore version of record (HTML full text; Tables II-V transcribed from the published table images); arXiv v1 preprint also read for comparison",true,[82,89,94,100,105],{"category":83,"model":84,"canonical":84,"role":85,"dataset":86,"specs":87,"locator":88},"lidar","3D LiDAR (KITTI; model not named in the paper)","dataset sensor","KITTI odometry and KITTI raw","point clouds of about 130 K points at about 10 Hz","Sec. III; Sec. III-A",{"category":90,"model":91,"canonical":91,"role":85,"dataset":86,"specs":92,"locator":93},"imu","KITTI IMU (model not named in the paper)","about 10 Hz in the synchronized data, 100 Hz in the unsynchronized data used for LIO-SAM","Sec. III",{"category":95,"model":96,"canonical":96,"role":97,"dataset":98,"specs":99,"locator":88},"gnss","KITTI GPS (model not named in the paper)","reference or ground truth","KITTI raw city sequence 05","raw GPS used as ground truth for the short KITTI raw city sequence 05 and as low-weight constraints in the GPS variant",{"category":83,"model":101,"canonical":101,"role":85,"dataset":102,"specs":103,"locator":104},"LiDAR scans of the Chilean underground mine dataset (instrument not reported)","Chilean underground mine dataset","44 scans of about 25 M points each, taken 30 to 40 m apart with large rotations; 152.5 s per scan acquisition","Sec. III-A",{"category":106,"model":107,"canonical":107,"role":108,"dataset":109,"specs":110,"locator":93},"compute","Intel Core i7-11800H","compute for runtime",null,"2021 XMG 64-bit laptop, 2.30 GHz x 8 cores, 24576 KB cache",[],{"totalRows":113,"groupCount":114,"groups":115,"others":571},99,5,[116,299,408,492],{"slug":117,"group":118,"sourceId":5,"sourceLabel":6,"table":119,"selfRows":120,"metrics":121,"seqs":134,"entrants":144,"cells":185,"outcomes":292,"locators":293,"hardware":294,"wordings":296,"notes":297},"artslam2022-table-v","artslam2022:Table V","Table V",60,[122,126,128,130,132],{"label":123,"unit":124,"statistic":125,"alignment":74},"Pre-filterer processing time per frame [ms]","ms","mean",{"label":127,"unit":124,"statistic":125,"alignment":74},"Tracker processing time per frame [ms]",{"label":129,"unit":124,"statistic":125,"alignment":74},"Floor detector processing time per frame [ms]",{"label":131,"unit":124,"statistic":125,"alignment":74},"Loop detection processing time per frame [ms]",{"label":133,"unit":124,"statistic":125,"alignment":74},"Graph optimization processing time per frame [ms]",[135,139,141],{"dataset":136,"sequence":137,"environment":138},"KITTI odometry","KITTI 00","vehicle",{"dataset":136,"sequence":140,"environment":138},"KITTI 07",{"dataset":142,"sequence":143,"environment":138},"KITTI raw","KITTI SHORT (raw city 05)",[145,147,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183],{"name":146,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM, Pre-filterer",{"name":148,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM, Tracker",{"name":150,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM, Floor detector",{"name":152,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM, Loop detection",{"name":154,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM, Graph optimization",{"name":156,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (SC), Pre-filterer",{"name":158,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (SC), Tracker",{"name":160,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (SC), Floor detector",{"name":162,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (SC), Loop detection",{"name":164,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (SC), Graph optimization",{"name":166,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (IMU), Pre-filterer",{"name":168,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (IMU), Tracker",{"name":170,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (IMU), Floor detector",{"name":172,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (IMU), Loop detection",{"name":174,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (IMU), Graph optimization",{"name":176,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (GPS), Pre-filterer",{"name":178,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (GPS), Tracker",{"name":180,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (GPS), Floor detector",{"name":182,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (GPS), Loop detection",{"name":184,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (GPS), Graph optimization",[186,190,193,196,199,202,203,205,207,210,213,216,218,220,223,226,228,230,232,235,238,239,240,241,243,245,246,247,248,250,252,253,254,255,257,259,260,261,262,264,266,267,268,269,271,273,274,275,276,277,278,279,280,281,283,285,286,287,288,290],[187,187,187,188,189,187,187,189,187],0,18.627,-1,[191,191,187,192,189,187,187,189,187],1,39.462,[194,194,187,195,189,187,187,189,187],2,25.976,[197,197,187,198,189,187,187,189,187],3,19.301,[200,200,187,201,189,187,187,189,187],4,16.33,[114,187,187,188,189,187,187,189,187],[204,191,187,192,189,187,187,189,187],6,[206,194,187,195,189,187,187,189,187],7,[208,197,187,209,189,187,187,189,187],8,9.38,[211,200,187,212,189,187,187,189,187],9,17.791,[214,187,187,215,189,187,187,189,187],10,21.667,[217,191,187,192,189,187,187,189,187],11,[219,194,187,195,189,187,187,189,187],12,[221,197,187,222,189,187,187,189,187],13,13.747,[224,200,187,225,189,187,187,189,187],14,14.486,[227,187,187,188,189,187,187,189,187],15,[229,191,187,192,189,187,187,189,187],16,[231,194,187,195,189,187,187,189,187],17,[233,197,187,234,189,187,187,189,187],18,14.681,[236,200,187,237,189,187,187,189,187],19,12.733,[187,187,191,188,189,187,187,189,187],[191,191,191,192,189,187,187,189,187],[194,194,191,195,189,187,187,189,187],[197,197,191,242,189,187,187,189,187],10.226,[200,200,191,244,189,187,187,189,187],1.32,[114,187,191,188,189,187,187,189,187],[204,191,191,192,189,187,187,189,187],[206,194,191,195,189,187,187,189,187],[208,197,191,249,189,187,187,189,187],7.239,[211,200,191,251,189,187,187,189,187],1.598,[214,187,191,215,189,187,187,189,187],[217,191,191,192,189,187,187,189,187],[219,194,191,195,189,187,187,189,187],[221,197,191,256,189,187,187,189,187],9.808,[224,200,191,258,189,187,187,189,187],1.71,[227,187,191,188,189,187,187,189,187],[229,191,191,192,189,187,187,189,187],[231,194,191,195,189,187,187,189,187],[233,197,191,263,189,187,187,189,187],10.407,[236,200,191,265,189,187,187,189,187],1.331,[187,187,194,188,189,187,187,189,187],[191,191,194,192,189,187,187,189,187],[194,194,194,195,189,187,187,189,187],[197,197,194,270,189,187,187,189,187],6.819,[200,200,194,272,189,187,187,189,187],0.132,[114,187,194,188,189,187,187,189,187],[204,191,194,192,189,187,187,189,187],[206,194,194,195,189,187,187,189,187],[208,197,194,270,189,187,187,189,187],[211,200,194,272,189,187,187,189,187],[214,187,194,215,189,187,187,189,187],[217,191,194,192,189,187,187,189,187],[219,194,194,195,189,187,187,189,187],[221,197,194,282,189,187,187,189,187],6.72,[224,200,194,284,189,187,187,189,187],0.091,[227,187,194,188,189,187,187,189,187],[229,191,194,192,189,187,187,189,187],[231,194,194,195,189,187,187,189,187],[233,197,194,289,189,187,187,189,187],9.085,[236,200,194,291,189,187,187,189,187],0.165,[],[119],[295],"2021 XMG laptop, Intel Core i7-11800H 2.30 GHz x 8 cores",[],[298],"Average processing time per frame (ms) of mandatory modules for ART-SLAM variants",{"slug":300,"group":301,"sourceId":5,"sourceLabel":6,"table":302,"selfRows":219,"metrics":303,"seqs":314,"entrants":318,"cells":343,"outcomes":401,"locators":403,"hardware":404,"wordings":405,"notes":406},"artslam2022-table-ii","artslam2022:Table II","Table II",[304,308,311],{"label":305,"unit":306,"statistic":125,"alignment":307},"ATE [m], MEAN","m","not_reported",{"label":309,"unit":306,"statistic":310,"alignment":307},"ATE [m], RMSE","RMSE",{"label":312,"unit":306,"statistic":313,"alignment":307},"ATE [m], STD","std",[315],{"dataset":136,"sequence":316,"environment":317},"07","vehicle, urban",[319,322,325,328,330,333,336,337,339,341],{"name":320,"methodId":321,"linkable":80,"proposed":76,"self":76},"LOAM","loam2014",{"name":323,"methodId":324,"linkable":80,"proposed":76,"self":76},"LeGO-LOAM","legoloam2018",{"name":326,"methodId":327,"linkable":80,"proposed":76,"self":76},"A-LOAM","aloam_software",{"name":329,"methodId":109,"linkable":76,"proposed":76,"self":76},"LeGO-LOAM-BOR",{"name":331,"methodId":332,"linkable":80,"proposed":76,"self":76},"LIO-SAM","liosam2020",{"name":334,"methodId":335,"linkable":76,"proposed":76,"self":76},"HDL","koide2019_hdlgraphslam",{"name":7,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":338,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (SC)",{"name":340,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (IMU)",{"name":342,"methodId":5,"linkable":80,"proposed":80,"self":80},"ART-SLAM (GPS)",[344,345,346,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399],[187,187,187,109,187,187,189,189,187],[187,191,187,109,187,187,189,189,187],[187,194,187,109,187,187,189,189,187],[191,187,187,348,189,187,189,189,187],1.191,[191,191,187,350,189,187,189,189,187],1.309,[191,194,187,352,189,187,189,189,187],0.546,[194,187,187,354,189,187,189,189,187],2.467,[194,191,187,356,189,187,189,189,187],2.741,[194,194,187,358,189,187,189,189,187],1.195,[197,187,187,360,189,187,189,189,187],1.604,[197,191,187,362,189,187,189,189,187],1.807,[197,194,187,364,189,187,189,189,187],0.832,[200,187,187,366,189,187,189,189,187],0.509,[200,191,187,368,189,187,189,189,187],0.675,[200,194,187,370,189,187,189,189,187],0.351,[114,187,187,372,189,187,189,189,187],0.954,[114,191,187,374,189,187,189,189,187],1.253,[114,194,187,376,189,187,189,189,187],0.767,[204,187,187,378,189,187,189,189,187],0.698,[204,191,187,380,189,187,189,189,187],0.777,[204,194,187,382,189,187,189,189,187],0.341,[206,187,187,384,189,187,189,189,187],0.73,[206,191,187,386,189,187,189,189,187],0.813,[206,194,187,388,189,187,189,189,187],0.358,[208,187,187,390,189,187,189,189,187],0.343,[208,191,187,392,189,187,189,189,187],0.366,[208,194,187,394,189,187,189,189,187],0.127,[211,187,187,396,189,187,189,189,187],0.782,[211,191,187,398,189,187,189,189,187],0.869,[211,194,187,400,189,187,189,189,187],0.382,[402],">10 m (bound as printed)",[302],[],[],[407],"KITTI odometry 07 (with loop); ATE after timestamp and index association; ART-SLAM variants: plain, with Scan Context, with IMU (de-skewing and orientation), with GPS",{"slug":409,"group":410,"sourceId":5,"sourceLabel":6,"table":411,"selfRows":219,"metrics":412,"seqs":416,"entrants":420,"cells":431,"outcomes":485,"locators":487,"hardware":488,"wordings":489,"notes":490},"artslam2022-table-iii","artslam2022:Table III","Table III",[413,414,415],{"label":305,"unit":306,"statistic":125,"alignment":307},{"label":309,"unit":306,"statistic":310,"alignment":307},{"label":312,"unit":306,"statistic":313,"alignment":307},[417],{"dataset":142,"sequence":418,"environment":419},"city 05","vehicle, city",[421,422,423,424,425,426,427,428,429,430],{"name":320,"methodId":321,"linkable":80,"proposed":76,"self":76},{"name":323,"methodId":324,"linkable":80,"proposed":76,"self":76},{"name":326,"methodId":327,"linkable":80,"proposed":76,"self":76},{"name":329,"methodId":109,"linkable":76,"proposed":76,"self":76},{"name":331,"methodId":332,"linkable":80,"proposed":76,"self":76},{"name":334,"methodId":335,"linkable":76,"proposed":76,"self":76},{"name":7,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":338,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":340,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":342,"methodId":5,"linkable":80,"proposed":80,"self":80},[432,433,434,435,437,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,472,473,474,476,478,480,481,483],[187,187,187,109,187,187,189,189,187],[187,191,187,109,187,187,189,189,187],[187,194,187,109,187,187,189,189,187],[191,187,187,436,189,187,189,189,187],0.707,[191,191,187,438,189,187,189,189,187],0.768,[191,194,187,440,189,187,189,189,187],0.3,[194,187,187,442,189,187,189,189,187],0.938,[194,191,187,444,189,187,189,189,187],1.044,[194,194,187,446,189,187,189,189,187],0.459,[197,187,187,448,189,187,189,189,187],1.094,[197,191,187,450,189,187,189,189,187],1.169,[197,194,187,452,189,187,189,189,187],0.409,[200,187,187,454,189,187,189,189,187],0.493,[200,191,187,456,189,187,189,189,187],0.338,[200,194,187,458,189,187,189,189,187],0.28,[114,187,187,460,189,187,189,189,187],0.893,[114,191,187,462,189,187,189,189,187],0.912,[114,194,187,464,189,187,189,189,187],0.476,[204,187,187,466,189,187,189,189,187],0.742,[204,191,187,468,189,187,189,189,187],0.812,[204,194,187,470,189,187,189,189,187],0.331,[206,187,187,466,189,187,189,189,187],[206,191,187,468,189,187,189,189,187],[206,194,187,470,189,187,189,189,187],[208,187,187,475,189,187,189,189,187],0.746,[208,191,187,477,189,187,189,189,187],0.814,[208,194,187,479,189,187,189,189,187],0.326,[211,187,187,390,189,187,189,189,187],[211,191,187,482,189,187,189,189,187],0.588,[211,194,187,484,189,187,189,189,187],0.477,[486],">5 m (bound as printed)",[411],[],[],[491],"KITTI raw city sequence 05 (short, no ground truth); raw GPS used as reference; values as printed (LIO-SAM mean exceeds RMSE)",{"slug":493,"group":494,"sourceId":5,"sourceLabel":6,"table":495,"selfRows":219,"metrics":496,"seqs":500,"entrants":503,"cells":514,"outcomes":565,"locators":566,"hardware":567,"wordings":568,"notes":569},"artslam2022-table-iv","artslam2022:Table IV","Table IV",[497,498,499],{"label":305,"unit":306,"statistic":125,"alignment":307},{"label":309,"unit":306,"statistic":310,"alignment":307},{"label":312,"unit":306,"statistic":313,"alignment":307},[501],{"dataset":136,"sequence":502,"environment":317},"00",[504,505,506,507,508,509,510,511,512,513],{"name":320,"methodId":321,"linkable":80,"proposed":76,"self":76},{"name":323,"methodId":324,"linkable":80,"proposed":76,"self":76},{"name":326,"methodId":327,"linkable":80,"proposed":76,"self":76},{"name":329,"methodId":109,"linkable":76,"proposed":76,"self":76},{"name":331,"methodId":332,"linkable":80,"proposed":76,"self":76},{"name":334,"methodId":335,"linkable":76,"proposed":76,"self":76},{"name":7,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":338,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":340,"methodId":5,"linkable":80,"proposed":80,"self":80},{"name":342,"methodId":5,"linkable":80,"proposed":80,"self":80},[515,516,517,518,520,522,524,525,526,527,529,531,533,534,535,536,538,540,542,544,546,548,550,552,554,556,558,560,561,563],[187,187,187,109,187,187,189,189,187],[187,191,187,109,187,187,189,189,187],[187,194,187,109,187,187,189,189,187],[191,187,187,519,189,187,189,189,187],9.537,[191,191,187,521,189,187,189,189,187],11.666,[191,194,187,523,189,187,189,189,187],6.718,[194,187,187,109,187,187,189,189,187],[194,191,187,109,187,187,189,189,187],[194,194,187,109,187,187,189,189,187],[197,187,187,528,189,187,189,189,187],6.24,[197,191,187,530,189,187,189,189,187],6.613,[197,194,187,532,189,187,189,189,187],2.188,[200,187,187,109,187,187,189,189,187],[200,191,187,109,187,187,189,189,187],[200,194,187,109,187,187,189,189,187],[114,187,187,537,189,187,189,189,187],1.378,[114,191,187,539,189,187,189,189,187],1.424,[114,194,187,541,189,187,189,189,187],0.779,[204,187,187,543,189,187,189,189,187],0.981,[204,191,187,545,189,187,189,189,187],1.092,[204,194,187,547,189,187,189,189,187],0.478,[206,187,187,549,189,187,189,189,187],1.232,[206,191,187,551,189,187,189,189,187],1.409,[206,194,187,553,189,187,189,189,187],0.684,[208,187,187,555,189,187,189,189,187],0.907,[208,191,187,557,189,187,189,189,187],1.014,[208,194,187,559,189,187,189,189,187],0.454,[211,187,187,545,189,187,189,189,187],[211,191,187,562,189,187,189,189,187],1.156,[211,194,187,564,189,187,189,189,187],0.38,[402],[495],[],[],[570],"KITTI odometry 00 (long, with loops); ATE after timestamp and index association",[572],{"group":573,"slug":574,"sourceLabel":6,"table":575,"selfRows":197,"datasets":576},"artslam2022:Text Sec. III-A","artslam2022-text-sec-iii-a","Text Sec. III-A",[102],1790510662514]