[{"data":1,"prerenderedAt":522},["ShallowReactive",2],{"method-roloam2022":3},{"method":4,"reference":54,"equipment":74,"figures":114,"results":115},{"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":26,"sensors":35,"platform":39,"estimator":41,"association":42,"timeModel":43,"deskew":44,"loopClosure":45,"globalOptimization":46,"mapRepresentation":47,"prior":48,"outputGeometry":49,"compute":50,"codeUrl":51,"codeLicense":52,"relatedVersions":53},"roloam2022","Oelsch et al., 2022","RO-LOAM","RO-LOAM: 3D Reference Object-based Trajectory and Map Optimization in LiDAR Odometry and Mapping",2022,"recent","C04","localization_in_prior_map_or_bim","RO-LOAM 是可外掛在 LiDAR SLAM 上的「參考物件式軌跡與地圖最佳化」：LOAM 本身不修改，每隔 L 幅掃描便把最近 M+1 幅裁切後的掃描以 ICP 對齊到已知參考物件的稠密點雲模型，再以 EKF 運動先驗檢查最後一個對齊位姿是否與前序一致（0.05 m 與 0.5 度內），通過者以高權重加入兩次修正之間的位姿圖，最佳化後重新插入過去掃描以修正 LOAM 地圖。實驗以八旋翼無人機搭載由 Dynamixel 致動器旋轉的 Velodyne VLP-16，在機庫內沿 B737 單側飛行三次，以 Leica Nova MS60 追蹤稜鏡作為地面真值；啟用後 LOAM 的中位數 APE 由約 67 至 81 cm 降到約 6.4 至 6.8 cm，且可在邊緣雲端伺服器上線上執行。","RO-LOAM periodically aligns short sequences of isolated scans to a known reference point-cloud model with ICP, accepts the last pose only if it agrees with an EKF motion prior, and uses it as a high-weight pose-graph constraint to correct the trajectory since the previous correction and to rebuild the LOAM map; on three real UAV hangar flights it cut LOAM median APE from about 67-81 cm to about 6.4-6.8 cm while running online on a server.","full_text_reviewed","peer_reviewed_published","main_body","作者在引言指出，建築 CAD 模型或以 BIM 相關高精度設備取得的稠密點雲可作為參考物件，並回顧營建工地 In situ Fabricator 與以 CAD 模型定位施工機器人的研究（Sec. I, II）。本文驗證僅在機庫內 B737 單側目視檢測的三組 UAV 飛行資料，參考模型由 Leica Nova MS60 掃描建立，並非 BIM 模型，也不是營建工地；地面真值為全測站追蹤稜鏡的三自由度位置。（推論）以參考模型間歇修正軌跡與地圖的架構可延伸到以 BIM 或既有點雲作為先驗的營建掃描，但竣工幾何與模型的偏差會直接影響結果（Sec. VI）。",[20,21],"completed_building","independent_reference",[23,24,25],"Median APE of map-optimized poses fell from 71.1, 67.2 and 80.6 cm (LOAM) to 6.5, 6.4 and 6.8 cm (LOAM + RO), and from 11.5, 9.6 and 15.3 cm (R-LOAM) to 5.9, 5.2 and 6.7 cm (R-LOAM + RO) on datasets 1 to 3 (Table IV, means of 5 runs)","over 50 successful TMOs per dataset with max APE below 30 cm and median below 5 cm (Sec. V)","nearly no extra onboard computation when run remotely (Sec. V)",[27,28,29,30,31,32,33,34],"Relies on an accurate initial relative pose between robot and reference object","any error directly harms TMO (Sec. VI)","deviations between model and actual geometry increase scan-to-model error (Sec. VI)","not a standalone SLAM algorithm (Sec. VI)","only 7-16% of scan-to-model aligned poses reach APE below 10 cm, so pure model-based localization would fail (Table I, Sec. V)","online results not fully reproducible, reported as means of 5 runs (Sec. V)","ground truth is 3-DoF position only","evaluated in one hangar scenario with three flights",[36,37,38],"Velodyne VLP-16 (10 Hz) on a Dynamixel actuator rotating the LiDAR about the roll axis within +\u002F-40 deg","actuator readings transform scans to the robot frame","Intel NUC logs data to SSD (Sec. III-A, IV-A)",[40],"octocopter UAV flown by an operator inside an aircraft hangar along one side of a B737 (Sec. IV-A, Fig. 3)","Unmodified LOAM (A-LOAM) map-optimized poses; every L scans the latest M+1 isolated scans (each with more than 50 points, downsampled to 500) are aligned to the reference point-cloud model by ICP with Huber loss and Levenberg-Marquardt (1 m max correspondence distance, 100 iterations, 2 s cap); the last pose is a candidate if its MSE is below 0.001 and it lies within 0.05 m and 0.5 deg of an EKF motion prior (ROS robot_localization, R = 0.01 I) built from the previous aligned poses; accepted poses become high-confidence constraints in a Ceres pose graph; final setting M = 9, L = 15 (Sec. III-C to III-E, IV-B, V)","raw scans transformed to the world frame with actuator readings and LOAM poses, cropped to the reference object by a bounding box, then point-to-point nearest-neighbour correspondences to the dense model point cloud within 1 m (Sec. III-B, III-C)","discrete per-scan poses; the LiDAR actuation is removed with actuator readings (Sec. III-A)","actuator motion compensated with actuator readings before LOAM; no ego-motion deskew beyond LOAM defaults is described (Sec. III-A)","none; global correction comes from model-aligned trajectory and map optimization (TMO); authors state it may complement relocalization or loop closure methods (Sec. VI)","subgraph between consecutive TMOs: first node (previous TMO) fixed, relative-pose edges with identity information, the new TMO constraint weighted 4000 I; Ceres Levenberg-Marquardt with Huber loss (Sec. III-E)","LOAM voxelized feature map in a cube structure; corrected by reinserting previous scans with pose-graph-optimized poses (Sec. III-A, III-F)","known location and geometry of a large static reference object (CAD from BIM or dense point cloud); experiments use a dense B737 point cloud with over 1.6 M points and 1.4 cm mean nearest-neighbour distance scanned by a Leica Nova MS60; the object-to-LiDAR relative pose is estimated before each flight from the first 20 static scans with RMSE below 3 cm (Sec. I, IV-A, IV-B)","corrected trajectory and corrected LOAM feature map (Fig. 5); no map accuracy metric is reported","designed to be offloaded to an edge cloud in parallel threads; experiments online with 10 Hz scans on a server with 32 Intel Xeon E5-2690 @2.90 GHz CPUs and 132 GB memory; LOAM mapping frequency 2.6 to 3.3 Hz across configurations (Sec. IV-B, V, Table IV)",null,"not_verified",[],{"id":5,"kind":55,"shortName":7,"title":8,"authors":56,"year":9,"venue":60,"venueType":61,"publisher":62,"volumeIssuePages":63,"doi":64,"arxivId":51,"url":65,"firstPublicDate":66,"publicationStatus":16,"metadataStatus":67,"fulltextStatus":15,"era":10,"classicReason":68,"codeUrl":51,"cluster":11,"topics":69,"mdpi":70,"verification":71,"label":6,"fulltextRoute":72,"versionRead":73,"addedByCensus":70},"method",[57,58,59],"Martin Oelsch","Mojtaba Karimi","Eckehard Steinbach","IEEE Robotics and Automation Letters","journal","IEEE","7(3): 6806-6813","10.1109\u002Flra.2022.3177846","https:\u002F\u002Fapi.semanticscholar.org\u002Fgraph\u002Fv1\u002Fpaper\u002FDOI:10.1109\u002FLRA.2022.3177846","2022-05-25","metadata_verified","not_applicable",[11],false,"corrected","NTU institutional (Chrome)","version of record: IEEE Xplore HTML full text, IEEE RA-L 7(3):6806-6813 (published 25 May 2022); Tables I-IV read from the publisher's table images",[75,81,86,91,96,102,106,109],{"category":76,"model":77,"canonical":77,"role":78,"dataset":51,"specs":79,"locator":80},"lidar","Velodyne VLP-16","method input","10 Hz update rate; continuously rotated about the roll axis within +\u002F-40 deg","Sec. IV-A",{"category":82,"model":83,"canonical":83,"role":78,"dataset":51,"specs":84,"locator":85},"other","Dynamixel actuator (model not stated)","rotates the LiDAR about the roll axis between +\u002F-40 deg; readings used for the LiDAR-to-robot transform","Sec. III-A, IV-A",{"category":87,"model":88,"canonical":88,"role":78,"dataset":51,"specs":89,"locator":90},"platform","Octocopter UAV (model not stated)","controlled by an operator inside a hangar along one side of a B737","Sec. IV-A, Fig. 3a",{"category":92,"model":93,"canonical":93,"role":94,"dataset":51,"specs":95,"locator":80},"compute","Intel NUC (onboard)","dataset sensor","saves LiDAR data on an SSD for offline evaluation",{"category":97,"model":98,"canonical":98,"role":99,"dataset":51,"specs":100,"locator":101},"total_station","Leica Nova MS60 MultiStation","reference or ground truth","measures ground-truth 3-DoF position (no rotation) of a mini prism on a rod","Sec. IV-A, Fig. 3b",{"category":103,"model":98,"canonical":98,"role":78,"dataset":51,"specs":104,"locator":105},"tls_scanner","its scanning functionality generated the B737 reference point cloud: over 1.6 M points, mean nearest-neighbour distance 1.4 cm (Sec. IV-A, Fig. 1)","Sec. IV-A, Fig. 1",{"category":82,"model":107,"canonical":107,"role":99,"dataset":51,"specs":108,"locator":80},"Leica mini prism on a rod","low-weight prism mounted on top of a rod for good visibility throughout the flight; its 3-DoF position measured by the MS60 is the ground truth",{"category":92,"model":110,"canonical":110,"role":111,"dataset":51,"specs":112,"locator":113},"Server with 32 Intel Xeon E5-2690 CPUs","compute for runtime","2.90 GHz, 132 GB memory; all experiments run online with 10 Hz scans","Sec. IV-B",[],{"totalRows":116,"groupCount":117,"groups":118,"others":521},109,4,[119,357,420,480],{"slug":120,"group":121,"sourceId":5,"sourceLabel":6,"table":122,"selfRows":123,"metrics":124,"seqs":154,"entrants":163,"cells":179,"outcomes":350,"locators":351,"hardware":352,"wordings":354,"notes":355},"roloam2022-table-iv","roloam2022:Table IV","Table IV",60,[125,130,133,136,139,143,145,147,149,151],{"label":126,"unit":127,"statistic":128,"alignment":129},"APE mapping (cm), max","cm","max","not_reported",{"label":131,"unit":127,"statistic":132,"alignment":129},"APE mapping (cm), mean","mean",{"label":134,"unit":127,"statistic":135,"alignment":129},"APE mapping (cm), median","median",{"label":137,"unit":127,"statistic":138,"alignment":129},"APE mapping (cm), RMSE","RMSE",{"label":140,"unit":141,"statistic":132,"alignment":142},"Freq. (Hz) mapping","Hz","none",{"label":144,"unit":127,"statistic":128,"alignment":129},"APE TMO (cm), max",{"label":146,"unit":127,"statistic":132,"alignment":129},"APE TMO (cm), mean",{"label":148,"unit":127,"statistic":135,"alignment":129},"APE TMO (cm), median",{"label":150,"unit":127,"statistic":138,"alignment":129},"APE TMO (cm), RMSE",{"label":152,"unit":153,"statistic":132,"alignment":142},"#TMOs (successful trajectory and map optimizations)","count",[155,159,161],{"dataset":156,"sequence":157,"environment":158},"RO-LOAM hangar datasets (octocopter, VLP-16, Leica MS60 ground truth)","Dataset 1","aircraft hangar, one side of a B737 (visual inspection)",{"dataset":156,"sequence":160,"environment":158},"Dataset 2",{"dataset":156,"sequence":162,"environment":158},"Dataset 3",[164,168,170,172,175,177],{"name":165,"methodId":166,"linkable":167,"proposed":70,"self":70},"LOAM [1]","aloam_software",true,{"name":169,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO",{"name":171,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (TMO poses)",{"name":173,"methodId":174,"linkable":167,"proposed":70,"self":70},"R-LOAM [2]","rloam2021",{"name":176,"methodId":5,"linkable":167,"proposed":167,"self":167},"R-LOAM + RO",{"name":178,"methodId":5,"linkable":167,"proposed":167,"self":167},"R-LOAM + RO (TMO poses)",[180,184,187,190,193,195,197,199,201,203,204,207,210,213,216,219,221,223,225,227,229,231,233,235,237,238,240,241,243,245,246,248,250,252,254,256,258,260,261,263,265,267,268,269,270,271,273,275,276,278,280,282,284,285,287,288,290,291,293,295,297,299,301,303,305,307,309,311,313,315,316,318,320,321,322,324,326,328,330,332,333,335,337,338,340,341,343,345,347,348],[181,181,181,182,183,181,183,183,181],0,466.3,-1,[181,185,181,186,183,181,183,183,181],1,134.6,[181,188,181,189,183,181,183,183,181],2,71.1,[181,191,181,192,183,181,183,183,181],3,182.7,[181,117,181,194,183,181,181,183,181],3.3,[185,181,181,196,183,181,183,183,181],84.2,[185,185,181,198,183,181,183,183,181],8.9,[185,188,181,200,183,181,183,183,181],6.5,[185,191,181,202,183,181,183,183,181],13.6,[185,117,181,191,183,181,181,183,181],[188,205,181,206,183,181,183,183,181],5,20.3,[188,208,181,209,183,181,183,183,181],6,5.2,[188,211,181,212,183,181,183,183,181],7,4.2,[188,214,181,215,183,181,183,183,181],8,6.4,[185,217,181,218,183,181,183,183,181],9,62,[191,181,181,220,183,181,183,183,181],50.7,[191,185,181,222,183,181,183,183,181],12.6,[191,188,181,224,183,181,183,183,181],11.5,[191,191,181,226,183,181,183,183,181],14.4,[191,117,181,228,183,181,181,183,181],3.1,[117,181,181,230,183,181,183,183,181],57.8,[117,185,181,232,183,181,183,183,181],8.1,[117,188,181,234,183,181,183,183,181],5.9,[117,191,181,236,183,181,183,183,181],10.5,[117,117,181,228,183,181,181,183,181],[205,205,181,239,183,181,183,183,181],22.9,[205,208,181,209,183,181,183,183,181],[205,211,181,242,183,181,183,183,181],4.1,[205,214,181,244,183,181,183,183,181],6.7,[117,217,181,218,183,181,183,183,181],[181,181,185,247,183,181,183,183,181],423.2,[181,185,185,249,183,181,183,183,181],117.1,[181,188,185,251,183,181,183,183,181],67.2,[181,191,185,253,183,181,183,183,181],164.7,[181,117,185,255,183,181,181,183,181],2.9,[185,181,185,257,183,181,183,183,181],89.7,[185,185,185,259,183,181,183,183,181],9.6,[185,188,185,215,183,181,183,183,181],[185,191,185,262,183,181,183,183,181],15.7,[185,117,185,264,183,181,181,183,181],2.6,[188,205,185,266,183,181,183,183,181],18.2,[188,208,185,117,183,181,183,183,181],[188,211,185,194,183,181,183,183,181],[188,214,185,209,183,181,183,183,181],[185,217,185,218,183,181,183,183,181],[191,181,185,272,183,181,183,183,181],58.4,[191,185,185,274,183,181,183,183,181],10.3,[191,188,185,259,183,181,183,183,181],[191,191,185,277,183,181,183,183,181],12.4,[191,117,185,279,183,181,181,183,181],2.8,[117,181,185,281,183,181,183,183,181],65,[117,185,185,283,183,181,183,183,181],7.2,[117,188,185,209,183,181,183,183,181],[117,191,185,286,183,181,183,183,181],10.4,[117,117,185,264,183,181,181,183,181],[205,205,185,289,183,181,183,183,181],16.8,[205,208,185,242,183,181,183,183,181],[205,211,185,292,183,181,183,183,181],3.6,[205,214,185,294,183,181,183,183,181],5.1,[117,217,185,296,183,181,183,183,181],64,[181,181,188,298,183,181,183,183,181],354.8,[181,185,188,300,183,181,183,183,181],123.8,[181,188,188,302,183,181,183,183,181],80.6,[181,191,188,304,183,181,183,183,181],154.8,[181,117,188,306,183,181,181,183,181],3.2,[185,181,188,308,183,181,183,183,181],88.4,[185,185,188,310,183,181,183,183,181],13.2,[185,188,188,312,183,181,183,183,181],6.8,[185,191,188,314,183,181,183,183,181],21.8,[185,117,188,255,183,181,181,183,181],[188,205,188,317,183,181,183,183,181],28.1,[188,208,188,319,183,181,183,183,181],4.6,[188,211,188,292,183,181,183,183,181],[188,214,188,200,183,181,183,183,181],[185,217,188,323,183,181,183,183,181],54,[191,181,188,325,183,181,183,183,181],69.7,[191,185,188,327,183,181,183,183,181],16.9,[191,188,188,329,183,181,183,183,181],15.3,[191,191,188,331,183,181,183,183,181],19.4,[191,117,188,191,183,181,181,183,181],[117,181,188,334,183,181,183,183,181],54.8,[117,185,188,336,183,181,183,183,181],9.3,[117,188,188,244,183,181,183,183,181],[117,191,188,339,183,181,183,183,181],12.2,[117,117,188,191,183,181,181,183,181],[205,205,188,342,183,181,183,183,181],23.9,[205,208,188,344,183,181,183,183,181],5.3,[205,211,188,346,183,181,183,183,181],3.9,[205,214,188,283,183,181,183,183,181],[117,217,188,349,183,181,183,183,181],58,[],[122],[353],"server with 32 Intel Xeon CPUs E5-2690 @2.90 GHz and 132 GB memory (Sec. IV-B)",[],[356],"Three hangar datasets with M = 9 and L = 15; means of 5 online runs; APE mapping = map-optimized poses, APE TMO = poses used for TMO; 3-DoF position ground truth from Leica MS60",{"slug":358,"group":359,"sourceId":5,"sourceLabel":6,"table":360,"selfRows":361,"metrics":362,"seqs":368,"entrants":370,"cells":379,"outcomes":414,"locators":415,"hardware":416,"wordings":417,"notes":418},"roloam2022-table-ii","roloam2022:Table II","Table II",20,[363,364,365,366,367],{"label":126,"unit":127,"statistic":128,"alignment":129},{"label":131,"unit":127,"statistic":132,"alignment":129},{"label":134,"unit":127,"statistic":135,"alignment":129},{"label":137,"unit":127,"statistic":138,"alignment":129},{"label":152,"unit":153,"statistic":129,"alignment":142},[369],{"dataset":156,"sequence":157,"environment":158},[371,373,375,377],{"name":372,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (M = 4, L = 50)",{"name":374,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (M = 9, L = 50)",{"name":376,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (M = 19, L = 50)",{"name":378,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (M = 29, L = 50)",[380,382,384,385,386,388,390,392,394,396,398,400,402,404,406,408,410,411,412,413],[181,181,181,381,183,181,183,183,181],79.5,[181,185,181,383,183,181,183,183,181],11.7,[181,188,181,217,183,181,183,183,181],[181,191,181,289,183,181,183,183,181],[181,117,181,387,183,181,183,183,181],18,[185,181,181,389,183,181,183,183,181],94.9,[185,185,181,391,183,181,183,183,181],9.9,[185,188,181,393,183,181,183,183,181],6.3,[185,191,181,395,183,181,183,183,181],16.6,[185,117,181,397,183,181,183,183,181],25,[188,181,181,399,183,181,183,183,181],96.7,[188,185,181,401,183,181,183,183,181],13.7,[188,188,181,403,183,181,183,183,181],9.1,[188,191,181,405,183,181,183,183,181],20.4,[188,117,181,407,183,181,183,183,181],19,[191,181,181,409,183,181,183,183,181],58.5,[191,185,181,224,183,181,183,183,181],[191,188,181,198,183,181,183,183,181],[191,191,181,262,183,181,183,183,181],[191,117,181,361,183,181,183,183,181],[],[360],[],[],[419],"Parameter study on Dataset 1 for LOAM + RO with L = 50; APE of map-optimized poses (cm) and number of successful TMOs",{"slug":421,"group":422,"sourceId":5,"sourceLabel":6,"table":423,"selfRows":361,"metrics":424,"seqs":430,"entrants":432,"cells":441,"outcomes":474,"locators":475,"hardware":476,"wordings":477,"notes":478},"roloam2022-table-iii","roloam2022:Table III","Table III",[425,426,427,428,429],{"label":126,"unit":127,"statistic":128,"alignment":129},{"label":131,"unit":127,"statistic":132,"alignment":129},{"label":134,"unit":127,"statistic":135,"alignment":129},{"label":137,"unit":127,"statistic":138,"alignment":129},{"label":152,"unit":153,"statistic":129,"alignment":142},[431],{"dataset":156,"sequence":157,"environment":158},[433,435,437,439],{"name":434,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (L = 15, M = 9)",{"name":436,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (L = 100, M = 9)",{"name":438,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (L = 200, M = 9)",{"name":440,"methodId":5,"linkable":167,"proposed":167,"self":167},"LOAM + RO (L = 300, M = 9)",[442,443,444,445,446,447,449,451,453,455,457,459,461,463,465,466,468,469,471,473],[181,181,181,196,183,181,183,183,181],[181,185,181,198,183,181,183,183,181],[181,188,181,200,183,181,183,183,181],[181,191,181,401,183,181,183,183,181],[181,117,181,218,183,181,183,183,181],[185,181,181,448,183,181,183,183,181],96.3,[185,185,181,450,183,181,183,183,181],17,[185,188,181,452,183,181,183,183,181],11.6,[185,191,181,454,183,181,183,183,181],24.4,[185,117,181,456,183,181,183,183,181],12,[188,181,181,458,183,181,183,183,181],91.9,[188,185,181,460,183,181,183,183,181],17.3,[188,188,181,462,183,181,183,183,181],13.3,[188,191,181,464,183,181,183,183,181],23,[188,117,181,208,183,181,183,183,181],[191,181,181,467,183,181,183,183,181],92.6,[191,185,181,454,183,181,183,183,181],[191,188,181,470,183,181,183,183,181],17.4,[191,191,181,472,183,181,183,183,181],31,[191,117,181,117,183,181,183,183,181],[],[423],[],[],[479],"Parameter study on Dataset 1 for LOAM + RO with M = 9; APE of map-optimized poses (cm) and number of successful TMOs",{"slug":481,"group":482,"sourceId":5,"sourceLabel":6,"table":483,"selfRows":217,"metrics":484,"seqs":492,"entrants":496,"cells":499,"outcomes":515,"locators":516,"hardware":517,"wordings":518,"notes":519},"roloam2022-table-i","roloam2022:Table I","Table I",[485,488,490],{"label":486,"unit":487,"statistic":129,"alignment":129},"scan-to-model aligned poses with APE \u003C 10 cm","%",{"label":489,"unit":487,"statistic":129,"alignment":129},"scan-to-model aligned poses with APE \u003C 50 cm",{"label":491,"unit":487,"statistic":129,"alignment":129},"scan-to-model aligned poses with APE \u003C 100 cm",[493,494,495],{"dataset":156,"sequence":157,"environment":158},{"dataset":156,"sequence":160,"environment":158},{"dataset":156,"sequence":162,"environment":158},[497],{"name":498,"methodId":5,"linkable":167,"proposed":167,"self":167},"scan-to-model alignment (ICP) initialized with LOAM poses",[500,501,503,504,506,508,509,511,513],[181,181,181,217,183,181,183,183,181],[181,181,185,502,183,181,183,183,181],16,[181,181,188,211,183,181,183,183,181],[181,185,181,505,183,181,183,183,181],32,[181,185,185,507,183,181,183,183,181],41,[181,185,188,397,183,181,183,183,181],[181,188,181,510,183,181,183,183,181],50,[181,188,185,512,183,181,183,183,181],59,[181,188,188,514,183,181,183,183,181],39,[],[483],[],[],[520],"Share of scan-to-model aligned poses below an APE threshold, using LOAM map-optimized poses as initial guess",[],1790510656016]