[{"data":1,"prerenderedAt":1123},["ShallowReactive",2],{"method-loam2017_auro":3},{"method":4,"reference":70,"equipment":89,"figures":172,"results":173},{"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":25,"limitations":31,"sensors":40,"platform":46,"estimator":53,"association":54,"timeModel":55,"deskew":56,"loopClosure":57,"globalOptimization":58,"mapRepresentation":59,"prior":60,"outputGeometry":61,"compute":62,"codeUrl":63,"codeLicense":64,"relatedVersions":65},"loam2017_auro","Zhang & Singh, 2017","LOAM (journal version)","Low-drift and real-time lidar odometry and mapping",2017,"classic","C04","odometry_with_local_mapping","本記錄為 LOAM 的期刊版本（Autonomous Robots，2016-02-18 線上發表、2017 年卷期）。方法核心與 RSS 2014 版相同：高頻、低精度的里程計估計速度並去除點雲運動畸變，低頻（預設為里程計的十分之一）的建圖以更多特徵點精細配準；兩者都使用依局部平滑度挑出的邊緣點與平面點，以 Levenberg-Marquardt 搭配 bisquare 權重求解，IMU 僅為選用的前處理先驗，且不含迴圈閉合。相較 RSS 版，期刊版把驗證擴充到四種感測系統（含八旋翼機與 Velodyne HDL-32E 車載測試），建圖以 5 cm（邊緣）與 10 cm（平面）體素平均，並說明 KITTI 測試為求精度改為逐幀建圖、只達即時速度的約 10%。","Journal version of LOAM: same odometry-mapping split with smoothness-selected edge and planar features and robust LM, no loop closure; adds octo-rotor and HDL-32E vehicle tests, separate 5 cm and 10 cm voxel sizes for edge and planar maps, and notes that its KITTI runs used per-scan mapping at 10% of real time.","full_text_reviewed","peer_reviewed_published","background","not_reported（作者在引言主張在許多實務情況，例如建築物單一樓層的建圖，迴圈閉合並非必要；此為作者主張，論文未在營建工地或以工程幾何參考驗證，室內測試僅為既有建築走廊與大廳）。",[20,21,22,23,24],"public_benchmark","controlled_experiment","completed_building","independent_reference","cross_site",[26,27,28,29,30],"KITTI odometry benchmark: 0.88% average position error, ranked #2, and reported to outperform stereo visual odometry methods by over 14% in position and 24% in orientation error (Sec. 7.5)","Hokuyo drift tests at 0.5 m\u002Fs: corridor 0.9% (58 m) and 1.1% (46 m) from the start and end gap of a closed loop, orchard 2.3% (52 m) and 2.8% (67 m) against GPS\u002FINS (Table 2)","handheld tests with tape-ruler ground truth: IMU pre-processing plus the method gave the lowest error in all four scenes, e.g., corridor 0.9% versus 2.1% without IMU and 16.7% with IMU orientation only (Table 3)","HDL-32E campus run 1.0 km: horizontal drift \u003C=1 m, vertical drift \u003C=1.5 m, overall \u003C=0.2% of distance","street run 3.6 km: horizontal error \u003C=2 m, both from satellite-image matching (Sec. 7.4)",[32,33,34,35,36,37,38,39],"No loop closure","correcting drift by closing loops is left to future work (Sec. 1, 9)","KITTI accuracy was obtained with mapping on every scan, so the system ran at 10% of real-time speed (Sec. 7.5)","assumes smooth, continuous angular and linear velocity within a sweep unless an IMU pre-processes the data (Sec. 3, 7.2)","matching errors were larger in natural outdoor scenes than in indoor scenes (Sec. 7.1, Fig. 11)","octo-rotor flights had no ground truth and were judged only visually (Sec. 7.3)","vertical accuracy of the 3.6 km street run could not be evaluated (Sec. 7.4)","follow-up statements retained: LeGO-LOAM Sec. IV-D (10% real time) and LIO-SAM ref [1] (IMU used only for de-skewing and motion prior)",[41,42,43,44,45],"2-axis lidar: back-and-forth spinning Hokuyo UTM-30LX (Sec. 4.1)","continuously spinning Hokuyo on an octo-rotor (Sec. 7.3)","Velodyne HDL-32E (Sec. 7.4)","Velodyne HDL-64E via KITTI (Sec. 7.5)","IMU optional: Xsens MTi-10 (Sec. 7.2), Microstrain 3DM-GX3-45 (Sec. 7.3)",[47,48,49,50,51,52],"cart (pushed, indoor)","ground vehicle","handheld","octo-rotor micro aerial vehicle","utility vehicle and passenger vehicle","vehicle (KITTI)","Levenberg-Marquardt adapted to robust fitting with bisquare weights; odometry at scan rate and mapping at about one-tenth of that rate (ratio 10 preferred, Sec. 8); for KITTI the mapping ran every scan, giving 10% of real-time speed (Sec. 7.5)","edge and planar feature points selected by local smoothness; point-to-edge-line and point-to-planar-patch distances; KD-tree nearest neighbours (Sec. 5-6)","constant angular and linear velocity within a sweep, linear pose interpolation (Sec. 3-5)","odometry-estimated velocity used to reproject points; optional IMU pre-processing removes orientation change and part of the acceleration effect (Sec. 7.2)","none; authors state they do not consider loop closure (Sec. 1) and list it as future work (Sec. 9)","none","feature point cloud map stored in 10 m cubes with KD-tree search; voxel-grid averaging at 5 cm (edge) and 10 cm (planar); map truncated to a 500 m cube around the sensor (Sec. 6)","none (IMU optional)","registered feature point cloud map and 6-DoF pose (Sec. 6); dense raw-point export not described in the text read","Laptop with 2.5 GHz quad cores and 6 GiB memory, ROS on Linux, odometry and mapping on two separate threads (Sec. 7). Per-call totals: Hokuyo accuracy tests odometry 48 ms and mapping 309 ms (Table 1); Velodyne HDL-32E tests odometry 69 ms and mapping 563 ms (Table 4). For KITTI, mapping was run on every scan, about 1 s per scan, i.e., 10% of real-time speed (Sec. 7.5).",null,"not_verified",[66],{"relation":67,"title":68,"doi_or_url":69},"conference_version","LOAM: Lidar Odometry and Mapping in Real-time","10.15607\u002FRSS.2014.X.007",{"id":5,"kind":71,"shortName":7,"title":8,"authors":72,"year":9,"venue":75,"venueType":76,"publisher":77,"volumeIssuePages":78,"doi":79,"arxivId":63,"url":80,"firstPublicDate":81,"publicationStatus":16,"metadataStatus":82,"fulltextStatus":15,"era":10,"classicReason":83,"codeUrl":63,"cluster":11,"topics":84,"mdpi":85,"verification":86,"label":6,"fulltextRoute":87,"versionRead":88,"addedByCensus":85},"method",[73,74],"Ji Zhang","Sanjiv Singh","Autonomous Robots","journal","Springer","41(2): 401-416","10.1007\u002Fs10514-016-9548-2","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1007\u002Fs10514-016-9548-2","2016-02-18","metadata_verified","necessary technical node: archival journal version of LOAM (online 2016-02-18) that later papers cite together with, or instead of, the RSS 2014 paper (e.g., LeGO-LOAM refs [19]-[20], LIO-SAM ref [1]).",[11],false,"corrected","NTU institutional (curl)","version of record: Springer publisher PDF, Auton Robot (2017) 41:401-416, published online 2016-02-18 (16 pages)",[90,96,100,105,109,113,119,123,129,133,139,143,148,151,155,158,162,166],{"category":91,"model":92,"canonical":92,"role":93,"dataset":63,"specs":94,"locator":95},"lidar","Hokuyo UTM-30LX","method input","2D scanner turned into a 2-axis back-and-forth spinning lidar by a motor and an encoder (Fig. 2); 180 deg FoV, 0.25 deg resolution, 40 lines\u002Fs; motor rotates at 180 deg\u002Fs between -90 and 90 deg, one sweep lasts 1 s; onboard encoder with 0.25 deg resolution","Sec. 4.1, Fig. 2",{"category":91,"model":97,"canonical":97,"role":93,"dataset":63,"specs":98,"locator":99},"Hokuyo laser scanner","scanner model not stated; continuously spinning 2-axis lidar of the same design as Fig. 2; sweep is a semi-spherical rotation on the slow axis lasting 1 s","Sec. 7.3, Fig. 14",{"category":101,"model":102,"canonical":102,"role":93,"dataset":63,"specs":103,"locator":104},"imu","Xsens MTi-10","orientation from gyros and accelerometers fused in a Kalman filter; used to pre-process the point cloud","Sec. 7.2",{"category":101,"model":106,"canonical":106,"role":93,"dataset":63,"specs":107,"locator":108},"Microstrain 3DM-GX3-45","not_reported","Sec. 7.3",{"category":91,"model":110,"canonical":110,"role":93,"dataset":63,"specs":111,"locator":112},"Velodyne HDL-32E","single-axis scanner with 32 beams, 10 Hz by default; mounted high on vehicle roof","Sec. 7.4, Fig. 17",{"category":91,"model":114,"canonical":114,"role":115,"dataset":116,"specs":117,"locator":118},"Velodyne HDL-64E","dataset sensor","KITTI odometry","logged at 10 Hz","Sec. 7.5, Fig. 20",{"category":120,"model":121,"canonical":121,"role":115,"dataset":116,"specs":122,"locator":118},"stereo_camera","KITTI color and monochrome stereo cameras (model not stated)","not used by the method",{"category":124,"model":125,"canonical":125,"role":126,"dataset":116,"specs":127,"locator":128},"gnss","KITTI high accuracy GPS\u002FINS (model not stated)","reference or ground truth","ground truth for sequences 0-10","Sec. 7.5",{"category":124,"model":130,"canonical":130,"role":126,"dataset":63,"specs":131,"locator":132},"High accuracy GPS\u002FINS on the ground vehicle (model not stated)","ground truth for orchard drift tests","Sec. 7.1, Table 2",{"category":134,"model":135,"canonical":136,"role":126,"dataset":63,"specs":137,"locator":138},"other","Tape ruler","tape ruler","manual ground truth for handheld tests","Sec. 7.2, Table 3",{"category":134,"model":140,"canonical":140,"role":126,"dataset":63,"specs":141,"locator":142},"Satellite image","trajectory and building walls matched to it to judge horizontal drift","Sec. 7.4, Figs. 18-19",{"category":144,"model":145,"canonical":145,"role":93,"dataset":63,"specs":146,"locator":147},"platform","Pushed cart (indoor)","carries lidar, battery and laptop; pushed by a walking person at 0.5 m\u002Fs","Sec. 7.1, Fig. 10",{"category":144,"model":149,"canonical":149,"role":93,"dataset":63,"specs":150,"locator":147},"Ground vehicle (outdoor)","lidar mounted at the front; 0.5 m\u002Fs",{"category":144,"model":152,"canonical":152,"role":93,"dataset":63,"specs":153,"locator":154},"Handheld (person holding the lidar)","walking at 0.5 m\u002Fs while moving the lidar up and down about 0.5 m; staircase test","Sec. 7.2, Fig. 13",{"category":144,"model":156,"canonical":156,"role":93,"dataset":63,"specs":157,"locator":99},"Octo-rotor micro aerial vehicle","manually flown at 1 m\u002Fs",{"category":144,"model":159,"canonical":159,"role":93,"dataset":63,"specs":160,"locator":161},"Utility vehicle","sidewalks and off-road terrain; 2-3 m\u002Fs on 1.0 km campus run","Sec. 7.4, Fig. 17a",{"category":144,"model":163,"canonical":163,"role":93,"dataset":63,"specs":164,"locator":165},"Passenger vehicle","streets; mostly 11-18 m\u002Fs on 3.6 km run","Sec. 7.4, Fig. 17b",{"category":167,"model":168,"canonical":168,"role":169,"dataset":63,"specs":170,"locator":171},"compute","Laptop computer (model not stated)","compute for runtime","2.5 GHz quad cores, 6 GiB memory, ROS on Linux; odometry and mapping on two threads","Sec. 7",[],{"totalRows":174,"groupCount":175,"groups":176,"others":989},200,28,[177,496,759,816],{"slug":178,"group":179,"sourceId":180,"sourceLabel":181,"table":182,"selfRows":183,"metrics":184,"seqs":194,"entrants":214,"cells":237,"outcomes":488,"locators":490,"hardware":492,"wordings":493,"notes":494},"lonet2019-table-1","lonet2019:Table 1","lonet2019","Li et al., 2019","Table 1",22,[185,189,192],{"label":186,"unit":187,"statistic":188,"alignment":58},"t_rel: average translational RMSE (%) on length of 100 m-800 m","%","mean",{"label":190,"unit":191,"statistic":188,"alignment":58},"r_rel: average rotational RMSE (deg\u002F100 m) on length of 100 m-800 m","deg\u002F100m",{"label":193,"unit":187,"statistic":188,"alignment":58},"t_rel: average translational RMSE (%) on length of 100 m-800 m (bracketed value)",[195,198,200,202,204,206,208,212],{"dataset":116,"sequence":196,"environment":197},"07 (not used for training)","urban, country and highway driving, vehicle-mounted Velodyne HDL-64",{"dataset":116,"sequence":199,"environment":197},"08 (not used for training)",{"dataset":116,"sequence":201,"environment":197},"09 (not used for training)",{"dataset":116,"sequence":203,"environment":197},"10 (not used for training)",{"dataset":116,"sequence":205,"environment":197},"mean over 00-06 (training sequences)",{"dataset":116,"sequence":207,"environment":197},"mean over 07-10 (test sequences)",{"dataset":209,"sequence":210,"environment":211},"Ford Campus Vision and Lidar","Ford-1","urban campus driving with many moving vehicles, roof-mounted lidar",{"dataset":209,"sequence":213,"environment":211},"Ford-2",[215,219,222,225,227,229,231,233,235],{"name":216,"methodId":217,"linkable":218,"proposed":85,"self":85},"ICP-po2po (PCL)","besl1992icp",true,{"name":220,"methodId":221,"linkable":218,"proposed":85,"self":85},"ICP-po2pl (PCL)","chen1992pointtoplane",{"name":223,"methodId":224,"linkable":218,"proposed":85,"self":85},"GICP [30]","segal2009gicp",{"name":226,"methodId":63,"linkable":85,"proposed":85,"self":85},"CLS [34]",{"name":228,"methodId":5,"linkable":218,"proposed":85,"self":218},"LOAM [45] (authors' modified re-run)",{"name":230,"methodId":63,"linkable":85,"proposed":85,"self":85},"Velas et al. [35] (values from [35])",{"name":232,"methodId":180,"linkable":218,"proposed":218,"self":85},"LO-Net",{"name":234,"methodId":180,"linkable":218,"proposed":218,"self":85},"LO-Net+Mapping",{"name":236,"methodId":5,"linkable":218,"proposed":85,"self":218},"LOAM [45] (bracketed values quoted from the LOAM paper)",[238,242,245,247,249,252,254,257,259,262,264,267,269,272,274,277,279,281,283,285,287,289,291,293,295,297,299,301,303,304,306,308,310,312,314,316,318,319,321,323,325,327,329,331,333,335,337,339,341,343,345,346,348,350,352,354,356,358,360,362,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,394,396,398,400,402,404,405,406,407,409,410,412,413,415,416,418,419,420,421,422,423,425,427,429,430,432,434,436,438,440,442,444,446,448,449,451,453,455,456,458,460,461,463,464,466,468,469,471,473,475,476,478,479,481,483,484,485,487],[239,239,239,240,241,239,241,241,239],0,5.17,-1,[239,243,239,244,241,239,241,241,239],1,3.35,[239,239,243,246,241,239,241,241,239],10.04,[239,243,243,248,241,239,241,241,239],4.93,[239,239,250,251,241,239,241,241,239],2,6.93,[239,243,250,253,241,239,241,241,239],2.89,[239,239,255,256,241,239,241,241,239],3,8.91,[239,243,255,258,241,239,241,241,239],4.74,[239,239,260,261,241,239,241,241,239],4,7.13,[239,243,260,263,241,239,241,241,239],3.08,[239,239,265,266,241,239,241,241,239],5,7.76,[239,243,265,268,241,239,241,241,239],3.98,[239,239,270,271,241,239,241,241,239],6,8.2,[239,243,270,273,241,239,241,241,239],2.64,[239,239,275,276,241,239,241,241,239],7,16.23,[239,243,275,278,241,239,241,241,239],2.84,[243,239,239,280,241,239,241,241,239],1.55,[243,243,239,282,241,239,241,241,239],1.42,[243,239,243,284,241,239,241,241,239],4.42,[243,243,243,286,241,239,241,241,239],2.14,[243,239,250,288,241,239,241,241,239],3.95,[243,243,250,290,241,239,241,241,239],1.71,[243,239,255,292,241,239,241,241,239],6.13,[243,243,255,294,241,239,241,241,239],2.6,[243,239,260,296,241,239,241,241,239],5.15,[243,243,260,298,241,239,241,241,239],1.91,[243,239,265,300,241,239,241,241,239],4.01,[243,243,265,302,241,239,241,241,239],1.97,[243,239,270,244,241,239,241,241,239],[243,243,270,305,241,239,241,241,239],1.65,[243,239,275,307,241,239,241,241,239],5.68,[243,243,275,309,241,239,241,241,239],1.96,[250,239,239,311,241,239,241,241,239],0.64,[250,243,239,313,241,239,241,241,239],0.45,[250,239,243,315,241,239,241,241,239],1.58,[250,243,243,317,241,239,241,241,239],0.75,[250,239,250,302,241,239,241,241,239],[250,243,250,320,241,239,241,241,239],0.77,[250,239,255,322,241,239,241,241,239],1.31,[250,243,255,324,241,239,241,241,239],0.62,[250,239,260,326,241,239,241,241,239],2.23,[250,243,260,328,241,239,241,241,239],0.78,[250,239,265,330,241,239,241,241,239],1.38,[250,243,265,332,241,239,241,241,239],0.65,[250,239,270,334,241,239,241,241,239],3.07,[250,243,270,336,241,239,241,241,239],1.17,[250,239,275,338,241,239,241,241,239],5.11,[250,243,275,340,241,239,241,241,239],1.47,[255,239,239,342,241,239,241,241,239],1.04,[255,243,239,344,241,239,241,241,239],0.73,[255,239,243,286,241,239,241,241,239],[255,243,243,347,241,239,241,241,239],1.05,[255,239,250,349,241,239,241,241,239],1.95,[255,243,250,351,241,239,241,241,239],0.92,[255,239,255,353,241,239,241,241,239],3.46,[255,243,255,355,241,239,241,241,239],1.28,[255,239,260,357,241,239,241,241,239],2.11,[255,243,260,359,241,239,241,241,239],0.86,[255,239,265,361,241,239,241,241,239],2.15,[255,243,265,243,241,239,241,241,239],[255,239,270,364,241,239,241,241,239],10.54,[255,243,270,366,241,239,241,241,239],3.9,[255,239,275,368,241,239,241,241,239],14.78,[255,243,275,370,241,239,241,241,239],4.6,[260,239,239,372,241,239,241,241,239],0.69,[260,243,239,374,241,239,241,241,239],0.5,[260,239,243,376,241,239,241,241,239],1.18,[260,243,243,378,241,239,241,241,239],0.44,[260,239,250,380,241,239,241,241,239],1.2,[260,243,250,382,241,239,241,241,239],0.48,[260,239,255,384,241,239,241,241,239],1.51,[260,243,255,386,241,239,241,241,239],0.57,[260,239,260,388,241,239,241,241,239],1.35,[260,243,260,390,241,239,241,241,239],0.51,[260,239,265,392,241,239,241,241,239],1.15,[260,243,265,374,241,239,241,241,239],[260,239,270,395,241,239,241,241,239],1.68,[260,243,270,397,241,239,241,241,239],0.54,[260,239,275,399,241,239,241,241,239],1.78,[260,243,275,401,241,239,241,241,239],0.49,[265,239,239,403,241,239,241,241,239],1.77,[265,243,239,63,239,239,241,241,239],[265,239,243,253,241,239,241,241,239],[265,243,243,63,239,239,241,241,239],[265,239,250,408,241,239,241,241,239],4.94,[265,243,250,63,239,239,241,241,239],[265,239,255,411,241,239,241,241,239],3.27,[265,243,255,63,239,239,241,241,239],[265,239,260,414,241,239,241,241,239],3.12,[265,243,260,63,239,239,241,241,239],[265,239,265,417,241,239,241,241,239],3.22,[265,243,265,63,239,239,241,241,239],[265,239,270,63,239,239,241,241,239],[265,243,270,63,239,239,241,241,239],[265,239,275,63,239,239,241,241,239],[265,243,275,63,239,239,241,241,239],[270,239,239,424,241,239,241,241,239],1.7,[270,243,239,426,241,239,241,241,239],0.89,[270,239,243,428,241,239,241,241,239],2.12,[270,243,243,320,241,239,241,241,239],[270,239,250,431,241,239,241,241,239],1.37,[270,243,250,433,241,239,241,241,239],0.58,[270,239,255,435,241,239,241,241,239],1.8,[270,243,255,437,241,239,241,241,239],0.93,[270,239,260,439,241,239,241,241,239],1.09,[270,243,260,441,241,239,241,241,239],0.63,[270,239,265,443,241,239,241,241,239],1.75,[270,243,265,445,241,239,241,241,239],0.79,[270,239,270,447,241,239,241,241,239],2.27,[270,243,270,324,241,239,241,241,239],[270,239,275,450,241,239,241,241,239],2.18,[270,243,275,452,241,239,241,241,239],0.59,[275,239,239,454,241,239,241,241,239],0.56,[275,243,239,313,241,239,241,241,239],[275,239,243,457,241,239,241,241,239],1.08,[275,243,243,459,241,239,241,241,239],0.43,[275,239,250,320,241,239,241,241,239],[275,243,250,462,241,239,241,241,239],0.38,[275,239,255,351,241,239,241,241,239],[275,243,255,465,241,239,241,241,239],0.41,[275,239,260,467,241,239,241,241,239],0.81,[275,243,260,378,241,239,241,241,239],[275,239,265,470,241,239,241,241,239],0.83,[275,243,265,472,241,239,241,241,239],0.42,[275,239,270,474,241,239,241,241,239],1.1,[275,243,270,374,241,239,241,241,239],[275,239,275,477,241,239,241,241,239],1.29,[275,243,275,378,241,239,241,241,239],[480,250,239,441,241,243,241,241,239],8,[480,250,243,482,241,243,241,241,239],1.12,[480,250,250,320,241,243,241,241,239],[480,250,255,445,241,243,241,241,239],[480,250,260,486,241,243,241,241,239],0.85,[480,250,265,470,241,243,241,241,239],[489],"not_reported (NA)",[182,491],"Table 1, footnote 1",[],[],[495],"KITTI odometry metric: t_rel = average translational RMSE (%) and r_rel = average rotational RMSE (deg\u002F100 m) over 100-800 m lengths. LO-Net trained on KITTI 00-06 and tested on 07-10 and on Ford without fine-tuning; loop closure disabled for all methods. LOAM values outside brackets come from the authors' modified re-run; bracketed values are quoted from the LOAM paper [45]. Velas et al. values quoted from [35] (r_rel and Ford NA). ICP variants run with PCL. Truncated: per-sequence rows 00-06 (training sequences) omitted; the mean over them (mean-dagger) is kept.",{"slug":497,"group":498,"sourceId":499,"sourceLabel":500,"table":182,"selfRows":501,"metrics":502,"seqs":511,"entrants":537,"cells":559,"outcomes":753,"locators":754,"hardware":755,"wordings":756,"notes":757},"pwclonet2021-table-1","pwclonet2021:Table 1","pwclonet2021","Wang et al., 2021c",13,[503,507,509],{"label":504,"unit":187,"statistic":505,"alignment":506},"trel (average translational RMSE, %)","RMSE","not_applicable",{"label":508,"unit":187,"statistic":505,"alignment":506},"Mean on 07-10, trel",{"label":510,"unit":191,"statistic":505,"alignment":506},"Mean on 07-10, rrel (deg\u002F100m)",[512,515,517,519,521,523,525,527,529,531,533,535],{"dataset":116,"sequence":513,"environment":514},"00* (training)","vehicle, road",{"dataset":116,"sequence":516,"environment":514},"01* (training)",{"dataset":116,"sequence":518,"environment":514},"02* (training)",{"dataset":116,"sequence":520,"environment":514},"03* (training)",{"dataset":116,"sequence":522,"environment":514},"04* (training)",{"dataset":116,"sequence":524,"environment":514},"05* (training)",{"dataset":116,"sequence":526,"environment":514},"06* (training)",{"dataset":116,"sequence":528,"environment":514},"07 (test)",{"dataset":116,"sequence":530,"environment":514},"08 (test)",{"dataset":116,"sequence":532,"environment":514},"09 (test)",{"dataset":116,"sequence":534,"environment":514},"10 (test)",{"dataset":116,"sequence":536,"environment":514},"mean on 07-10 (test)",[538,540,542,544,546,548,550,552,554,557],{"name":539,"methodId":5,"linkable":218,"proposed":85,"self":218},"Full LOAM [31]",{"name":541,"methodId":217,"linkable":218,"proposed":85,"self":85},"ICP-po2po",{"name":543,"methodId":221,"linkable":218,"proposed":85,"self":85},"ICP-po2pl",{"name":545,"methodId":224,"linkable":218,"proposed":85,"self":85},"GICP [19]",{"name":547,"methodId":63,"linkable":85,"proposed":85,"self":85},"CLS [21]",{"name":549,"methodId":63,"linkable":85,"proposed":85,"self":85},"Velas et al. [22]",{"name":551,"methodId":180,"linkable":218,"proposed":85,"self":85},"LO-Net [10]",{"name":553,"methodId":63,"linkable":85,"proposed":85,"self":85},"DMLO [11]",{"name":555,"methodId":556,"linkable":218,"proposed":85,"self":85},"LOAM w\u002Fo mapping (published code run by authors)","loam2014",{"name":558,"methodId":499,"linkable":218,"proposed":218,"self":85},"Ours (PWCLO-Net)",[560,561,563,565,567,569,570,572,573,574,576,578,581,583,585,587,589,591,593,595,596,597,598,599,600,602,604,606,608,609,611,613,615,616,617,618,619,620,622,624,625,627,629,630,632,634,635,636,637,638,639,641,643,644,646,647,649,651,653,654,655,656,657,658,660,662,664,666,668,669,670,672,674,675,676,677,678,680,681,683,685,687,688,689,691,692,693,694,695,697,699,700,701,702,703,705,707,709,711,713,715,717,719,720,722,724,726,728,730,732,733,735,736,738,740,741,743,745,747,748,750,752],[239,239,239,474,241,239,241,241,239],[239,239,243,562,241,239,241,241,239],2.79,[239,239,250,564,241,239,241,241,239],1.54,[239,239,255,566,241,239,241,241,239],1.13,[239,239,260,568,241,239,241,241,239],1.45,[239,239,265,317,241,239,241,241,239],[239,239,270,571,241,239,241,241,239],0.72,[239,239,275,372,241,239,241,241,239],[239,239,480,376,241,239,241,241,239],[239,239,575,380,241,239,241,241,239],9,[239,239,577,384,241,239,241,241,239],10,[239,243,579,580,241,239,241,241,239],11,1.145,[239,250,579,582,241,239,241,241,239],0.498,[243,239,239,584,241,239,241,241,239],6.88,[243,239,243,586,241,239,241,241,239],11.21,[243,239,250,588,241,239,241,241,239],8.21,[243,239,255,590,241,239,241,241,239],11.07,[243,239,260,592,241,239,241,241,239],6.64,[243,239,265,594,241,239,241,241,239],3.97,[243,239,270,349,241,239,241,241,239],[243,239,275,240,241,239,241,241,239],[243,239,480,246,241,239,241,241,239],[243,239,575,251,241,239,241,241,239],[243,239,577,256,241,239,241,241,239],[243,243,579,601,241,239,241,241,239],7.763,[243,250,579,603,241,239,241,241,239],3.978,[250,239,239,605,241,239,241,241,239],3.8,[250,239,243,607,241,239,241,241,239],13.53,[250,239,250,575,241,239,241,241,239],[250,239,255,610,241,239,241,241,239],2.72,[250,239,260,612,241,239,241,241,239],2.96,[250,239,265,614,241,239,241,241,239],2.29,[250,239,270,403,241,239,241,241,239],[250,239,275,280,241,239,241,241,239],[250,239,480,284,241,239,241,241,239],[250,239,575,288,241,239,241,241,239],[250,239,577,292,241,239,241,241,239],[250,243,579,621,241,239,241,241,239],4.013,[250,250,579,623,241,239,241,241,239],1.968,[255,239,239,477,241,239,241,241,239],[255,239,243,626,241,239,241,241,239],4.39,[255,239,250,628,241,239,241,241,239],2.53,[255,239,255,395,241,239,241,241,239],[255,239,260,631,241,239,241,241,239],3.76,[255,239,265,633,241,239,241,241,239],1.02,[255,239,270,351,241,239,241,241,239],[255,239,275,311,241,239,241,241,239],[255,239,480,315,241,239,241,241,239],[255,239,575,302,241,239,241,241,239],[255,239,577,322,241,239,241,241,239],[255,243,579,640,241,239,241,241,239],1.375,[255,250,579,642,241,239,241,241,239],0.648,[260,239,239,357,241,239,241,241,239],[260,239,243,645,241,239,241,241,239],4.22,[260,239,250,614,241,239,241,241,239],[260,239,255,648,241,239,241,241,239],1.63,[260,239,260,650,241,239,241,241,239],1.59,[260,239,265,652,241,239,241,241,239],1.98,[260,239,270,351,241,239,241,241,239],[260,239,275,342,241,239,241,241,239],[260,239,480,286,241,239,241,241,239],[260,239,575,349,241,239,241,241,239],[260,239,577,353,241,239,241,241,239],[260,243,579,659,241,239,241,241,239],2.148,[260,250,579,661,241,239,241,241,239],0.995,[265,239,239,663,241,239,241,241,239],3.02,[265,239,243,665,241,239,241,241,239],4.44,[265,239,250,667,241,239,241,241,239],3.42,[265,239,255,408,241,239,241,241,239],[265,239,260,403,241,239,241,241,239],[265,239,265,671,241,239,241,241,239],2.35,[265,239,270,673,241,239,241,241,239],1.88,[265,239,275,403,241,239,241,241,239],[265,239,480,253,241,239,241,241,239],[265,239,575,408,241,239,241,241,239],[265,239,577,411,241,239,241,241,239],[265,243,579,679,241,239,241,241,239],3.218,[270,239,239,340,241,239,241,241,239],[270,239,243,682,241,239,241,241,239],1.36,[270,239,250,684,241,239,241,241,239],1.52,[270,239,255,686,241,239,241,241,239],1.03,[270,239,260,390,241,239,241,241,239],[270,239,265,342,241,239,241,241,239],[270,239,270,690,241,239,241,241,239],0.71,[270,239,275,424,241,239,241,241,239],[270,239,480,428,241,239,241,241,239],[270,239,575,431,241,239,241,241,239],[270,239,577,435,241,239,241,241,239],[270,243,579,696,241,239,241,241,239],1.748,[270,250,579,698,241,239,241,241,239],0.793,[275,239,275,344,241,239,241,241,239],[275,239,480,457,241,239,241,241,239],[275,239,575,474,241,239,241,241,239],[275,239,577,482,241,239,241,241,239],[275,243,579,704,241,239,241,241,239],1.008,[275,250,579,706,241,239,241,241,239],0.538,[480,239,239,708,241,239,241,241,239],15.99,[480,239,243,710,241,239,241,241,239],3.43,[480,239,250,712,241,239,241,241,239],9.4,[480,239,255,714,241,239,241,241,239],18.18,[480,239,260,716,241,239,241,241,239],9.59,[480,239,265,718,241,239,241,241,239],9.16,[480,239,270,256,241,239,241,241,239],[480,239,275,721,241,239,241,241,239],10.87,[480,239,480,723,241,239,241,241,239],12.72,[480,239,575,725,241,239,241,241,239],8.1,[480,239,577,727,241,239,241,241,239],12.67,[480,243,579,729,241,239,241,241,239],11.09,[480,250,579,731,241,239,241,241,239],6.405,[575,239,239,328,241,239,241,241,239],[575,239,243,734,241,239,241,241,239],0.67,[575,239,250,359,241,239,241,241,239],[575,239,255,737,241,239,241,241,239],0.76,[575,239,260,739,241,239,241,241,239],0.37,[575,239,265,313,241,239,241,241,239],[575,239,270,742,241,239,241,241,239],0.27,[575,239,275,744,241,239,241,241,239],0.6,[575,239,480,746,241,239,241,241,239],1.26,[575,239,575,445,241,239,241,241,239],[575,239,577,749,241,239,241,241,239],1.69,[575,243,579,751,241,239,241,241,239],1.085,[575,250,579,401,241,239,241,241,239],[],[182],[],[],[758],"KITTI odometry, trained on 00-06 (marked *) and tested on 07-10; trel = average translational RMSE (%) over 100-800 m subsequences; rows other than LOAM w\u002Fo mapping and Ours are copied from LO-Net [10]; LOAM is a full system with mapping, others are odometry only",{"slug":760,"group":761,"sourceId":5,"sourceLabel":6,"table":762,"selfRows":763,"metrics":764,"seqs":767,"entrants":781,"cells":788,"outcomes":810,"locators":811,"hardware":812,"wordings":813,"notes":814},"loam2017-auro-table-3","loam2017_auro:Table 3","Table 3",12,[765],{"label":766,"unit":187,"statistic":107,"alignment":107},"motion estimation error relative to distance (tape-ruler ground truth)",[768,772,775,778],{"dataset":769,"sequence":770,"environment":771},"author-collected handheld Hokuyo datasets","Corridor (32 m)","corridor",{"dataset":769,"sequence":773,"environment":774},"Lobby (27 m)","lobby",{"dataset":769,"sequence":776,"environment":777},"Vegetated road (43 m)","vegetated road",{"dataset":769,"sequence":779,"environment":780},"Orchard (51 m)","orchard",[782,784,786],{"name":783,"methodId":5,"linkable":218,"proposed":85,"self":218},"IMU (orientation from IMU only, translation from the method)",{"name":785,"methodId":5,"linkable":218,"proposed":218,"self":218},"Ours (no IMU)",{"name":787,"methodId":5,"linkable":218,"proposed":218,"self":218},"Ours+IMU (IMU pre-processing followed by the method)",[789,791,793,795,797,798,800,802,804,805,807,809],[239,239,239,790,241,239,241,241,239],16.7,[243,239,239,792,241,239,241,241,239],2.1,[250,239,239,794,241,239,241,241,239],0.9,[239,239,243,796,241,239,241,241,239],11.7,[243,239,243,424,241,239,241,241,239],[250,239,243,799,241,239,241,241,239],1.3,[239,239,250,801,241,239,241,241,239],13.7,[243,239,250,803,241,239,241,241,239],4.4,[250,239,250,294,241,239,241,241,239],[239,239,255,806,241,239,241,241,239],11.4,[243,239,255,808,241,239,241,241,239],3.7,[250,239,255,792,241,239,241,241,239],[],[762],[],[],[815],"Motion estimation errors with and without IMU; handheld lidar, 0.5 m\u002Fs walking, ground truth by tape ruler",{"slug":817,"group":818,"sourceId":819,"sourceLabel":820,"table":821,"selfRows":763,"metrics":822,"seqs":827,"entrants":852,"cells":871,"outcomes":983,"locators":984,"hardware":985,"wordings":986,"notes":987},"saloam2021-table-ii","saloam2021:Table II","saloam2021","Li et al., 2021a","Table II",[823,825],{"label":824,"unit":187,"statistic":188,"alignment":506},"relative translational error (%)",{"label":826,"unit":187,"statistic":188,"alignment":506},"relative translational error (%), Average",[828,830,832,834,836,838,840,842,844,846,848,850],{"dataset":116,"sequence":829,"environment":514},"00*",{"dataset":116,"sequence":831,"environment":514},"01",{"dataset":116,"sequence":833,"environment":514},"02*",{"dataset":116,"sequence":835,"environment":514},"03",{"dataset":116,"sequence":837,"environment":514},"04",{"dataset":116,"sequence":839,"environment":514},"05*",{"dataset":116,"sequence":841,"environment":514},"06*",{"dataset":116,"sequence":843,"environment":514},"07*",{"dataset":116,"sequence":845,"environment":514},"08*",{"dataset":116,"sequence":847,"environment":514},"09*",{"dataset":116,"sequence":849,"environment":514},"10",{"dataset":116,"sequence":851,"environment":514},"Average 00-10",[853,855,858,861,864,867,869],{"name":854,"methodId":5,"linkable":218,"proposed":85,"self":218},"LOAM* (from [19])",{"name":856,"methodId":857,"linkable":218,"proposed":85,"self":85},"FLOAM","floam2021",{"name":859,"methodId":860,"linkable":218,"proposed":85,"self":85},"ISC-LOAM","iscloam2020",{"name":862,"methodId":863,"linkable":218,"proposed":85,"self":85},"SUMA","suma2018",{"name":865,"methodId":866,"linkable":218,"proposed":85,"self":85},"SUMA++","sumapp2019",{"name":868,"methodId":819,"linkable":218,"proposed":218,"self":85},"Ours-ODOM",{"name":870,"methodId":819,"linkable":218,"proposed":218,"self":85},"Ours-LOOP",[872,873,875,876,877,878,879,880,881,882,883,884,886,887,889,891,892,893,894,895,896,898,899,900,902,903,905,907,908,910,911,912,913,914,916,918,919,920,922,924,926,927,928,929,931,933,934,936,937,938,939,941,942,944,946,947,949,951,952,953,955,956,958,959,961,962,963,965,966,967,969,970,971,972,973,974,975,976,977,978,979,980,981,982],[239,239,239,328,241,239,241,241,239],[239,239,243,874,241,239,241,241,239],1.43,[239,239,250,351,241,239,241,241,239],[239,239,255,359,241,239,241,241,239],[239,239,260,690,241,239,241,241,239],[239,239,265,386,241,239,241,241,239],[239,239,270,332,241,239,241,241,239],[239,239,275,441,241,239,241,241,239],[239,239,480,482,241,239,241,241,239],[239,239,575,320,241,239,241,241,239],[239,239,577,445,241,239,241,241,239],[239,243,579,885,241,239,241,241,239],0.84,[243,239,239,351,241,239,241,241,239],[243,239,243,888,241,239,241,241,239],2.8,[243,239,250,890,241,239,241,241,239],1.56,[243,239,255,439,241,239,241,241,239],[243,239,260,874,241,239,241,241,239],[243,239,265,445,241,239,241,241,239],[243,239,270,571,241,239,241,241,239],[243,239,275,397,241,239,241,241,239],[243,239,480,897,241,239,241,241,239],1.11,[243,239,575,355,241,239,241,241,239],[243,239,577,403,241,239,241,241,239],[243,243,579,901,241,239,241,241,239],1.27,[250,239,239,633,241,239,241,241,239],[250,239,243,904,241,239,241,241,239],2.92,[250,239,250,906,241,239,241,241,239],1.67,[250,239,255,392,241,239,241,241,239],[250,239,260,909,241,239,241,241,239],1.5,[250,239,265,467,241,239,241,241,239],[250,239,270,737,241,239,241,241,239],[250,239,275,454,241,239,241,241,239],[250,239,480,380,241,239,241,241,239],[250,239,575,915,241,239,241,241,239],1.4,[250,239,577,917,241,239,241,241,239],1.87,[250,243,579,388,241,239,241,241,239],[255,239,239,320,241,239,241,241,239],[255,239,243,921,241,239,241,241,239],11.15,[255,239,250,923,241,239,241,241,239],2.93,[255,239,255,925,241,239,241,241,239],1.25,[255,239,260,359,241,239,241,241,239],[255,239,265,454,241,239,241,241,239],[255,239,270,311,241,239,241,241,239],[255,239,275,930,241,239,241,241,239],0.47,[255,239,480,932,241,239,241,241,239],1.06,[255,239,575,445,241,239,241,241,239],[255,239,577,935,241,239,241,241,239],0.99,[255,243,579,349,241,239,241,241,239],[260,239,239,332,241,239,241,241,239],[260,239,243,648,241,239,241,241,239],[260,239,250,940,241,239,241,241,239],3.54,[260,239,255,734,241,239,241,241,239],[260,239,260,943,241,239,241,241,239],0.34,[260,239,265,945,241,239,241,241,239],0.4,[260,239,270,930,241,239,241,241,239],[260,239,275,948,241,239,241,241,239],0.39,[260,239,480,950,241,239,241,241,239],1.01,[260,239,575,433,241,239,241,241,239],[260,239,577,734,241,239,241,241,239],[260,243,579,954,241,239,241,241,239],0.94,[265,239,239,452,241,239,241,241,239],[265,239,243,957,241,239,241,241,239],1.89,[265,239,250,320,241,239,241,241,239],[265,239,255,960,241,239,241,241,239],0.87,[265,239,260,452,241,239,241,241,239],[265,239,265,313,241,239,241,241,239],[265,239,270,964,241,239,241,241,239],0.52,[265,239,275,465,241,239,241,241,239],[265,239,480,486,241,239,241,241,239],[265,239,575,968,241,239,241,241,239],0.68,[265,239,577,328,241,239,241,241,239],[265,243,579,737,241,239,241,241,239],[270,239,239,452,241,239,241,241,239],[270,239,243,957,241,239,241,241,239],[270,239,250,445,241,239,241,241,239],[270,239,255,960,241,239,241,241,239],[270,239,260,452,241,239,241,241,239],[270,239,265,739,241,239,241,241,239],[270,239,270,964,241,239,241,241,239],[270,239,275,465,241,239,241,241,239],[270,239,480,885,241,239,241,241,239],[270,239,575,320,241,239,241,241,239],[270,239,577,328,241,239,241,241,239],[270,243,579,737,241,239,241,241,239],[],[821],[],[],[988],"KITTI odometry 00-10; mean relative pose error over 100-800 m trajectories (rotation deg\u002F100m \u002F translation %); * marks sequences with loops; LOAM values quoted from its journal paper [19]; other baselines run with open-source code",[990,996,1001,1007,1013,1018,1023,1028,1033,1039,1045,1052,1057,1064,1069,1075,1079,1085,1091,1096,1101,1105,1112,1118],{"group":991,"slug":992,"sourceLabel":993,"table":821,"selfRows":763,"datasets":994},"suma2018:Table II","suma2018-table-ii","Behley & Stachniss, 2018",[995],"KITTI odometry (training)",{"group":997,"slug":998,"sourceLabel":999,"table":821,"selfRows":763,"datasets":1000},"sumapp2019:Table II","sumapp2019-table-ii","Chen et al., 2019",[995],{"group":1002,"slug":1003,"sourceLabel":1004,"table":1005,"selfRows":579,"datasets":1006},"imlsslam2018:Table I","imlsslam2018-table-i","Deschaud, 2018","Table I",[116],{"group":1008,"slug":1009,"sourceLabel":1010,"table":1011,"selfRows":579,"datasets":1012},"litamin2_2021:Table III","litamin2-2021-table-iii","Yokozuka et al., 2021","Table III",[116],{"group":1014,"slug":1015,"sourceLabel":6,"table":1016,"selfRows":579,"datasets":1017},"loam2017_auro:Table 5","loam2017-auro-table-5","Table 5",[116],{"group":1019,"slug":1020,"sourceLabel":1021,"table":182,"selfRows":579,"datasets":1022},"mc2slam2019:Table 1","mc2slam2019-table-1","Neuhaus et al., 2019",[116],{"group":1024,"slug":1025,"sourceLabel":1026,"table":821,"selfRows":579,"datasets":1027},"ndtloam2022:Table II","ndtloam2022-table-ii","Chen et al., 2022b",[116],{"group":1029,"slug":1030,"sourceLabel":6,"table":182,"selfRows":480,"datasets":1031},"loam2017_auro:Table 1","loam2017-auro-table-1",[1032],"author-collected Hokuyo datasets",{"group":1034,"slug":1035,"sourceLabel":6,"table":1036,"selfRows":480,"datasets":1037},"loam2017_auro:Table 4","loam2017-auro-table-4","Table 4",[1038],"author-collected Velodyne HDL-32E datasets",{"group":1040,"slug":1041,"sourceLabel":1042,"table":1005,"selfRows":480,"datasets":1043},"voxgraph2020:Table I","voxgraph2020-table-i","Reijgwart et al., 2020",[1044],"Voxgraph MAV field dataset (this paper)",{"group":1046,"slug":1047,"sourceLabel":1048,"table":821,"selfRows":270,"datasets":1049},"lvisam2021:Table II","lvisam2021-table-ii","Shan et al., 2021",[1050,1051],"Handheld (authors' data)","Jackal (authors' data)",{"group":1053,"slug":1054,"sourceLabel":1055,"table":821,"selfRows":270,"datasets":1056},"nubert2021delora:Table II","nubert2021delora-table-ii","Nubert et al., 2021",[116],{"group":1058,"slug":1059,"sourceLabel":1060,"table":1061,"selfRows":265,"datasets":1062},"liosam2020:Table IV","liosam2020-table-iv","Shan et al., 2020","Table IV",[1063],"Own LIO-SAM datasets",{"group":1065,"slug":1066,"sourceLabel":6,"table":1067,"selfRows":260,"datasets":1068},"loam2017_auro:Table 2","loam2017-auro-table-2","Table 2",[1032],{"group":1070,"slug":1071,"sourceLabel":6,"table":1072,"selfRows":260,"datasets":1073},"loam2017_auro:Text Sec. 7.4","loam2017-auro-text-sec-7-4","Text Sec. 7.4",[1074],"author-collected HDL-32E",{"group":1076,"slug":1077,"sourceLabel":1060,"table":821,"selfRows":255,"datasets":1078},"liosam2020:Table II","liosam2020-table-ii",[1063],{"group":1080,"slug":1081,"sourceLabel":6,"table":1082,"selfRows":250,"datasets":1083},"loam2017_auro:Text Sec. 7.5","loam2017-auro-text-sec-7-5","Text Sec. 7.5",[116,1084],"KITTI odometry benchmark",{"group":1086,"slug":1087,"sourceLabel":993,"table":1088,"selfRows":250,"datasets":1089},"suma2018:Text Sec. IV","suma2018-text-sec-iv","Text Sec. IV",[1090],"KITTI odometry (test)",{"group":1092,"slug":1093,"sourceLabel":1004,"table":1094,"selfRows":243,"datasets":1095},"imlsslam2018:Text Sec. VI-B","imlsslam2018-text-sec-vi-b","Text Sec. VI-B",[116],{"group":1097,"slug":1098,"sourceLabel":1004,"table":1099,"selfRows":243,"datasets":1100},"imlsslam2018:Text Sec. VI-C","imlsslam2018-text-sec-vi-c","Text Sec. VI-C",[116],{"group":1102,"slug":1103,"sourceLabel":1060,"table":1011,"selfRows":243,"datasets":1104},"liosam2020:Table III","liosam2020-table-iii",[1063],{"group":1106,"slug":1107,"sourceLabel":1108,"table":1109,"selfRows":243,"datasets":1110},"molalo2025:Table 7","molalo2025-table-7","Blanco-Claraco, 2025","Table 7",[1111],"Voxgraph dataset",{"group":1113,"slug":1114,"sourceLabel":1115,"table":1116,"selfRows":243,"datasets":1117},"zhang2024_3dlidarslam_survey:Table 8","zhang2024-3dlidarslam-survey-table-8","Zhang et al., 2024a","Table 8",[116],{"group":1119,"slug":1120,"sourceLabel":1115,"table":1121,"selfRows":243,"datasets":1122},"zhang2024_3dlidarslam_survey:Table 9","zhang2024-3dlidarslam-survey-table-9","Table 9",[116],1790510658678]