[{"data":1,"prerenderedAt":848},["ShallowReactive",2],{"method-rtabmap2019":3},{"method":4,"reference":62,"equipment":81,"figures":138,"results":139},{"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":25,"sensors":29,"platform":37,"estimator":42,"association":43,"timeModel":44,"deskew":45,"loopClosure":46,"globalOptimization":47,"mapRepresentation":48,"prior":49,"outputGeometry":50,"compute":51,"codeUrl":52,"codeLicense":53,"relatedVersions":54},"rtabmap2019","Labbé & Michaud, 2019","RTAB-Map","RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation",2019,"recent","C08","full_slam_with_global_correction","RTAB-Map 起源於具記憶體管理的外觀式迴圈偵測，將節點在工作記憶與長期記憶之間轉移，使迴圈偵測在固定時間內完成，以支援大範圍與長期線上運作。擴充版成為以圖為基礎的 SLAM 函式庫，可接收任意來源的里程計，並支援 RGB-D、雙目及 2D\u002F3D LiDAR，後端可選 TORO、g2o 或 GTSAM。論文以同一系統比較視覺與 LiDAR 組態在 KITTI、EuRoC、TUM RGB-D 與 MIT Stata Center 資料上的表現，輸出包括點雲、OctoMap 與佔據格地圖。","RTAB-Map is a graph-based SLAM library with memory-managed appearance-based loop closure that accepts any odometry and RGB-D, stereo or LiDAR inputs, used to compare visual and LiDAR configurations on several datasets.","full_text_reviewed","peer_reviewed_published","main_body","原論文未報告營建工地測試（評估含 MIT Stata Center 既有建築）。Shang 與 Shen 在施工現場以無人機搭載 RealSense R200 並使用 RTAB-Map 建立點雲，以攝影測量為參考比較，見 [shang2018_uav_vslam]。",[20,21],"public_benchmark","completed_building",[23,24],"add: WheelIMU→S2M had the lowest or equal-lowest ATEend and ATEmax among the compared 2D lidar SLAM systems on both MIT Stata Center sequences (Table 9)","with memory management the combined two-session run stayed real time with the same final ATE of 12 cm (Sec. 5.1)",[26,27,28],"add: bag-of-words loop closure depends on a camera and lidar refinement runs only after visual motion estimation succeeds (Sec. 6)","short-range lidar odometry without wheel odometry drifted along corridors (S2S ATEend 11 m on 12-14-25) (Table 8, Sec. 4.4)","RGB-D depth is poor beyond about 4 m, stereo cannot see textureless ground, and glass or reflective objects make light-based sensing unsafe for navigation (Sec. 4.4, 5, 6)",[30,31,32,33,34,35,36],"RGB-D","stereo","2D LiDAR","3D LiDAR","wheel odometry","IMU only through external odometry (wheel and IMU EKF) or integrated visual-inertial odometry such as OKVIS, MSCKF and Google Tango (Sec. 3.1.1, 4.3, 4.4)","the bag-of-words loop closure needs a camera, and without one the authors suggest feeding an empty image and relying on laser proximity detection only (Sec. 6)",[38,39,40,41],"wheeled UGV","vehicle","UAV","handheld","graph-based SLAM with selectable back-ends TORO, g2o or GTSAM; odometry from any external or built-in visual\u002FLiDAR source (Fig. 1; back-end paragraph)","visual odometry: GFTT features with BRIEF descriptors matched by NNDR to a local feature map (F2M) or tracked by optical flow to the last keyframe (F2F), constant-velocity prediction, PnP RANSAC and local BA with g2o; lidar odometry: libpointmatcher ICP, point-to-point or point-to-plane, scan-to-scan or scan-to-map; loop closure: incremental bag-of-words with TF-IDF and a Bayes filter, transform from visual PnP optionally refined by ICP; proximity detection by laser scans for nearby graph nodes (Sec. 3.1, 3.4)","discrete poses (graph nodes created at a fixed detection rate)","no internal deskewing: laser scans are assumed to be motion-distortion corrected before input to RTAB-Map; authors note correction can be ignored when scanner rotation is fast relative to robot speed (Sec. 3.1.2)","appearance-based loop closure detection with memory management (working, short-term and long-term memory) to bound detection time; proximity detection (abstract; Fig. 1)","pose-graph optimisation with TORO, g2o or GTSAM (GTSAM default); loop and proximity links rejected when their optimised change exceeds RGBD\u002FOptimizeMaxError times the translational variance; multi-session mapping (Sec. 3.5, 5.1)","pose graph with node sensor data; assembled 2D occupancy grid, OctoMap and point cloud outputs (Fig. 1)","none; multi-session map reuse","assembled point cloud (voxel-filtered, PointCloud2), OctoMap and 2D occupancy grid ROS outputs built from per-node local grids and re-assembled after loop closure (Fig. 1, Fig. 8, Sec. 3.6); file export features of the application not described in the paper","Intel Core i7-3770 (four cores), 6 GB RAM, 512 GB SSD, Ubuntu 16.04; offline datasets on one core, MIT Stata Center online in ROS (Sec. 4); average odometry time 15 to 25 ms for lidar and 32 to 100 ms for visual configurations on MIT Stata Center (Table 8); memory management adds about 52 ms on average and keeps updates within the 2 Hz limit (Sec. 5.1); ORB2-RTAB needed 1600 MB RAM versus 230 MB for the other visual configurations (Sec. 4.4)","https:\u002F\u002Fgithub.com\u002Fintrolab\u002Frtabmap","BSD-style 3-clause (LICENSE header)",[55,59],{"relation":56,"title":57,"doi_or_url":58},"preprint","RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation (accepted-manuscript preprint posted 2024-03-10)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2403.06341",{"relation":60,"title":61,"doi_or_url":52},"code_release","rtabmap",{"id":5,"kind":63,"shortName":7,"title":8,"authors":64,"year":9,"venue":67,"venueType":68,"publisher":69,"volumeIssuePages":70,"doi":71,"arxivId":72,"url":58,"firstPublicDate":73,"publicationStatus":16,"metadataStatus":74,"fulltextStatus":15,"era":10,"classicReason":75,"codeUrl":52,"cluster":11,"topics":76,"mdpi":77,"verification":78,"label":6,"fulltextRoute":79,"versionRead":80,"addedByCensus":77},"software",[65,66],"Mathieu Labbé","François Michaud","Journal of Field Robotics","journal","Wiley","36(2):416-446","10.1002\u002Frob.21831","2403.06341","2018-10-27","metadata_verified","not_applicable",[11],false,"confirmed","arXiv","arXiv 2403.06341v1 (accepted manuscript, 40 pages) read in full; version of record in Journal of Field Robotics 36(2) checked on Wiley Online Library (Full Access through NTU): same section structure and identical Tables 8 and 9",[82,89,96,100,105,111,116,120,125,128,131,134],{"category":83,"model":84,"canonical":84,"role":85,"dataset":86,"specs":87,"locator":88},"compute","Intel Core i7-3770","compute for runtime",null,"four cores, 6 GB RAM, 512 GB SSD, Ubuntu 16.04; single core for offline datasets","Sec. 4",{"category":90,"model":91,"canonical":91,"role":92,"dataset":93,"specs":94,"locator":95},"stereo_camera","two synchronized monochrome PointGrey cameras","dataset sensor","KITTI","rectified 1241x376 images, baseline 0.54 m, 10 Hz, car roof","Sec. 4.1",{"category":97,"model":98,"canonical":98,"role":92,"dataset":93,"specs":99,"locator":95},"lidar","Velodyne 64E","roof-mounted, synchronized with stereo at 10 Hz; downsampled with a 50 cm voxel filter for S2S and S2M",{"category":101,"model":102,"canonical":102,"role":92,"dataset":93,"specs":103,"locator":104},"platform","car","autonomous-driving recording car","Sec. 1, Sec. 4.1",{"category":106,"model":107,"canonical":107,"role":92,"dataset":108,"specs":109,"locator":110},"rgbd","Kinect v1","TUM RGB-D","hand-held; RGB and depth at 30 Hz, synchronized with the dataset tool","Sec. 4.2",{"category":90,"model":112,"canonical":112,"role":92,"dataset":113,"specs":114,"locator":115},"EuRoC stereo camera (model not reported)","EuRoC","stereo images at 20 Hz on a drone; exposure not synchronized between cameras, exposure compensation applied","Sec. 4.3",{"category":117,"model":118,"canonical":118,"role":92,"dataset":113,"specs":119,"locator":115},"imu","EuRoC IMU (model not reported)","synchronized with the cameras; used by OKVIS and MSCKF odometry",{"category":101,"model":121,"canonical":121,"role":92,"dataset":122,"specs":123,"locator":124},"PR2 robot","MIT Stata Center","teleoperated in an office building; lidar on the base, cameras on the head","Sec. 4.4",{"category":97,"model":126,"canonical":126,"role":92,"dataset":122,"specs":127,"locator":124},"UTM30","2D long-range lidar, 30 m range, 40 Hz; also filtered to 5.6 m to emulate a short-range lidar such as a URG04LX",{"category":90,"model":129,"canonical":129,"role":92,"dataset":122,"specs":130,"locator":124},"PR2 head stereo camera (model not reported)","replayed at 15 Hz; baseline scaled by 1.091664 to match lidar scale",{"category":106,"model":132,"canonical":132,"role":92,"dataset":122,"specs":133,"locator":124},"PR2 head RGB-D camera (model not reported)","replayed at 15 Hz; depth scaled by 1.043; used for loop closure in lidar configurations",{"category":135,"model":136,"canonical":136,"role":92,"dataset":122,"specs":137,"locator":124},"wheel_or_leg_odometry","wheel encoders and IMU fused by EKF (WheelIMU)","odometry already recorded in the ROS bags",[],{"totalRows":140,"groupCount":141,"groups":142,"others":806},157,11,[143,432,669,760],{"slug":144,"group":145,"sourceId":5,"sourceLabel":6,"table":146,"selfRows":147,"metrics":148,"seqs":162,"entrants":171,"cells":221,"outcomes":423,"locators":425,"hardware":426,"wordings":428,"notes":429},"rtabmap2019-table-8","rtabmap2019:Table 8","Table 8",114,[149,154,157],{"label":150,"unit":151,"statistic":152,"alignment":153},"ATEend","m","RMSE","not_reported",{"label":155,"unit":151,"statistic":156,"alignment":153},"ATEmax (maximum per-frame ATE during the run)","max",{"label":158,"unit":159,"statistic":160,"alignment":161},"oavg (average odometry time)","ms","mean","none",[163,167,169],{"dataset":164,"sequence":165,"environment":166},"MIT Stata Center (PR2)","2012-01-25-12-14-25","indoor office building, teleoperated PR2",{"dataset":164,"sequence":168,"environment":166},"2012-01-25-12-33-29",{"dataset":164,"sequence":170,"environment":166},"both 2012-01-25 sequences",[172,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219],{"name":173,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU→S2S odometry (Long-range lidar)",true,{"name":176,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU→S2M odometry (Long-range lidar)",{"name":178,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with S2S odometry (Long-range lidar)",{"name":180,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with S2M odometry (Long-range lidar)",{"name":182,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMUrefined odometry (Long-range lidar)",{"name":184,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU odometry (Long-range lidar)",{"name":186,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU→S2S odometry (Short-range lidar)",{"name":188,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU→S2M odometry (Short-range lidar)",{"name":190,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with S2S odometry (Short-range lidar)",{"name":192,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with S2M odometry (Short-range lidar)",{"name":194,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMUrefined odometry (Short-range lidar)",{"name":196,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU odometry (Short-range lidar)",{"name":198,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with F2M odometry (Stereo camera)",{"name":200,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with F2F odometry (Stereo camera)",{"name":202,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with Fovis odometry (Stereo camera)",{"name":204,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with ORB2-RTAB odometry (Stereo camera)",{"name":206,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with Viso2 odometry (Stereo camera)",{"name":208,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU odometry (Stereo camera)",{"name":210,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with F2M odometry (RGB-D camera)",{"name":212,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with F2F odometry (RGB-D camera)",{"name":214,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with Fovis odometry (RGB-D camera)",{"name":216,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with ORB2-RTAB odometry (RGB-D camera)",{"name":218,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with DVO odometry (RGB-D camera)",{"name":220,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map with WheelIMU odometry (RGB-D camera)",[222,226,229,230,232,235,237,238,239,240,242,243,244,246,248,249,251,252,253,254,255,257,258,260,261,263,265,266,268,270,272,274,276,277,279,280,281,282,284,286,287,289,290,291,294,296,298,300,301,303,305,306,308,309,311,312,314,317,319,321,322,324,327,329,331,333,335,337,338,339,340,341,343,345,347,349,351,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,393,394,395,396,398,400,402,404,406,408,410,412,414,415,417,419,421],[223,223,223,224,225,223,225,225,223],0,0.06,-1,[223,227,223,228,225,223,225,225,223],1,0.08,[223,223,227,228,225,223,225,225,223],[223,227,227,231,225,223,225,225,223],0.09,[223,233,233,234,225,223,223,225,227],2,15,[227,223,223,236,225,223,225,225,223],0.05,[227,227,223,236,225,223,225,225,223],[227,223,227,228,225,223,225,225,223],[227,227,227,231,225,223,225,225,223],[227,233,233,241,225,223,223,225,227],25,[233,223,223,236,225,223,225,225,223],[233,227,223,228,225,223,225,225,223],[233,223,227,245,225,223,225,225,223],0.07,[233,227,227,247,225,223,225,225,223],0.1,[233,233,233,234,225,223,223,225,227],[250,223,223,236,225,223,225,225,223],3,[250,227,223,224,225,223,225,225,223],[250,223,227,245,225,223,225,225,223],[250,227,227,247,225,223,225,225,223],[250,233,233,241,225,223,223,225,227],[256,223,223,245,225,223,225,225,223],4,[256,227,223,247,225,223,225,225,223],[256,223,227,259,225,223,225,225,223],0.11,[256,227,227,259,225,223,225,225,223],[262,223,223,231,225,223,225,225,223],5,[262,227,223,264,225,223,225,225,223],0.26,[262,223,227,247,225,223,225,225,223],[262,227,227,267,225,223,225,225,223],1.13,[269,223,223,264,225,223,225,225,223],6,[269,227,223,271,225,223,225,225,223],0.27,[269,223,227,273,225,223,225,225,223],0.63,[269,227,227,275,225,223,225,225,223],0.7,[269,233,233,234,225,223,223,225,227],[278,223,223,245,225,223,225,225,223],7,[278,227,223,228,225,223,225,225,223],[278,223,227,231,225,223,225,225,223],[278,227,227,247,225,223,225,225,223],[278,233,233,283,225,223,223,225,227],22,[285,223,223,141,225,223,225,225,223],8,[285,227,223,141,225,223,225,225,223],[285,223,227,288,225,223,225,225,223],4.47,[285,227,227,288,225,223,225,225,223],[285,233,233,234,225,223,223,225,227],[292,223,223,293,225,223,225,225,223],9,4.61,[292,227,223,295,225,223,225,225,223],4.64,[292,223,227,297,225,223,225,225,223],1.27,[292,227,227,299,225,223,225,225,223],1.28,[292,233,233,283,225,223,223,225,227],[302,223,223,245,225,223,225,225,223],10,[302,227,223,304,225,223,225,225,223],0.12,[302,223,227,259,225,223,225,225,223],[302,227,227,307,225,223,225,225,223],0.14,[141,223,223,304,225,223,225,225,223],[141,227,223,310,225,223,225,225,223],0.39,[141,223,227,304,225,223,225,225,223],[141,227,227,313,225,223,225,225,223],2.23,[315,223,223,316,225,223,225,225,223],12,0.3,[315,227,223,318,225,223,225,225,223],0.47,[315,223,227,320,225,223,225,225,223],0.23,[315,227,227,318,225,223,225,225,223],[315,233,233,323,225,223,223,225,227],60,[325,223,223,326,225,223,225,225,223],13,0.28,[325,227,223,328,225,223,225,225,223],0.61,[325,223,227,330,225,223,225,225,223],0.34,[325,227,227,332,225,223,225,225,223],1.09,[325,233,233,334,225,223,223,225,227],40,[336,223,223,86,223,223,225,225,223],14,[336,227,223,86,223,223,225,225,223],[336,223,227,86,223,223,225,225,223],[336,227,227,86,223,223,225,225,223],[336,233,233,86,223,223,223,225,227],[234,223,223,342,225,223,225,225,223],0.227,[234,227,223,344,225,223,225,225,223],0.31,[234,223,227,346,225,223,225,225,223],0.37,[234,227,227,348,225,223,225,225,223],0.57,[234,233,233,350,225,223,223,225,227],45,[352,223,223,353,225,223,225,225,223],16,0.88,[352,227,223,355,225,223,225,225,223],3.64,[352,223,227,357,225,223,225,225,223],0.71,[352,227,227,359,225,223,225,225,223],1.4,[352,233,233,361,225,223,223,225,227],100,[363,223,223,304,225,223,225,225,223],17,[363,227,223,365,225,223,225,225,223],1.1,[363,223,227,367,225,223,225,225,223],0.16,[363,227,227,369,225,223,225,225,223],3.95,[371,223,223,346,225,223,225,225,223],18,[371,227,223,373,225,223,225,225,223],0.91,[371,223,227,375,225,223,225,225,223],0.38,[371,227,227,377,225,223,225,225,223],0.8,[371,233,233,379,225,223,223,225,227],54,[381,223,223,375,225,223,225,225,223],19,[381,227,223,383,225,223,225,225,223],0.69,[381,223,227,385,225,223,225,225,223],0.42,[381,227,227,387,225,223,225,225,223],0.94,[381,233,233,389,225,223,223,225,227],32,[391,223,223,86,223,223,225,225,223],20,[391,227,223,86,223,223,225,225,223],[391,223,227,86,223,223,225,225,223],[391,227,227,86,223,223,225,225,223],[391,233,233,86,223,223,223,225,227],[397,223,223,326,225,223,225,225,223],21,[397,227,223,399,225,223,225,225,223],0.64,[397,223,227,401,225,223,225,225,223],0.49,[397,227,227,403,225,223,225,225,223],0.85,[397,233,233,405,225,223,223,225,227],44,[283,223,223,407,225,223,225,225,223],0.56,[283,227,223,409,225,223,225,225,223],0.77,[283,223,227,411,225,223,225,225,223],0.55,[283,227,227,413,225,223,225,225,223],1.62,[283,233,233,350,225,223,223,225,227],[416,223,223,259,225,223,225,225,223],23,[416,227,223,418,225,223,225,225,223],1.3,[416,223,227,420,225,223,225,225,223],0.19,[416,227,227,422,225,223,225,225,223],3.6,[424],"failed",[146],[427],"Intel Core i7-3770 (four cores), 6 GB RAM, Ubuntu 16.04; MIT Stata Center run online in ROS, not limited to one core (Sec. 4)",[],[430,431],"Online results on MIT Stata Center PR2 bags 2012-01-25; ATE computed at every frame on the map graph with loop closures; ATEend = error at end of run, ATEmax = maximum during run; memory management disabled; visual bags replayed at 15 Hz; short-range lidar emulated by filtering UTM30 scans to 5.6 m; stereo baseline scaled by 1.091664 and depth by 1.043 to match lidar; x = lost, could not complete","Online results on MIT Stata Center PR2 bags 2012-01-25; ATE computed at every frame on the map graph with loop closures; ATEend = error at end of run, ATEmax = maximum during run; memory management disabled; visual bags replayed at 15 Hz; short-range lidar emulated by filtering UTM30 scans to 5.6 m; stereo baseline scaled by 1.091664 and depth by 1.043 to match lidar; x = lost, could not complete; oavg = average odometry processing time",{"slug":433,"group":434,"sourceId":435,"sourceLabel":436,"table":437,"selfRows":302,"metrics":438,"seqs":444,"entrants":472,"cells":499,"outcomes":662,"locators":663,"hardware":664,"wordings":666,"notes":667},"maplab2-2023-table-ii","maplab2_2023:Table II","maplab2_2023","Cramariuc et al., 2023","Table II",[439,441],{"label":440,"unit":151,"statistic":152,"alignment":153},"RMSE of the absolute position error (APE)",{"label":442,"unit":443,"statistic":153,"alignment":75},"Total Time (processing all sequences)","min",[445,449,451,454,456,459,461,464,467,469],{"dataset":446,"sequence":447,"environment":448},"HILTI 2021 SLAM Dataset","Construction 1","outdoor construction site (dataset description)",{"dataset":446,"sequence":450,"environment":448},"Construction 2",{"dataset":446,"sequence":452,"environment":453},"IC Office","indoor office",{"dataset":446,"sequence":455,"environment":453},"Office Mitte",{"dataset":446,"sequence":457,"environment":458},"Basement 3","basement (per sequence name)",{"dataset":446,"sequence":460,"environment":458},"Basement 4",{"dataset":446,"sequence":462,"environment":463},"Parking","parking (per sequence name)",{"dataset":446,"sequence":465,"environment":466},"Campus 1","campus (per sequence name)",{"dataset":446,"sequence":468,"environment":466},"Campus 2",{"dataset":446,"sequence":470,"environment":471},"all 9 sequences (total dataset duration 52 min)","mixed indoor and outdoor",[473,476,479,481,483,485,488,491,493,495,497],{"name":474,"methodId":475,"linkable":174,"proposed":77,"self":77},"ORB SLAM3","orbslam3_2021",{"name":477,"methodId":478,"linkable":174,"proposed":77,"self":77},"LVI SAM","lvisam2021",{"name":480,"methodId":5,"linkable":174,"proposed":77,"self":174},"RTAB Map",{"name":482,"methodId":86,"linkable":77,"proposed":77,"self":77},"maplab",{"name":484,"methodId":86,"linkable":77,"proposed":77,"self":77},"ROVIO",{"name":486,"methodId":487,"linkable":174,"proposed":77,"self":77},"OKVIS","okvis2015",{"name":489,"methodId":490,"linkable":174,"proposed":77,"self":77},"FAST LIO2","fastlio2_2022",{"name":492,"methodId":435,"linkable":174,"proposed":174,"self":77},"maplab 2.0: ROVIO + SIFT",{"name":494,"methodId":435,"linkable":174,"proposed":174,"self":77},"maplab 2.0: OKVIS + SP + B",{"name":496,"methodId":435,"linkable":174,"proposed":174,"self":77},"maplab 2.0: OKVIS + SP + B + ICP",{"name":498,"methodId":435,"linkable":174,"proposed":174,"self":77},"maplab 2.0: FAST-LIO2 + SP + B",[500,502,504,506,507,509,511,513,514,515,516,517,519,521,523,524,526,528,529,530,531,532,533,535,536,537,538,540,541,542,543,544,545,546,548,550,551,553,555,557,558,559,561,563,564,565,566,567,568,570,572,573,574,575,576,577,579,580,581,582,584,586,587,588,589,590,591,593,595,597,598,600,602,603,604,606,607,608,610,611,613,615,617,619,620,621,622,624,625,627,628,630,631,633,634,635,636,638,639,640,642,644,646,648,650,652,654,656,658,660],[223,223,223,501,225,223,225,225,223],1.55,[227,223,223,503,225,223,225,225,223],0.13,[233,223,223,505,225,223,225,225,223],0.36,[250,223,223,367,225,223,225,225,223],[256,223,223,508,225,223,225,225,223],0.98,[262,223,223,510,225,223,225,225,223],1.17,[269,223,223,512,225,223,225,225,223],0.04,[278,223,223,307,225,223,225,225,223],[285,223,223,228,225,223,225,225,223],[292,223,223,228,225,223,225,225,223],[302,223,223,512,225,223,225,225,223],[223,223,227,518,225,223,225,225,223],2.77,[227,223,227,520,225,223,225,225,223],0.33,[233,223,227,522,225,223,225,225,223],0.67,[250,223,227,348,225,223,225,225,223],[256,223,227,525,225,223,225,225,223],1.5,[262,223,227,527,225,223,225,225,223],2.13,[269,223,227,245,225,223,225,225,223],[278,223,227,330,225,223,225,225,223],[285,223,227,420,225,223,225,225,223],[292,223,227,420,225,223,225,225,223],[302,223,227,245,225,223,225,225,223],[223,223,233,534,225,223,225,225,223],1.86,[227,223,233,304,225,223,225,225,223],[233,223,233,525,225,223,225,225,223],[250,223,233,231,225,223,225,225,223],[256,223,233,539,225,223,225,225,223],1.16,[262,223,233,297,225,223,225,225,223],[269,223,233,228,225,223,225,225,223],[278,223,233,228,225,223,225,225,223],[285,223,233,228,225,223,225,225,223],[292,223,233,245,225,223,225,225,223],[302,223,233,245,225,223,225,225,223],[223,223,250,547,225,223,225,225,223],1.7,[227,223,250,549,225,223,225,225,223],0.24,[233,223,250,387,225,223,225,225,223],[250,223,250,552,225,223,225,225,223],3.18,[256,223,250,554,225,223,225,225,223],0.86,[262,223,250,556,225,223,225,225,223],1.15,[269,223,250,304,225,223,225,225,223],[278,223,250,271,225,223,225,225,223],[285,223,250,560,225,223,225,225,223],0.18,[292,223,250,562,225,223,225,225,223],0.15,[302,223,250,247,225,223,225,225,223],[223,223,256,501,225,223,225,225,223],[227,223,256,247,225,223,225,225,223],[233,223,256,375,225,223,225,225,223],[250,223,256,231,225,223,225,225,223],[256,223,256,569,225,223,225,225,223],3.05,[262,223,256,571,225,223,225,225,223],1.01,[269,223,256,236,225,223,225,225,223],[278,223,256,231,225,223,225,225,223],[285,223,256,231,225,223,225,225,223],[292,223,256,228,225,223,225,225,223],[302,223,256,236,225,223,225,225,223],[223,223,262,578,225,223,225,225,223],1.71,[227,223,262,503,225,223,225,225,223],[233,223,262,375,225,223,225,225,223],[250,223,262,259,225,223,225,225,223],[256,223,262,583,225,223,225,225,223],2.9,[262,223,262,585,225,223,225,225,223],1.23,[269,223,262,512,225,223,225,225,223],[278,223,262,259,225,223,225,225,223],[285,223,262,247,225,223,225,225,223],[292,223,262,231,225,223,225,225,223],[302,223,262,512,225,223,225,225,223],[223,223,269,592,225,223,225,225,223],5.49,[227,223,269,594,225,223,225,225,223],4.43,[233,223,269,596,225,223,225,225,223],7.82,[250,223,269,310,225,223,225,225,223],[256,223,269,599,225,223,225,225,223],6.13,[262,223,269,601,225,223,225,225,223],3.36,[269,223,269,262,225,223,225,225,223],[278,223,269,344,225,223,225,225,223],[285,223,269,605,225,223,225,225,223],0.21,[292,223,269,605,225,223,225,225,223],[302,223,269,605,225,223,225,225,223],[223,223,278,609,225,223,225,225,223],1.93,[227,223,278,304,225,223,225,225,223],[233,223,278,612,225,223,225,225,223],0.93,[250,223,278,614,225,223,225,225,223],0.6,[256,223,278,616,225,223,225,225,223],5.1,[262,223,278,618,225,223,225,225,223],2.41,[269,223,278,245,225,223,225,225,223],[278,223,278,375,225,223,225,225,223],[285,223,278,420,225,223,225,225,223],[292,223,278,623,225,223,225,225,223],0.17,[302,223,278,245,225,223,225,225,223],[223,223,285,626,225,223,225,225,223],2.24,[227,223,285,307,225,223,225,225,223],[233,223,285,629,225,223,225,225,223],0.79,[250,223,285,318,225,223,225,225,223],[256,223,285,632,225,223,225,225,223],2.02,[262,223,285,313,225,223,225,225,223],[269,223,285,231,225,223,225,225,223],[278,223,285,326,225,223,225,225,223],[285,223,285,637,225,223,225,225,223],0.2,[292,223,285,560,225,223,225,225,223],[302,223,285,228,225,223,225,225,223],[223,227,292,641,225,223,223,225,223],61,[227,227,292,643,225,223,223,225,223],68,[233,227,292,645,225,223,223,225,223],163,[250,227,292,647,225,223,223,225,223],82,[256,227,292,649,225,223,223,225,223],58,[262,227,292,651,225,223,223,225,223],121,[269,227,292,653,225,223,223,225,223],52,[278,227,292,655,225,223,223,225,223],98,[285,227,292,657,225,223,223,225,223],236,[292,227,292,659,225,223,223,225,223],267,[302,227,292,661,225,223,223,225,223],194,[],[437],[665],"Intel i7-8700 + Nvidia RTX 2080 GPU",[],[668],"HILTI 2021 SLAM Dataset, RMSE of APE; seven baselines and four maplab 2.0 configurations (ROVIO + SIFT, OKVIS + SP + B, OKVIS + SP + B + ICP, FAST-LIO2 + SP + B); sensors used differ per method (icons in table); Total Time measured on Intel i7-8700 with Nvidia RTX 2080 for 52 min of data",{"slug":670,"group":671,"sourceId":5,"sourceLabel":6,"table":672,"selfRows":285,"metrics":673,"seqs":676,"entrants":680,"cells":704,"outcomes":754,"locators":755,"hardware":756,"wordings":757,"notes":758},"rtabmap2019-table-9","rtabmap2019:Table 9","Table 9",[674,675],{"label":150,"unit":151,"statistic":152,"alignment":153},{"label":155,"unit":151,"statistic":156,"alignment":153},[677,679],{"dataset":164,"sequence":165,"environment":678},"indoor office building; Long-range lidar",{"dataset":164,"sequence":168,"environment":678},[681,683,686,689,691,694,696,698,700,702],{"name":682,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map (WheelIMU→S2M) [Long-range lidar]",{"name":684,"methodId":685,"linkable":174,"proposed":77,"self":77},"Cartographer (WheelIMU) [Long-range lidar]","cartographer2016",{"name":687,"methodId":688,"linkable":174,"proposed":77,"self":77},"GMapping (WheelIMU) [Long-range lidar]","gmapping2007",{"name":690,"methodId":86,"linkable":77,"proposed":77,"self":77},"Karto SLAM (WheelIMU) [Long-range lidar]",{"name":692,"methodId":693,"linkable":174,"proposed":77,"self":77},"Hector SLAM (no odometry) [Long-range lidar]","hector2011",{"name":695,"methodId":5,"linkable":174,"proposed":174,"self":174},"RTAB-Map (WheelIMU→S2M) [Short-range lidar]",{"name":697,"methodId":685,"linkable":174,"proposed":77,"self":77},"Cartographer (WheelIMU) [Short-range lidar]",{"name":699,"methodId":688,"linkable":174,"proposed":77,"self":77},"GMapping (WheelIMU) [Short-range lidar]",{"name":701,"methodId":86,"linkable":77,"proposed":77,"self":77},"Karto SLAM (WheelIMU) [Short-range lidar]",{"name":703,"methodId":693,"linkable":174,"proposed":77,"self":77},"Hector SLAM (no odometry) [Short-range lidar]",[705,706,707,708,709,710,711,712,713,714,715,716,717,719,721,722,723,724,725,726,727,728,729,730,731,733,735,737,738,739,740,741,743,745,746,747,748,750,751,753],[223,223,223,236,225,223,225,225,223],[223,227,223,236,225,223,225,225,223],[223,223,227,228,225,223,225,225,223],[223,227,227,231,225,223,225,225,223],[227,223,223,259,225,223,225,225,223],[227,227,223,259,225,223,225,225,223],[227,223,227,247,225,223,225,225,223],[227,227,227,304,225,223,225,225,223],[233,223,223,420,225,223,225,225,223],[233,227,223,420,225,223,225,225,223],[233,223,227,247,225,223,225,225,223],[233,227,227,367,225,223,225,225,223],[250,223,223,718,225,223,225,225,223],0.22,[250,227,223,720,225,223,225,225,223],0.29,[250,223,227,562,225,223,225,225,223],[250,227,227,623,225,223,225,225,223],[256,223,223,224,225,223,225,225,223],[256,227,223,245,225,223,225,225,223],[256,223,227,231,225,223,225,225,223],[256,227,227,231,225,223,225,225,223],[262,223,223,245,225,223,225,225,223],[262,227,223,228,225,223,225,225,223],[262,223,227,231,225,223,225,225,223],[262,227,227,247,225,223,225,225,223],[269,223,223,732,225,223,225,225,223],0.45,[269,227,223,734,225,223,225,225,223],0.52,[269,223,227,736,225,223,225,225,223],0.32,[269,227,227,318,225,223,225,225,223],[278,223,223,578,225,223,225,225,223],[278,227,223,578,225,223,225,225,223],[278,223,227,375,225,223,225,225,223],[278,227,227,742,225,223,225,225,223],1.84,[285,223,223,744,225,223,225,225,223],0.48,[285,227,223,614,225,223,225,225,223],[285,223,227,605,225,223,225,225,223],[285,227,227,605,225,223,225,225,223],[292,223,223,749,225,223,225,225,223],4.59,[292,227,223,749,225,223,225,225,223],[292,223,227,752,225,223,225,225,223],5.53,[292,227,227,752,225,223,225,225,223],[],[672],[],[],[759],"MIT Stata Center 2012-01-25 sequences; RTAB-Map WheelIMU→S2M versus other ROS 2D lidar SLAM run with default parameters; Cartographer, GMapping and Karto use WheelIMU odometry, Hector SLAM uses none; GMapping ATE computed on the current best particle path",{"slug":761,"group":762,"sourceId":763,"sourceLabel":764,"table":765,"selfRows":269,"metrics":766,"seqs":781,"entrants":786,"cells":789,"outcomes":799,"locators":800,"hardware":801,"wordings":803,"notes":804},"asadi2020ugvuav-table-4","asadi2020ugvuav:Table 4","asadi2020ugvuav","Asadi et al., 2020","Table 4",[767,770,772,774,777,779],{"label":768,"unit":769,"statistic":153,"alignment":153},"CPU (%), Min usage","% of 400",{"label":771,"unit":769,"statistic":156,"alignment":153},"CPU (%), Max usage",{"label":773,"unit":769,"statistic":160,"alignment":153},"CPU (%), Average usage",{"label":775,"unit":776,"statistic":153,"alignment":153},"RAM (GB), Min usage","GB",{"label":778,"unit":776,"statistic":156,"alignment":153},"RAM (GB), Max usage",{"label":780,"unit":776,"statistic":160,"alignment":153},"RAM (GB), Average usage",[782],{"dataset":783,"sequence":784,"environment":785},"own 3 min test run","3 min run, all modules active","NCSU Constructed Facilities Lab (indoor, construction-like)",[787],{"name":788,"methodId":5,"linkable":174,"proposed":77,"self":174},"RTAB-MAP (UGV SLAM Module)",[790,791,793,794,796,797],[223,223,223,363,225,223,223,225,223],[223,227,223,792,225,223,223,225,223],86,[223,233,223,653,225,223,223,225,223],[223,250,223,795,225,223,223,225,223],1.8,[223,256,223,250,225,223,223,225,223],[223,262,223,798,225,223,223,225,223],2.4,[],[765],[802],"UGV laptop: Intel Core i7-4710HQ quad-core, 16 GB DDR3 RAM, NVIDIA GeForce GTX 960M",[],[805],"Hardware utilization of one module on the UGV laptop during a 3 min run with all modules active; CPU in percent of 400 (quad core), RAM in GB of 16, GPU memory and streaming-multiprocessor load in percent",[807,814,821,826,830,835,842],{"group":808,"slug":809,"sourceLabel":810,"table":811,"selfRows":262,"datasets":812},"hu2023robotassisted:Table 5","hu2023robotassisted-table-5","Hu et al., 2023","Table 5",[813],"own NUS 5G Centre scan",{"group":815,"slug":816,"sourceLabel":817,"table":818,"selfRows":256,"datasets":819},"chen2025quadrupedinspection:Table 7","chen2025quadrupedinspection-table-7","Chen et al., 2025a","Table 7",[820],"authors' HKUST corridor recording (ROS bag)",{"group":822,"slug":823,"sourceLabel":6,"table":824,"selfRows":250,"datasets":825},"rtabmap2019:Text Sec. 5.1","rtabmap2019-text-sec-5-1","Text Sec. 5.1",[164],{"group":827,"slug":828,"sourceLabel":817,"table":146,"selfRows":233,"datasets":829},"chen2025quadrupedinspection:Table 8","chen2025quadrupedinspection-table-8",[820],{"group":831,"slug":832,"sourceLabel":6,"table":833,"selfRows":233,"datasets":834},"rtabmap2019:Text Sec. 4.4","rtabmap2019-text-sec-4-4","Text Sec. 4.4",[164],{"group":836,"slug":837,"sourceLabel":838,"table":839,"selfRows":233,"datasets":840},"shang2018_uav_vslam:Text Accuracy Evaluation","shang2018-uav-vslam-text-accuracy-evaluation","Shang & Shen, 2018","Text Accuracy Evaluation",[841],"own UAV flight",{"group":843,"slug":844,"sourceLabel":838,"table":845,"selfRows":227,"datasets":846},"shang2018_uav_vslam:Text Site Asset Tracking","shang2018-uav-vslam-text-site-asset-tracking","Text Site Asset Tracking",[847],"own experimental study (platform and site not specified)",1790510656106]