[{"data":1,"prerenderedAt":354},["ShallowReactive",2],{"method-xu2019ogmvslam":3},{"method":4,"reference":52,"equipment":73,"figures":105,"results":106},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":22,"limitations":27,"sensors":32,"platform":35,"estimator":39,"association":40,"timeModel":41,"deskew":42,"loopClosure":43,"globalOptimization":44,"mapRepresentation":45,"prior":46,"outputGeometry":47,"compute":48,"codeUrl":49,"codeLicense":50,"relatedVersions":51},"xu2019ogmvslam","Xu et al., 2019","OGM-enhanced visual SLAM (Xu et al. 2019)","An Occupancy Grid Mapping enhanced visual SLAM for real-time locating applications in indoor GPS-denied environments",2019,"recent","C11b","full_slam_with_global_correction","作者以 ORB-SLAM2 的 RGB-D 模式為基礎，建立可用於室內即時定位系統（RTLS）的視覺 SLAM。除了 ORB-SLAM2 原有的稀疏特徵地圖外，系統把 Kinect 點雲在指定高度範圍內切成虛擬雷射掃描，搭配關鍵影格位姿投影成二維佔據格地圖；為避免早期位姿誤差污染地圖，只用關鍵影格建圖，並在固定數量關鍵影格後或迴圈閉合修正後，以最佳化過的全部歷史關鍵影格重建佔據格地圖。系統可在 SLAM 模式與只定位模式間切換，佔據格地圖則讓使用者互動、A* 路徑規劃、依位置觸發的資料蒐集與局部點雲更新成為可能。定位精度以地下室走廊 15 個 AprilTag 標記的位置與間距評估。","ORB-SLAM2 RGB-D extended with a 2D occupancy grid built from keyframe poses and virtual laser scans cut from the Kinect point cloud (rebuilt after loop correction), giving an indoor real-time locating system with SLAM and localization modes; accuracy assessed with 15 floor markers in an 80 m basement corridor loop.","full_text_reviewed","peer_reviewed_published","supplementary","作者把系統定位為營建與設施管理機器人的室內即時定位方案，並稱測試場地為兩種典型室內營建環境，但實際描述的是大學實驗室房間與建築地下室走廊，文中沒有說明是否處於施工階段；走廊評估使用 15 個地面標記，世界座標以同一組標記求得的轉換對齊後才比較（Sec. 5、Sec. 5.2.2）。",[20,21],"completed_building","controlled_experiment",[23,24,25,26],"Marker position RMSE 0.039 to 0.186 m and marker distance RMSE 0.018 to 0.235 m in a low-feature basement corridor loop (Tables 1-2)","Repeated measurement of a fixed marker from six locations gave standard deviations of 0.002, 0.002 and 0.003 m (Sec. 5.2.1)","Localization mode runs at about 17.1 FPS on a laptop, above the 1 Hz real-time threshold used for construction equipment tracking (Sec. 4.2)","No environment instrumentation or prior floor plan required; switching between SLAM and localization modes allows incremental map extension (Sec. 3-4)",[28,29,30,31],"Largest errors occurred where the wheelchair passed close to low-feature walls (markers #7 and #9) (Sec. 5.2.2)","Feature-based ORB-SLAM2 struggles with severe illumination change, repetitive features, large viewpoint differences and non-smooth rotation in corridors (Sec. 7)","Only indoor RGB-D SLAM with a Kinect was evaluated (Sec. 3)","Virtual laser scans are of lower quality than real laser scanner data and are used only for mapping, not localization (Sec. 4.1.2)",[33,34],"RGB-D camera (Microsoft Kinect, via ROS openni_launch; depth registered to RGB)","virtual 2D laser scan cut from the Kinect point cloud (pointcloud_to_laserscan)",[36,37,38],"robotic wheelchair carrying a Kinect (corridor evaluation)","robotic powerchair and TurtleBot (application demonstrations)","laboratory room tests (carrier not specified)","ORB-SLAM2 RGB-D (ORB2 RGBD) for 3D camera poses in SLAM or localization-only mode; a separate occupancy-grid mapping node projects keyframe poses to 2D and integrates virtual laser scans with log-odds updates (lfree 5, locc 15), rebuilding the OGM from all optimized historical keyframes periodically and after loop correction (Sec. 4.1)","ORB features and bag-of-words relocalization of ORB-SLAM2; OGM cells updated by Bresenham ray tracing of virtual scan beams (Sec. 4.1.4, 4.2)","discrete keyframes; RGB, depth and virtual scan synchronized into one custom ROS message","not_applicable (RGB-D camera)","ORB-SLAM2 loop detection and correction; OGM rebuilt with the corrected keyframe poses (Sec. 4.1.3)","ORB-SLAM2 local mapping, loop closing and pose-graph correction; saved feature maps serialized with the scans to allow incremental map extension across sessions","sparse ORB feature map plus a 2D occupancy grid map (ROS OccupancyGrid); colored RGB-D point cloud built incrementally for the application example","none (maps built by the system itself in SLAM mode, then reused in localization mode)","2D occupancy grid with real-time 2D camera pose and virtual scan overlay; incremental colored point cloud from RGB-D frames (Sec. 6.3)","Localization mode about 17.1 FPS average (12.8 to 24.4) at 640 x 480 on a laptop with Intel Core i7-4940MX 3.1 GHz (Sec. 4.2)",null,"not_applicable",[],{"id":5,"kind":53,"shortName":7,"title":8,"authors":54,"year":9,"venue":59,"venueType":60,"publisher":61,"volumeIssuePages":62,"doi":63,"arxivId":49,"url":64,"firstPublicDate":65,"publicationStatus":16,"metadataStatus":66,"fulltextStatus":15,"era":10,"classicReason":50,"codeUrl":49,"cluster":11,"topics":67,"mdpi":68,"verification":69,"label":6,"fulltextRoute":70,"versionRead":71,"addedByCensus":72},"method",[55,56,57,58],"Lichao Xu","Chen Feng","Vineet R. Kamat","Carol C. Menassa","Automation in Construction","journal","Elsevier","104:230-245","10.1016\u002Fj.autcon.2019.04.011","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0926580518311506","2019-05-03","metadata_verified",[11],false,"corrected","NTU institutional (Chrome)","version of record, Automation in Construction 104:230-245 (ScienceDirect HTML full text)",true,[74,80,85,89,95,101],{"category":75,"model":76,"canonical":76,"role":77,"dataset":49,"specs":78,"locator":79},"rgbd","Kinect","method input","RGB and depth 640 x 480; openni_launch driver with depth registration to RGB","Sec. 3, Sec. 4.1.1, Sec. 4.2",{"category":81,"model":82,"canonical":82,"role":77,"dataset":49,"specs":83,"locator":84},"platform","robotic wheelchair equipped with a Kinect","moved for five complete loops along an 80 m basement corridor","Sec. 5.2.2",{"category":81,"model":86,"canonical":86,"role":77,"dataset":49,"specs":87,"locator":88},"robotic powerchair","localized in real time on the OGM for A* path planning and navigation demonstrations","Sec. 6.1, Fig. 13",{"category":90,"model":91,"canonical":91,"role":92,"dataset":49,"specs":93,"locator":94},"compute","laptop with Intel Core i7-4940MX CPU @ 3.1GHz","compute for runtime","localization speed evaluation","Sec. 4.2",{"category":96,"model":97,"canonical":97,"role":98,"dataset":49,"specs":99,"locator":100},"other","AprilTag markers (15)","reference or ground truth","fixed on the corridor floor; poses detected by the AprilTag algorithm","Sec. 5.1-5.2",{"category":81,"model":102,"canonical":102,"role":77,"dataset":49,"specs":103,"locator":104},"TurtleBot","data collection platform for the geo-tagged environmental data collection example","Sec. 6.2, Fig. 14",[],{"totalRows":107,"groupCount":108,"groups":109,"others":353},36,4,[110,208,284,322],{"slug":111,"group":112,"sourceId":5,"sourceLabel":6,"table":113,"selfRows":114,"metrics":115,"seqs":121,"entrants":154,"cells":157,"outcomes":202,"locators":203,"hardware":204,"wordings":205,"notes":206},"xu2019ogmvslam-table-1","xu2019ogmvslam:Table 1","Table 1",15,[116],{"label":117,"unit":118,"statistic":119,"alignment":120},"marker position RMSE (2D)","m","RMSE","control points",[122,126,128,130,132,134,136,138,140,142,144,146,148,150,152],{"dataset":123,"sequence":124,"environment":125},"authors' basement corridor data","marker #1 (76 measurements)","completed building, basement corridor (low-feature)",{"dataset":123,"sequence":127,"environment":125},"marker #2 (54 measurements)",{"dataset":123,"sequence":129,"environment":125},"marker #3 (63 measurements)",{"dataset":123,"sequence":131,"environment":125},"marker #4 (54 measurements)",{"dataset":123,"sequence":133,"environment":125},"marker #5 (42 measurements)",{"dataset":123,"sequence":135,"environment":125},"marker #6 (50 measurements)",{"dataset":123,"sequence":137,"environment":125},"marker #7 (50 measurements)",{"dataset":123,"sequence":139,"environment":125},"marker #8 (64 measurements)",{"dataset":123,"sequence":141,"environment":125},"marker #9 (80 measurements)",{"dataset":123,"sequence":143,"environment":125},"marker #10 (68 measurements)",{"dataset":123,"sequence":145,"environment":125},"marker #11 (53 measurements)",{"dataset":123,"sequence":147,"environment":125},"marker #12 (57 measurements)",{"dataset":123,"sequence":149,"environment":125},"marker #13 (30 measurements)",{"dataset":123,"sequence":151,"environment":125},"marker #14 (93 measurements)",{"dataset":123,"sequence":153,"environment":125},"marker #15 (41 measurements)",[155],{"name":156,"methodId":5,"linkable":72,"proposed":72,"self":72},"proposed OGM-enhanced ORB2 RGB-D RTLS",[158,162,165,168,171,173,176,179,182,185,188,191,193,196,199],[159,159,159,160,161,159,161,161,159],0,0.098,-1,[159,159,163,164,161,159,161,161,159],1,0.151,[159,159,166,167,161,159,161,161,159],2,0.088,[159,159,169,170,161,159,161,161,159],3,0.135,[159,159,108,172,161,159,161,161,159],0.121,[159,159,174,175,161,159,161,161,159],5,0.075,[159,159,177,178,161,159,161,161,159],6,0.186,[159,159,180,181,161,159,161,161,159],7,0.133,[159,159,183,184,161,159,161,161,159],8,0.185,[159,159,186,187,161,159,161,161,159],9,0.149,[159,159,189,190,161,159,161,161,159],10,0.155,[159,159,192,167,161,159,161,161,159],11,[159,159,194,195,161,159,161,161,159],12,0.039,[159,159,197,198,161,159,161,161,159],13,0.094,[159,159,200,201,161,159,161,161,159],14,0.065,[],[113],[],[],[207],"Localization mode on the building-scale maps; 15 AprilTag markers on the floor of an 80 m basement corridor loop, five loops with a robotic wheelchair; estimated 2D marker positions compared with measured true positions after aligning the system world frame to the marker network frame with a 3D transformation from the same 15 marker pairs",{"slug":209,"group":210,"sourceId":5,"sourceLabel":6,"table":211,"selfRows":114,"metrics":212,"seqs":215,"entrants":246,"cells":248,"outcomes":278,"locators":279,"hardware":280,"wordings":281,"notes":282},"xu2019ogmvslam-table-2","xu2019ogmvslam:Table 2","Table 2",[213],{"label":214,"unit":118,"statistic":119,"alignment":50},"marker distance RMSE",[216,218,220,222,224,226,228,230,232,234,236,238,240,242,244],{"dataset":123,"sequence":217,"environment":125},"markers #1-#2 (true distance 3.05 m)",{"dataset":123,"sequence":219,"environment":125},"markers #2-#3 (true distance 0.917 m)",{"dataset":123,"sequence":221,"environment":125},"markers #3-#4 (true distance 3.05 m)",{"dataset":123,"sequence":223,"environment":125},"markers #4-#5 (true distance 4.27 m)",{"dataset":123,"sequence":225,"environment":125},"markers #5-#6 (true distance 6.409 m)",{"dataset":123,"sequence":227,"environment":125},"markers #6-#7 (true distance 7.319 m)",{"dataset":123,"sequence":229,"environment":125},"markers #7-#8 (true distance 7.733 m)",{"dataset":123,"sequence":231,"environment":125},"markers #8-#9 (true distance 7.723 m)",{"dataset":123,"sequence":233,"environment":125},"markers #9-#10 (true distance 3.773 m)",{"dataset":123,"sequence":235,"environment":125},"markers #10-#11 (true distance 7.624 m)",{"dataset":123,"sequence":237,"environment":125},"markers #11-#12 (true distance 7.318 m)",{"dataset":123,"sequence":239,"environment":125},"markers #12-#13 (true distance 6.709 m)",{"dataset":123,"sequence":241,"environment":125},"markers #13-#14 (true distance 6.491 m)",{"dataset":123,"sequence":243,"environment":125},"markers #14-#15 (true distance 7.238 m)",{"dataset":123,"sequence":245,"environment":125},"markers #15-#1 (true distance 1.239 m)",[247],{"name":156,"methodId":5,"linkable":72,"proposed":72,"self":72},[249,251,253,255,257,259,261,263,265,267,269,271,273,275,276],[159,159,159,250,161,159,161,161,159],0.018,[159,159,163,252,161,159,161,161,159],0.061,[159,159,166,254,161,159,161,161,159],0.067,[159,159,169,256,161,159,161,161,159],0.035,[159,159,108,258,161,159,161,161,159],0.041,[159,159,174,260,161,159,161,161,159],0.202,[159,159,177,262,161,159,161,161,159],0.193,[159,159,180,264,161,159,161,161,159],0.113,[159,159,183,266,161,159,161,161,159],0.177,[159,159,186,268,161,159,161,161,159],0.235,[159,159,189,270,161,159,161,161,159],0.045,[159,159,192,272,161,159,161,161,159],0.083,[159,159,194,274,161,159,161,161,159],0.132,[159,159,197,195,161,159,161,161,159],[159,159,200,277,161,159,161,161,159],0.019,[],[211],[],[],[283],"Distance between adjacent markers estimated by the system versus measured true distance, same corridor experiment",{"slug":285,"group":286,"sourceId":5,"sourceLabel":6,"table":287,"selfRows":169,"metrics":288,"seqs":299,"entrants":304,"cells":307,"outcomes":314,"locators":316,"hardware":317,"wordings":319,"notes":320},"xu2019ogmvslam-text-sec-4-2","xu2019ogmvslam:Text Sec.4.2","Text Sec.4.2",[289,293,296],{"label":290,"unit":291,"statistic":292,"alignment":50},"mean localization speed (about)","FPS","mean",{"label":294,"unit":291,"statistic":295,"alignment":50},"max localization speed (about)","max",{"label":297,"unit":291,"statistic":298,"alignment":50},"min localization speed (about)","other: minimum",[300],{"dataset":301,"sequence":302,"environment":303},"authors' laboratory data","localization mode","university laboratory room",[305],{"name":306,"methodId":5,"linkable":72,"proposed":72,"self":72},"proposed OGM-enhanced ORB2 RGB-D RTLS (localization mode)",[308,310,312],[159,159,159,309,159,159,159,161,159],17.1,[159,163,159,311,159,159,159,161,159],24.4,[159,166,159,313,159,159,159,161,159],12.8,[315],"other: approximate ('~') value stated in text",[94],[318],"laptop Intel Core i7-4940MX CPU @ 3.1 GHz",[],[321],"Localization-mode update rate of the 2D pose on the OGM as reported by ROS rostopic, 640 x 480 RGB and registered depth images",{"slug":323,"group":324,"sourceId":5,"sourceLabel":6,"table":325,"selfRows":169,"metrics":326,"seqs":334,"entrants":338,"cells":340,"outcomes":346,"locators":347,"hardware":349,"wordings":350,"notes":351},"xu2019ogmvslam-text-sec-5-2-1","xu2019ogmvslam:Text Sec.5.2.1","Text Sec.5.2.1",[327,330,332],{"label":328,"unit":118,"statistic":329,"alignment":50},"standard deviation of marker x position","std",{"label":331,"unit":118,"statistic":329,"alignment":50},"standard deviation of marker y position",{"label":333,"unit":118,"statistic":329,"alignment":50},"standard deviation of marker z position",[335],{"dataset":336,"sequence":337,"environment":303},"authors' laboratory room data","single marker, 600 measurements",[339],{"name":156,"methodId":5,"linkable":72,"proposed":72,"self":72},[341,343,344],[159,159,159,342,161,159,161,161,159],0.002,[159,163,159,342,161,159,161,161,159],[159,166,159,345,161,159,161,161,159],0.003,[],[348],"Sec. 5.2.1",[],[],[352],"Repeatability test: one fixed marker measured 100 times from each of six camera locations (600 measurements) in the laboratory-scale map; accuracy not evaluated because the world frame is arbitrary",[],1790510661876]