[{"data":1,"prerenderedAt":476},["ShallowReactive",2],{"method-yin2023semanticbimloc":3},{"method":4,"reference":54,"equipment":74,"figures":87,"results":88},{"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":21,"limitations":25,"sensors":33,"platform":35,"estimator":37,"association":38,"timeModel":39,"deskew":40,"loopClosure":41,"globalOptimization":42,"mapRepresentation":43,"prior":44,"outputGeometry":45,"compute":46,"codeUrl":47,"codeLicense":48,"relatedVersions":49},"yin2023semanticbimloc","Yin et al., 2023","Semantic localization on BIM maps","Semantic localization on BIM-generated maps using a 3D LiDAR sensor",2023,"recent","C11b","localization_in_prior_map_or_bim","作者將 BIM 依樓層拆分，經 IfcOpenShell 轉為網格後取樣成帶有構件類別的語意點雲地圖，免除事先以 SLAM 建圖。定位時先做點對面 ICP，再依語意一致性篩選並加權的 ICP 精化位姿。實驗在新加坡國立大學六層校舍（已完工使用）進行，參考軌跡取自離線 2D Cartographer SLAM，非獨立測量。","Localizes a 3D LiDAR on semantically labeled point maps sampled from BIM using coarse-to-fine semantic ICP, avoiding a prior SLAM map, validated in a completed university building.","full_text_reviewed","peer_reviewed_published","main_body","測試於 NUS SDE4 已完工六層校舍的 2-5 樓（10 段、總長逾 340 m）；作者明言施工中動態環境需更新 BIM（Sec. 4.1, 4.5）。",[20],"completed_building",[22,23,24],"overall translation RMSE 0.080 m and rotation 0.663 deg; 34% translation improvement over baseline ICP (Table 4)","semantic filtering alone (Sem (ORG)) improved overall translation error by 18% over ICP (ORG) (Sec. 4.3)","Z drift (Delta Z) of the BIM-based localization stayed within 0.084 m on the four tested sequences, against up to -0.968 m (LOAM), -2.675 m (DLO) and -1.547 m (Open3D SLAM) (Table 6)",[26,27,28,29,30,31,32],"assumes static built environment; BIM updates needed for dynamic construction sites (Sec. 4.5)","as-designed vs as-built deviations can cause failure (Sec. 4.5)","depends on previous pose; no global localization; floor and initial pose set manually at the first frame (Sec. 4.5)","reference trajectory from Cartographer SLAM run in 2D (x, y, yaw) with tuned parameters, not an external survey (Sec. 4.3)","authors state that the BIM-based localization does not show better 2D pose accuracy than the LiDAR-only LOAM, DLO and Open3D SLAM on the four tested sequences; Table 6 is mixed: lowest translation RMSE on Seq. 3-3 but highest yaw RMSE on Seq. 2-3, 4-2 and 5-2 (Table 6, Sec. 4.4)","axis-aligned Dynamo bounding boxes cause mixed or wrongly labelled map points (Fig. 8, Sec. 4.5)","long, narrow corridors with only walls and floors degrade tracking and caused a trajectory discontinuity on the 4th storey (Sec. 4.5)",[34],"3D LiDAR (Velodyne VLP-16)",[36],"not_reported: Fig. 5 shows a Velodyne VLP-16 with portable power and a laptop; the carrier is not stated; data collected with planar motion (Sec. 4.1, 4.4)","frame-to-map registration: point-to-plane ICP then semantic-weighted point-to-plane ICP with Huber kernel; previous pose as initial guess; no odometry (Alg. 2, Sec. 3.3)","coarse point-to-plane ICP, then each scan point is labelled only if all K nearest map points share one BIM category (Eq. 7); only floors, walls and columns are kept (chosen from the Seq. 3-1 test in Table 3); weighted point-to-plane ICP with w = w_c w_rho, semantic weight mu = 0.8 and Huber threshold delta = 0.05 m; about 3% of raw points reach the final step (Sec. 3.3, 4.3, Table 5)","discrete poses","not_reported","none (localization only)","none","storey-wise semantic point cloud sampled from BIM meshes (IfcOpenShell -> OBJ -> sampling at 30 points\u002Fm3 as written), labelled with the 13 BIM categories extracted with Dynamo, using non-oriented (axis-aligned) Dynamo bounding boxes searched with a k-d tree; about 40% walls, 20% floors and 20% curtain panels (Sec. 3.2, 4.1, 4.2)","BIM (IFC) with element categories (Sec. 3.2)","pose trajectory in BIM frame (no new map)","online localization on a low-power laptop, Intel i5-8265U, 16 GB RAM; libpointmatcher on ROS; mean time of Algorithm 2 per scan 108, 79, 112 and 114 ms on Seq. 2-2, 3-3, 4-1 and 5-1; authors state it can track a LiDAR operating at 10 Hz; maps prepared offline with Dynamo, CloudCompare and MATLAB (Sec. 4.1, 4.3)",null,"not_verified",[50],{"relation":51,"title":52,"doi_or_url":53},"preprint","Semantic localization on BIM-generated maps using a 3D LiDAR sensor (arXiv v1 2022-05-02, v2 2022-11-29)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.00816",{"id":5,"kind":55,"shortName":7,"title":8,"authors":56,"year":9,"venue":60,"venueType":61,"publisher":62,"volumeIssuePages":63,"doi":64,"arxivId":65,"url":53,"firstPublicDate":66,"publicationStatus":16,"metadataStatus":67,"fulltextStatus":15,"era":10,"classicReason":68,"codeUrl":47,"cluster":11,"topics":69,"mdpi":70,"verification":71,"label":6,"fulltextRoute":72,"versionRead":73,"addedByCensus":70},"method",[57,58,59],"Huan Yin","Zhiyi Lin","Justin K.W. Yeoh","Automation in Construction","journal","Elsevier","146, 104641","10.1016\u002Fj.autcon.2022.104641","2205.00816","2022-05-02","metadata_verified","not_applicable",[11],false,"confirmed","arXiv","arXiv 2205.00816v2 PDF (29 Nov 2022, carries the Automation in Construction 146, 104641 citation), read in full; version of record on ScienceDirect (Chrome, NTU institutional access) spot-checked: Table 4 'All' row, Table 6 and the laptop specification match",[75,81],{"category":76,"model":77,"canonical":77,"role":78,"dataset":47,"specs":79,"locator":80},"lidar","Velodyne VLP-16","method input","single 3D LiDAR, no IMU or odometry used; operated at 10 Hz","Sec. 4.1, Fig. 5, Sec. 4.3",{"category":82,"model":83,"canonical":83,"role":84,"dataset":47,"specs":85,"locator":86},"compute","laptop with Intel I5-8265U, 16G RAM","compute for runtime","low-power laptop; libpointmatcher on ROS","Sec. 4.1",[],{"totalRows":89,"groupCount":90,"groups":91,"others":475},38,3,[92,325,442],{"slug":93,"group":94,"sourceId":5,"sourceLabel":6,"table":95,"selfRows":96,"metrics":97,"seqs":105,"entrants":130,"cells":141,"outcomes":319,"locators":320,"hardware":321,"wordings":322,"notes":323},"yin2023semanticbimloc-table-4","yin2023semanticbimloc:Table 4","Table 4",22,[98,102],{"label":99,"unit":100,"statistic":101,"alignment":40},"Tr. (m), RMSE of x-y translation error","m","RMSE",{"label":103,"unit":104,"statistic":101,"alignment":40},"Rt. (deg), RMSE of yaw error","deg",[106,110,112,114,116,118,120,122,124,126,128],{"dataset":107,"sequence":108,"environment":109},"self-collected NUS SDE4 sequences","2-1","completed six-storey university building (NUS SDE4), corridors and lounges, storeys 2-5",{"dataset":107,"sequence":111,"environment":109},"2-2",{"dataset":107,"sequence":113,"environment":109},"2-3",{"dataset":107,"sequence":115,"environment":109},"3-1",{"dataset":107,"sequence":117,"environment":109},"3-2",{"dataset":107,"sequence":119,"environment":109},"3-3",{"dataset":107,"sequence":121,"environment":109},"4-1",{"dataset":107,"sequence":123,"environment":109},"4-2",{"dataset":107,"sequence":125,"environment":109},"5-1",{"dataset":107,"sequence":127,"environment":109},"5-2",{"dataset":107,"sequence":129,"environment":109},"All",[131,134,136,138],{"name":132,"methodId":133,"linkable":70,"proposed":70,"self":70},"ICP (ORG): libpointmatcher point-to-plane ICP with default geometric outlier filters (baseline)","pomerleau2013comparing",{"name":135,"methodId":47,"linkable":70,"proposed":70,"self":70},"Sem (ORG): ICP (ORG) plus semantic labelling and selection (ablation)",{"name":137,"methodId":47,"linkable":70,"proposed":70,"self":70},"Sem (w_rho): semantic filtering with Huber weight only (ablation)",{"name":139,"methodId":5,"linkable":140,"proposed":140,"self":140},"Sem (w_c w_rho): full semantic localization (proposed)",true,[142,146,149,151,153,156,158,160,162,165,167,170,172,175,177,180,182,185,187,190,192,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,240,242,244,246,248,250,252,254,255,256,258,259,261,262,264,266,268,270,272,274,276,277,279,281,283,285,287,289,291,292,294,295,297,298,300,302,304,305,307,309,311,313,315,317],[143,143,143,144,145,143,145,145,143],0,0.14,-1,[143,147,143,148,145,143,145,145,143],1,0.78,[143,143,147,150,145,143,145,145,143],0.116,[143,147,147,152,145,143,145,145,143],0.657,[143,143,154,155,145,143,145,145,143],2,0.078,[143,147,154,157,145,143,145,145,143],0.64,[143,143,90,159,145,143,145,145,143],0.062,[143,147,90,161,145,143,145,145,143],0.54,[143,143,163,164,145,143,145,145,143],4,0.049,[143,147,163,166,145,143,145,145,143],0.485,[143,143,168,169,145,143,145,145,143],5,0.037,[143,147,168,171,145,143,145,145,143],0.367,[143,143,173,174,145,143,145,145,143],6,0.235,[143,147,173,176,145,143,145,145,143],1.284,[143,143,178,179,145,143,145,145,143],7,0.193,[143,147,178,181,145,143,145,145,143],1.097,[143,143,183,184,145,143,145,145,143],8,0.069,[143,147,183,186,145,143,145,145,143],0.366,[143,143,188,189,145,143,145,145,143],9,0.072,[143,147,188,191,145,143,145,145,143],0.539,[143,143,193,194,145,143,145,145,143],10,0.122,[143,147,193,196,145,143,145,145,143],0.735,[147,143,143,198,145,143,145,145,143],0.127,[147,147,143,200,145,143,145,145,143],0.976,[147,143,147,202,145,143,145,145,143],0.121,[147,147,147,204,145,143,145,145,143],0.919,[147,143,154,206,145,143,145,145,143],0.091,[147,147,154,208,145,143,145,145,143],0.441,[147,143,90,210,145,143,145,145,143],0.03,[147,147,90,212,145,143,145,145,143],0.385,[147,143,163,214,145,143,145,145,143],0.032,[147,147,163,216,145,143,145,145,143],0.375,[147,143,168,218,145,143,145,145,143],0.034,[147,147,168,220,145,143,145,145,143],0.348,[147,143,173,222,145,143,145,145,143],0.179,[147,147,173,224,145,143,145,145,143],0.681,[147,143,178,226,145,143,145,145,143],0.129,[147,147,178,228,145,143,145,145,143],0.792,[147,143,183,230,145,143,145,145,143],0.031,[147,147,183,232,145,143,145,145,143],0.404,[147,143,188,234,145,143,145,145,143],0.046,[147,147,188,236,145,143,145,145,143],0.365,[147,143,193,238,145,143,145,145,143],0.1,[147,147,193,157,145,143,145,145,143],[154,143,143,241,145,143,145,145,143],0.115,[154,147,143,243,145,143,145,145,143],0.891,[154,143,147,245,145,143,145,145,143],0.081,[154,147,147,247,145,143,145,145,143],0.603,[154,143,154,249,145,143,145,145,143],0.079,[154,147,154,251,145,143,145,145,143],0.611,[154,143,90,253,145,143,145,145,143],0.029,[154,147,90,220,145,143,145,145,143],[154,143,163,210,145,143,145,145,143],[154,147,163,257,145,143,145,145,143],0.343,[154,143,168,230,145,143,145,145,143],[154,147,168,260,145,143,145,145,143],0.362,[154,143,173,198,145,143,145,145,143],[154,147,173,263,145,143,145,145,143],0.671,[154,143,178,265,145,143,145,145,143],0.117,[154,147,178,267,145,143,145,145,143],0.651,[154,143,183,269,145,143,145,145,143],0.022,[154,147,183,271,145,143,145,145,143],0.327,[154,143,188,273,145,143,145,145,143],0.054,[154,147,188,275,145,143,145,145,143],0.318,[154,143,193,245,145,143,145,145,143],[154,147,193,278,145,143,145,145,143],0.573,[90,143,143,280,145,143,145,145,143],0.113,[90,147,143,282,145,143,145,145,143],0.893,[90,143,147,284,145,143,145,145,143],0.097,[90,147,147,286,145,143,145,145,143],0.759,[90,143,154,288,145,143,145,145,143],0.077,[90,147,154,290,145,143,145,145,143],0.59,[90,143,90,253,145,143,145,145,143],[90,147,90,293,145,143,145,145,143],0.335,[90,143,163,210,145,143,145,145,143],[90,147,163,296,145,143,145,145,143],0.324,[90,143,168,210,145,143,145,145,143],[90,147,168,299,145,143,145,145,143],0.359,[90,143,173,301,145,143,145,145,143],0.137,[90,147,173,303,145,143,145,145,143],0.842,[90,143,178,249,145,143,145,145,143],[90,147,178,306,145,143,145,145,143],1.198,[90,143,183,308,145,143,145,145,143],0.025,[90,147,183,310,145,143,145,145,143],0.369,[90,143,188,312,145,143,145,145,143],0.036,[90,147,188,314,145,143,145,145,143],0.345,[90,143,193,316,145,143,145,145,143],0.08,[90,147,193,318,145,143,145,145,143],0.663,[],[95],[],[],[324],"Ten self-collected VLP-16 sequences; RMSE of x-y translation and yaw against offline Cartographer 2D SLAM reference poses; trajectories aligned with the rpg trajectory-evaluation tool [50] (alignment type not stated); 40 ICP iterations for every method; columns ICP (w_rho) and Sem (w_c) omitted to respect the row cap",{"slug":326,"group":327,"sourceId":5,"sourceLabel":6,"table":328,"selfRows":329,"metrics":330,"seqs":337,"entrants":342,"cells":353,"outcomes":436,"locators":437,"hardware":438,"wordings":439,"notes":440},"yin2023semanticbimloc-table-6","yin2023semanticbimloc:Table 6","Table 6",12,[331,333,335],{"label":332,"unit":100,"statistic":101,"alignment":40},"Tr. (m), 2D translation RMSE",{"label":334,"unit":104,"statistic":101,"alignment":40},"Rt. (deg), yaw RMSE",{"label":336,"unit":100,"statistic":40,"alignment":42},"Delta Z (m) = Z_last - Z_init",[338,339,340,341],{"dataset":107,"sequence":113,"environment":109},{"dataset":107,"sequence":119,"environment":109},{"dataset":107,"sequence":123,"environment":109},{"dataset":107,"sequence":127,"environment":109},[343,346,349,351],{"name":344,"methodId":345,"linkable":140,"proposed":70,"self":70},"LOAM [5] (A-LOAM code)","aloam_software",{"name":347,"methodId":348,"linkable":140,"proposed":70,"self":70},"DLO [55]","dlo2022",{"name":350,"methodId":47,"linkable":70,"proposed":70,"self":70},"Open3D SLAM [56]",{"name":352,"methodId":5,"linkable":140,"proposed":140,"self":140},"BIM-based Localization (proposed)",[354,356,358,360,362,364,366,368,370,372,374,376,378,379,381,383,384,386,388,389,391,393,394,396,398,399,401,403,404,406,408,410,412,414,416,418,420,421,422,424,425,426,428,429,430,432,433,434],[143,143,143,355,145,143,145,145,143],0.058,[143,147,143,357,145,143,145,145,143],0.296,[143,154,143,359,145,143,145,145,143],-0.968,[143,143,147,361,145,143,145,145,143],0.04,[143,147,147,363,145,143,145,145,143],0.302,[143,154,147,365,145,143,145,145,143],-0.01,[143,143,154,367,145,143,145,145,143],0.038,[143,147,154,369,145,143,145,145,143],0.326,[143,154,154,371,145,143,145,145,143],-0.793,[143,143,90,373,145,143,145,145,143],0.017,[143,147,90,375,145,143,145,145,143],0.303,[143,154,90,377,145,143,145,145,143],-0.938,[147,143,143,159,145,143,145,145,143],[147,147,143,380,145,143,145,145,143],0.263,[147,154,143,382,145,143,145,145,143],-2.675,[147,143,147,218,145,143,145,145,143],[147,147,147,385,145,143,145,145,143],0.396,[147,154,147,387,145,143,145,145,143],-0.025,[147,143,154,312,145,143,145,145,143],[147,147,154,390,145,143,145,145,143],0.291,[147,154,154,392,145,143,145,145,143],-0.981,[147,143,90,373,145,143,145,145,143],[147,147,90,395,145,143,145,145,143],0.182,[147,154,90,397,145,143,145,145,143],-1.149,[154,143,143,238,145,143,145,145,143],[154,147,143,400,145,143,145,145,143],0.28,[154,154,143,402,145,143,145,145,143],-1.547,[154,143,147,234,145,143,145,145,143],[154,147,147,405,145,143,145,145,143],0.662,[154,154,147,407,145,143,145,145,143],0.015,[154,143,154,409,145,143,145,145,143],0.041,[154,147,154,411,145,143,145,145,143],0.276,[154,154,154,413,145,143,145,145,143],-0.874,[154,143,90,415,145,143,145,145,143],0.033,[154,147,90,417,145,143,145,145,143],0.215,[154,154,90,419,145,143,145,145,143],-0.709,[90,143,143,288,145,143,145,145,143],[90,147,143,290,145,143,145,145,143],[90,154,143,423,145,143,145,145,143],0.084,[90,143,147,210,145,143,145,145,143],[90,147,147,299,145,143,145,145,143],[90,154,147,427,145,143,145,145,143],-0.002,[90,143,154,249,145,143,145,145,143],[90,147,154,306,145,143,145,145,143],[90,154,154,431,145,143,145,145,143],-0.052,[90,143,90,312,145,143,145,145,143],[90,147,90,314,145,143,145,145,143],[90,154,90,435,145,143,145,145,143],0.083,[],[328],[],[],[441],"LiDAR-only comparison (no IMU for any method) on four sequences; 2D RMSE against the Cartographer 2D reference; Delta Z = mean height of the last 50 poses minus that of the first 50 poses, planar motion assumed",{"slug":443,"group":444,"sourceId":5,"sourceLabel":6,"table":445,"selfRows":163,"metrics":446,"seqs":451,"entrants":456,"cells":458,"outcomes":467,"locators":468,"hardware":470,"wordings":472,"notes":473},"yin2023semanticbimloc-text-sec-4-3","yin2023semanticbimloc:Text Sec.4.3","Text Sec.4.3",[447],{"label":448,"unit":449,"statistic":450,"alignment":42},"mean time cost of semantic localization (Algorithm 2)","ms","mean",[452,453,454,455],{"dataset":107,"sequence":111,"environment":109},{"dataset":107,"sequence":119,"environment":109},{"dataset":107,"sequence":121,"environment":109},{"dataset":107,"sequence":125,"environment":109},[457],{"name":139,"methodId":5,"linkable":140,"proposed":140,"self":140},[459,461,463,465],[143,143,143,460,145,143,143,145,143],108,[143,143,147,462,145,143,143,145,143],79,[143,143,154,464,145,143,143,145,143],112,[143,143,90,466,145,143,143,145,143],114,[],[469],"Sec. 4.3",[471],"low-power laptop, Intel i5-8265U, 16 GB RAM",[],[474],"Mean time cost of Algorithm 2 per scan in four case studies (Fig. 13, Table 5)",[],1790510665776]