[{"data":1,"prerenderedAt":289},["ShallowReactive",2],{"method-vegatorres2023ogm2pgbm":3},{"method":4,"reference":60,"equipment":82,"figures":103,"results":144},{"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":26,"sensors":31,"platform":34,"estimator":36,"association":37,"timeModel":38,"deskew":39,"loopClosure":40,"globalOptimization":41,"mapRepresentation":42,"prior":43,"outputGeometry":44,"compute":45,"codeUrl":46,"codeLicense":47,"relatedVersions":48},"vegatorres2023ogm2pgbm","Torres et al., 2023","OGM2PGBM","OGM2PGBM: Robust BIM-based 2D-LiDAR localization for lifelong indoor navigation",2023,"recent","C11b","localization_in_prior_map_or_bim","作者提出從 BIM 產生適合 2D LiDAR 定位的地圖，並比較不同定位器在 Scan-BIM 偏差下的表現。首先以 IfcConvert 在指定高度切出只含結構構件的 SVG 剖面，再用 OpenCV 輪廓階層區分室外、室內與障礙物，得到佔據格地圖；接著以骨架化與波前覆蓋路徑在可通行區域產生路點，不經 Gazebo 直接以光線投射模擬雷射掃描與里程計，組成 Cartographer 與 SLAM Toolbox 可讀的位姿圖地圖。作者在 Gazebo 中以空房間、依 TLS 資料建立的真實辦公室與災後雜亂三種情境（有無行人各一），比較 AMCL、GMCL 兩種粒子濾波與 Cartographer、SLAM Toolbox 兩種圖式定位的 RMSE 與全域定位收斂時間。","Generates occupancy grids from IFC models and converts them, via ray-cast virtual scans along coverage paths, into pose-graph maps for Cartographer and SLAM Toolbox; in Gazebo scenarios with increasing Scan-BIM deviation and walking agents, graph-based localizers track pose more accurately than AMCL and GMCL, while GMCL is best for global localization.","full_text_reviewed","peer_reviewed_published","supplementary","針對設計 BIM 與竣工現況不一致（家具、施工偏差、動態人員）時的 2D LiDAR 定位，量化粒子濾波與圖式定位的差異；結果全部來自 Gazebo 模擬，其中第二情境依真實辦公室的 TLS 資料建立（Sec. 5、Table 1）。",[20],"simulation",[22,23,24,25],"In the office scenario with medium Scan-BIM deviation, Cartographer with the generated pose-graph map reached 7.19 cm translational RMSE versus 33.68 cm for AMCL (Table 1; Abstract)","Graph-based localizers outperformed particle filters for pose tracking in all evaluated sequences (Sec. 6.1)","Pose-graph maps are generated without Gazebo, making the pipeline faster and more portable; works from any OGM (Sec. 4.2)","OGM extraction handles complex multi-storey, non-convex models with slanted floors (Sec. 4.1)",[27,28,29,30],"Cartographer failed in the Disaster scenario because of wrong data associations (Table 1; Sec. 6.1)","No method converged for global localization in the Disaster scenario; AMCL did not converge in scenario 2-1 (Sec. 6.2)","SLAM Toolbox provides no global localization service and its lifelong mode performed poorly (Sec. 5.4)","Only 2D LiDAR; 3D LiDAR and multi-sensor fusion are future work (Sec. 8)",[32,33],"2D LiDAR (simulated Hokuyo UST-10LX)","simulated IMU and wheel odometry",[35],"simulation (Robotnik SUMMIT-XL holonomic robot in Gazebo, about 1 m\u002Fs)","Compared localizers: particle filters AMCL and GMCL, and graph-based Cartographer (pure localization) and SLAM Toolbox using the generated pose-graph maps; proposed use: GMCL for global localization until covariance below 0.05, then switch to a graph-based localizer for pose tracking (Sec. 4.3)","scan matching of the respective localizers against OGM or pose-graph submaps (not modified by the authors)","as in the compared localizers","not_applicable (2D LiDAR in simulation)","not_applicable for pure localization; Cartographer and SLAM Toolbox constraints to the prior pose graph","graph-based localizers optimize recent poses against the frozen prior pose graph; the prior graph needs no optimization because simulated scan poses are exact (Sec. 4.2)","2D occupancy grid map extracted from IFC (IfcConvert SVG section, OpenCV contour hierarchy separating outdoor, indoor and obstacles) and a pose-graph map (.pbstream for Cartographer, .posegraph for SLAM Toolbox) built from ray-cast virtual scans along a skeleton-based wavefront coverage path (Sec. 4.1-4.2)","as-designed IFC BIM model (multi-storey, slanted floors handled by rotation); non-permanent entities (spaces, windows, doors) excluded","2D robot pose in the BIM frame; no point cloud produced","not_reported","https:\u002F\u002Fgithub.com\u002FMigVega\u002FOgm2Pgbm","MIT (LICENSE file on main branch checked 2026-09-25)",[49,53,57],{"relation":50,"title":51,"doi_or_url":52},"preprint","arXiv 2308.05443 v1 (posted after the chapter, longer title)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2308.05443",{"relation":54,"title":55,"doi_or_url":56},"repository_copy","mediaTUM record","https:\u002F\u002Fmediatum.ub.tum.de\u002F1688028",{"relation":58,"title":59,"doi_or_url":46},"code_release","MigVega\u002FOgm2Pgbm",{"id":5,"kind":61,"shortName":7,"title":8,"authors":62,"year":9,"venue":66,"venueType":67,"publisher":68,"volumeIssuePages":69,"doi":70,"arxivId":71,"url":72,"firstPublicDate":73,"publicationStatus":16,"metadataStatus":74,"fulltextStatus":15,"era":10,"classicReason":75,"codeUrl":46,"cluster":11,"topics":76,"mdpi":77,"verification":78,"label":6,"fulltextRoute":79,"versionRead":80,"addedByCensus":81},"method",[63,64,65],"M. A. Vega Torres","A. Braun","A. Borrmann","ECPPM 2022: eWork and eBusiness in Architecture, Engineering and Construction 2022 (CRC Press)","book_chapter","CRC Press","pp. 567-574","10.1201\u002F9781003354222-72","2308.05443","https:\u002F\u002Fdoi.org\u002F10.1201\u002F9781003354222-72","2023-03-08","metadata_verified","not_applicable",[11],false,"corrected","arXiv","arXiv v1 (2023-08-10, CC BY 4.0), posted after the CRC Press chapter (2023-03-08); chapter itself not read",true,[83,90,95,99],{"category":84,"model":85,"canonical":85,"role":86,"dataset":87,"specs":88,"locator":89},"platform","Robotnik SUMMIT XL (simulated)","method input","Gazebo simulation of the three BIM-based evaluation scenarios (building not named in the paper)","holonomic; commanded at about 1 m\u002Fs and 1 deg\u002Fs in Gazebo","Sec. 5.3",{"category":91,"model":92,"canonical":92,"role":86,"dataset":87,"specs":93,"locator":94},"lidar","Hokuyo UST-10LX (simulated)","2D LiDAR simulated in Gazebo; glass removed from collision models","Sec. 5.2-5.3",{"category":96,"model":97,"canonical":97,"role":86,"dataset":87,"specs":98,"locator":89},"imu","simulated IMU","simulated together with wheel odometry and ground truth odometry",{"category":100,"model":101,"canonical":101,"role":86,"dataset":87,"specs":102,"locator":89},"wheel_or_leg_odometry","simulated wheel odometry","simulated in the six sequences",[104,117,127,136],{"refId":5,"refLabel":6,"fig":105,"whatZh":106,"license":107,"licenseUrl":108,"sourceUrl":109,"src":110,"width":111,"height":112,"thumb":113,"thumbWidth":114,"thumbHeight":115,"modified":116},"Figure 1","由多層 BIM 產生佔據格地圖、轉為位姿圖地圖並用於全域定位與位姿追蹤的整體流程","CC BY 4.0","http:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby\u002F4.0\u002F","https:\u002F\u002Far5iv.labs.arxiv.org\u002Fhtml\u002F2308.05443\u002Fassets\u002FCompleteMethod_v14.png","\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-1.webp",1400,715,"\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-1.thumb.webp",480,245,"resized to at most 1400 px wide and converted to WebP",{"refId":5,"refLabel":6,"fig":118,"whatZh":119,"license":107,"licenseUrl":108,"sourceUrl":120,"src":121,"width":122,"height":123,"thumb":124,"thumbWidth":114,"thumbHeight":125,"modified":126},"Figure 2 (b)","評估情境二：依真實 TLS 資料建立的一般辦公室環境","https:\u002F\u002Far5iv.labs.arxiv.org\u002Fhtml\u002F2308.05443\u002Fassets\u002F02_Figures\u002F5_Experiments\u002FEnvironments\u002F2_v2.jpg","\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-2-b.webp",577,616,"\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-2-b.thumb.webp",512,"converted to WebP",{"refId":5,"refLabel":6,"fig":128,"whatZh":129,"license":107,"licenseUrl":108,"sourceUrl":130,"src":131,"width":132,"height":133,"thumb":134,"thumbWidth":114,"thumbHeight":135,"modified":126},"Figure 2 (c)","評估情境三：模擬災後、Scan-BIM 偏差很大的環境","https:\u002F\u002Far5iv.labs.arxiv.org\u002Fhtml\u002F2308.05443\u002Fassets\u002F02_Figures\u002F5_Experiments\u002FEnvironments\u002F3_v3.png","\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-2-c.webp",671,727,"\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-2-c.thumb.webp",520,{"refId":5,"refLabel":6,"fig":137,"whatZh":138,"license":107,"licenseUrl":108,"sourceUrl":139,"src":140,"width":141,"height":142,"thumb":143,"thumbWidth":141,"thumbHeight":142,"modified":126},"Figure 3 (c)","序列 2-1 的佔據格地圖與機器人軌跡，空房間地圖以藍色疊合顯示 Scan-BIM 偏差","https:\u002F\u002Far5iv.labs.arxiv.org\u002Fhtml\u002F2308.05443\u002Fassets\u002Fbasemap_2_1.png","\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-3-c.webp",176,277,"\u002Ffigure-files\u002Fvegatorres2023ogm2pgbm\u002Ffigure-3-c.thumb.webp",{"totalRows":145,"groupCount":146,"groups":147,"others":288},12,1,[148],{"slug":149,"group":150,"sourceId":5,"sourceLabel":6,"table":151,"selfRows":145,"metrics":152,"seqs":160,"entrants":175,"cells":186,"outcomes":281,"locators":283,"hardware":284,"wordings":285,"notes":286},"vegatorres2023ogm2pgbm-table-1","vegatorres2023ogm2pgbm:Table 1","Table 1",[153,157],{"label":154,"unit":155,"statistic":156,"alignment":45},"translational RMSE","cm","RMSE",{"label":158,"unit":159,"statistic":156,"alignment":45},"angular RMSE","deg",[161,165,167,169,171,173],{"dataset":162,"sequence":163,"environment":164},"Gazebo simulation from an as-designed IFC model, three scenarios (building not named in the paper)","1-1 (Empty Room, no dynamic agents)","simulated indoor office floor (as-designed BIM, furniture, disaster clutter)",{"dataset":162,"sequence":166,"environment":164},"1-2 (Empty Room, with dynamic agents)",{"dataset":162,"sequence":168,"environment":164},"2-1 (Reality (office, TLS-based), no dynamic agents)",{"dataset":162,"sequence":170,"environment":164},"2-2 (Reality (office, TLS-based), with dynamic agents)",{"dataset":162,"sequence":172,"environment":164},"3-1 (Disaster, no dynamic agents)",{"dataset":162,"sequence":174,"environment":164},"3-2 (Disaster, with dynamic agents)",[176,179,181,183],{"name":177,"methodId":178,"linkable":77,"proposed":77,"self":77},"AMCL",null,{"name":180,"methodId":178,"linkable":77,"proposed":77,"self":77},"GMCL",{"name":182,"methodId":5,"linkable":81,"proposed":81,"self":81},"SLAM Toolbox (localization with prior .posegraph from OGM2PGBM)",{"name":184,"methodId":185,"linkable":81,"proposed":81,"self":77},"Cartographer (pure localization with .pbstream from OGM2PGBM)","cartographer2016",[187,191,193,195,197,200,202,205,207,210,212,215,217,219,221,223,224,226,228,230,232,234,236,238,240,242,244,246,247,249,251,253,254,256,258,260,262,264,265,267,269,271,273,275,277,278,279,280],[188,188,188,189,190,188,190,190,188],0,8.49,-1,[188,146,188,192,190,188,190,190,188],0.44,[188,188,146,194,190,188,190,190,188],8.47,[188,146,146,196,190,188,190,190,188],0.5,[188,188,198,199,190,188,190,190,188],2,33.68,[188,146,198,201,190,188,190,190,188],2.71,[188,188,203,204,190,188,190,190,188],3,37.44,[188,146,203,206,190,188,190,190,188],3.26,[188,188,208,209,190,188,190,190,188],4,63.04,[188,146,208,211,190,188,190,190,188],3.29,[188,188,213,214,190,188,190,190,188],5,65.12,[188,146,213,216,190,188,190,190,188],3.37,[146,188,188,218,190,188,190,190,188],8.27,[146,146,188,220,190,188,190,190,188],0.24,[146,188,146,222,190,188,190,190,188],7.86,[146,146,146,220,190,188,190,190,188],[146,188,198,225,190,188,190,190,188],24.27,[146,146,198,227,190,188,190,190,188],2.57,[146,188,203,229,190,188,190,190,188],52.38,[146,146,203,231,190,188,190,190,188],4.37,[146,188,208,233,190,188,190,190,188],66.6,[146,146,208,235,190,188,190,190,188],3.7,[146,188,213,237,190,188,190,190,188],126.91,[146,146,213,239,190,188,190,190,188],4.46,[198,188,188,241,190,188,190,190,188],3.69,[198,146,188,243,190,188,190,190,188],0.17,[198,188,146,245,190,188,190,190,188],3.95,[198,146,146,243,190,188,190,190,188],[198,188,198,248,190,188,190,190,188],28.69,[198,146,198,250,190,188,190,190,188],1.5,[198,188,203,252,190,188,190,190,188],23.57,[198,146,203,250,190,188,190,190,188],[198,188,208,255,190,188,190,190,188],37.84,[198,146,208,257,190,188,190,190,188],1.34,[198,188,213,259,190,188,190,190,188],37.96,[198,146,213,261,190,188,190,190,188],1.7,[203,188,188,263,190,188,190,190,188],4.01,[203,146,188,220,190,188,190,190,188],[203,188,146,266,190,188,190,190,188],3.96,[203,146,146,268,190,188,190,190,188],0.25,[203,188,198,270,190,188,190,190,188],7.19,[203,146,198,272,190,188,190,190,188],0.15,[203,188,203,274,190,188,190,190,188],4.11,[203,146,203,276,190,188,190,190,188],0.21,[203,188,208,178,188,188,190,190,188],[203,146,208,178,188,188,190,190,188],[203,188,213,178,188,188,190,190,188],[203,146,213,178,188,188,190,190,188],[282],"failed (reported as '-'; wrong data associations)",[151],[],[],[287],"Pose tracking in Gazebo with a Robotnik SUMMIT-XL and Hokuyo UST-10LX; maps from an as-designed IFC model; three scenarios with increasing Scan-BIM deviation, with and without walking human agents; PF methods averaged over 30 runs; RMSE against simulator ground truth computed with evo and rpg trajectory evaluation; '-' = Cartographer found wrong associations and failed",[],1790510664232]