[{"data":1,"prerenderedAt":525},["ShallowReactive",2],{"method-bimloc2026":3},{"method":4,"reference":54,"equipment":79,"figures":121,"results":122},{"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":27,"sensors":35,"platform":39,"estimator":41,"association":42,"timeModel":43,"deskew":44,"loopClosure":45,"globalOptimization":46,"mapRepresentation":47,"prior":48,"outputGeometry":49,"compute":50,"codeUrl":51,"codeLicense":52,"relatedVersions":53},"bimloc2026","Zhang et al., 2026","BIM-Loc (S05)","BIM-Loc: BIM-integrated discrepancy-aware LiDAR-based indoor localization",2026,"recent","C11a","localization_in_prior_map_or_bim","BIM-Loc 以設計階段 BIM 作為先驗，將受差異影響的定位問題拆為 BIM 輔助軌跡最佳化與階層式差異偵測兩個耦合子問題，並迭代求解。其以多次命中射線投射建立點雲與 BIM 面的資料關聯，於位姿圖中加入掃描間一致性與掃描對 BIM 一致性因子，並以貝氏核推論在 BIM 表面紋理空間中逐像素、面、構件更新差異狀態。作者在模擬、已完工辦公建物（SLABIM）與施工中工地（CityU）評估，並明言其差異偵測只判斷構件存在與否，無法量化偏差大小。","Discrepancy-aware LiDAR localization that fuses odometry with BIM surface constraints in a pose graph and incrementally labels BIM elements as consistent, discrepant or unknown via kernelised Bayesian inference in texture space, validated in simulation, a completed office and an active construction site.","full_text_reviewed","online_first","main_body","作者以 CityU 施工中樓層（06 至 12 樓）資料集評估（作者註明資料來自同團隊 Zhang et al., 2024），含手持 Ouster OS0-128 的 7 條序列與 Livox Mid-360 的 2 條序列，共 9 條、總長逾 3.5 km；工地含未完成結構、材料與臨時設備。該工地無真值軌跡，評估僅用 MME、scan-to-BIM 距離與以同一 BIM 為參考的 WD，以及影像疊合定性比對；以真值 ATE 呈現的優勢僅見於已完工辦公建物（SLABIM）。差異偵測的量化結果（F1）僅在模擬中取得。",[20,21,22,23,24],"simulation","public_benchmark","completed_building","real_construction_site","task_level_validation",[26],"[\"Worst-case ATE on SLABIM office sequences 0.147 m translation and 2.911 deg rotation, lower than Fast-Loc and PALoc (Table 3)\", \"Lowest scan-to-BIM RMSE on all CityU construction sequences (Table 5)\", \"BIM storage far smaller than sampled point clouds (Sec. 5.2)\", \"In simulation, translation ATE RMSE stays at or below 0.046 m with up to 35% missing structures and up to 25% occlusion by extra structures shifted by up to 0.5 m, lower than DLO in all six tiers (rotation not lower in all tiers) (App. C.1, Table 9)\", \"Scan-to-BIM RMSE converges within 10 to 30 s over 50 perturbed initial poses (sigma 0.05 m and 3.33 deg) on CityU Livox Mid-360 data (App. C.2, Fig. 21)\", \"Texture-space discrepancy map needs about 5.0 MB for a 4000 m2 floor versus about 823.4 MB for a TSDF voxel map (Sec. 5.3)\"]",[28,29,30,31,32,33,34],"[\"Requires an approximate initial pose (Sec. 6)\", \"Discrepancy detection only for presence or absence of elements","shape changes, boundary shifts and thickness variations not considered","cannot quantify deviation amounts (Sec. 6)\", \"Requires BIM of at least LOD 300","LOD 200 degrades accuracy","LOD 100 unsuitable (Sec. 5.4)\", \"(inference) On the construction benchmark no ground-truth trajectories exist","scan-to-BIM distance and WD use the same BIM as the prior, so they measure consistency with the design model rather than independent geometric accuracy\", \"Exploration is passive","operators get no real-time coverage feedback, which risks incomplete or redundant scanning (Sec. 6)\", \"Degenerate when fewer than 3 to 4 non-coplanar structural facets are observed, e.g. facing a single flat wall (App. C.1)\"]",[36,37,38],"3D LiDAR (Velodyne VLP-16 in simulation; Livox Mid-360; Ouster OS0-128)","IMU","camera (visualisation only)",[20,40],"handheld","Pose graph optimization with BIM-integrated factors solved incrementally with iSAM2 (GTSAM); front-end odometry is DLO (front-end agnostic)","Multi-hit ray casting against BIM facets; point-cluster plane factors (eigenvalue-based inter-scan BA-style) and point-to-BIM-surface residuals","discrete poses","not_reported (delegated to front-end odometry)","none (drift bounded by BIM constraints)","Online pose graph with odometry, inter-scan consistency and scan-BIM factors","As-designed BIM meshes (LOD 300, IFC) plus 2D texture-space discrepancy maps","As-designed BIM (IFC, LOD 300, non-structural entities such as MEP and furniture filtered) plus an approximate initial pose (Sec. 6). In the simulation benchmark the initial pose was given in advance to all methods (Sec. 4.1.2); in the initial-pose sensitivity study on CityU Livox Mid-360 data the nominal initial poses came from the global scan-to-BIM registration of Zhang et al. (2024), which typically reaches 5-7 cm translation and within 1 deg rotation error (App. C.2)","BIM-aligned trajectory, aggregated scans, structure-level discrepancy labels (consistent, discrepant, unknown); no quantitative deviation magnitudes (Sec. 6)","CPU only on a Mini-PC with Intel Core i9-12900 integrated with the sensor suite (Sec. 4); incremental iSAM2 in GTSAM (Sec. 5.1); batch-wise processing with 1.5 s batches (15 frames at 10 Hz): about 350 ms per batch for multi-hit ray casting, factor generation and discrepancy detection in parallel threads, and about 22 ms per frame for trajectory optimization (App. D); module means in Table 8",null,"not_verified",[],{"id":5,"kind":55,"shortName":7,"title":8,"authors":56,"year":9,"venue":65,"venueType":66,"publisher":67,"volumeIssuePages":68,"doi":69,"arxivId":51,"url":70,"firstPublicDate":71,"publicationStatus":16,"metadataStatus":72,"fulltextStatus":15,"era":10,"classicReason":73,"codeUrl":51,"cluster":11,"topics":74,"mdpi":75,"verification":76,"label":6,"fulltextRoute":77,"versionRead":78,"addedByCensus":75},"method",[57,58,59,60,61,62,63,64],"Yinqiang Zhang","Liang Lu","Yipeng Pan","Maolin Lei","Yuhan Xie","Zhanteng Xie","Xiaowei Luo","Jia Pan","The International Journal of Robotics Research","journal","SAGE","OnlineFirst (article 02783649261462593; volume and pages not yet assigned)","10.1177\u002F02783649261462593","https:\u002F\u002Fjournals.sagepub.com\u002Fdoi\u002Ffull\u002F10.1177\u002F02783649261462593","2026-07-06","metadata_verified","not_applicable",[11],false,"corrected","arXiv","arXiv:2606.14237v1 (12 June 2026, 24 pages incl. Appendices A-E; comments state it was accepted by IJRR), CC BY-NC-ND 4.0; the SAGE version of record (OnlineFirst, 6 July 2026) was not re-read in this pass",[80,87,93,97,101,106,110,115],{"category":81,"model":82,"canonical":82,"role":83,"dataset":84,"specs":85,"locator":86},"lidar","Velodyne VLP-16","dataset sensor","BIM-robot simulation benchmark","simulated sensor on a mobile robot in the Gazebo BIM-robot simulator","Sec. 4.1",{"category":81,"model":88,"canonical":89,"role":83,"dataset":90,"specs":91,"locator":92},"Livox Mid-360","Livox MID-360","SLABIM (HKUST office benchmark)","handheld sensor suite with built-in IMU","Sec. 4.2, Fig. 13",{"category":81,"model":88,"canonical":89,"role":83,"dataset":94,"specs":95,"locator":96},"CityU construction benchmark","Floor 06 and Floor 08 sequences; each sequence has LiDAR scans with synchronized IMU measurements","Sec. 4.2, Sec. 4.2.1, Fig. 13",{"category":81,"model":98,"canonical":98,"role":83,"dataset":94,"specs":99,"locator":100},"Ouster OS0-128","handheld sensor suite; seven sequences, Floors 06 to 12","Sec. 4.2.1, Fig. 13",{"category":102,"model":103,"canonical":103,"role":83,"dataset":90,"specs":104,"locator":105},"imu","Livox Mid-360 built-in IMU","not_reported","Sec. 4.2, Fig. 13 caption",{"category":102,"model":107,"canonical":107,"role":83,"dataset":94,"specs":108,"locator":109},"IMU (model not reported)","synchronized IMU measurements included in each CityU sequence; the IMU device (built-in or external) is not named","Sec. 4 (inputs include IMU measurements), Sec. 4.2",{"category":111,"model":112,"canonical":112,"role":83,"dataset":94,"specs":113,"locator":114},"camera","camera (model not reported)","part of the CityU sensor suite, used for visualization only (BIM overlay checks)","Sec. 4.2.1, Sec. 4.2.4, Fig. 17",{"category":116,"model":117,"canonical":117,"role":118,"dataset":51,"specs":119,"locator":120},"compute","Mini-PC with Intel Core i9-12900","compute for runtime","CPU only, no GPU acceleration; integrated with the sensor suite","Sec. 4",[],{"totalRows":123,"groupCount":124,"groups":125,"others":518},49,5,[126,290,366,471],{"slug":127,"group":128,"sourceId":5,"sourceLabel":6,"table":129,"selfRows":130,"metrics":131,"seqs":139,"entrants":159,"cells":167,"outcomes":284,"locators":285,"hardware":286,"wordings":287,"notes":288},"bimloc2026-table-3","bimloc2026:Table 3","Table 3",18,[132,136],{"label":133,"unit":134,"statistic":135,"alignment":104},"ATE RMSE translation","m","RMSE",{"label":137,"unit":138,"statistic":135,"alignment":104},"ATE RMSE rotation error [degree]","deg",[140,143,145,147,149,151,153,155,157],{"dataset":90,"sequence":141,"environment":142},"3F-Region1","completed office building",{"dataset":90,"sequence":144,"environment":142},"3F-Region2",{"dataset":90,"sequence":146,"environment":142},"3F-Region3",{"dataset":90,"sequence":148,"environment":142},"4F-Region1",{"dataset":90,"sequence":150,"environment":142},"4F-Region2",{"dataset":90,"sequence":152,"environment":142},"4F-Region3",{"dataset":90,"sequence":154,"environment":142},"5F-Region1",{"dataset":90,"sequence":156,"environment":142},"5F-Region2",{"dataset":90,"sequence":158,"environment":142},"5F-Region3",[160,163,165],{"name":161,"methodId":5,"linkable":162,"proposed":162,"self":162},"BIM-Loc",true,{"name":164,"methodId":51,"linkable":75,"proposed":75,"self":75},"Fast-Loc",{"name":166,"methodId":51,"linkable":75,"proposed":75,"self":75},"PALoc",[168,172,175,177,179,182,184,186,188,190,192,194,196,198,200,202,204,206,208,211,213,215,217,219,221,224,226,228,230,232,234,236,238,240,242,244,246,249,251,253,255,257,259,262,264,266,268,270,272,274,276,278,280,282],[169,169,169,170,171,169,171,171,169],0,0.147,-1,[169,173,169,174,171,169,171,171,169],1,0.748,[173,169,169,176,171,169,171,171,169],10.75,[173,173,169,178,171,169,171,171,169],40.61,[180,169,169,181,171,169,171,171,169],2,0.359,[180,173,169,183,171,169,171,171,169],4.036,[169,169,173,185,171,169,171,171,169],0.144,[169,173,173,187,171,169,171,171,169],0.565,[173,169,173,189,171,169,171,171,169],1.271,[173,173,173,191,171,169,171,171,169],9.468,[180,169,173,193,171,169,171,171,169],1.121,[180,173,173,195,171,169,171,171,169],12.99,[169,169,180,197,171,169,171,171,169],0.055,[169,173,180,199,171,169,171,171,169],0.47,[173,169,180,201,171,169,171,171,169],3.958,[173,173,180,203,171,169,171,171,169],115.4,[180,169,180,205,171,169,171,171,169],0.17,[180,173,180,207,171,169,171,171,169],3.144,[169,169,209,210,171,169,171,171,169],3,0.098,[169,173,209,212,171,169,171,171,169],0.668,[173,169,209,214,171,169,171,171,169],17.46,[173,173,209,216,171,169,171,171,169],105.7,[180,169,209,218,171,169,171,171,169],0.353,[180,173,209,220,171,169,171,171,169],2.581,[169,169,222,223,171,169,171,171,169],4,0.053,[169,173,222,225,171,169,171,171,169],0.558,[173,169,222,227,171,169,171,171,169],21.13,[173,173,222,229,171,169,171,171,169],123.9,[180,169,222,231,171,169,171,171,169],0.374,[180,173,222,233,171,169,171,171,169],2.51,[169,169,124,235,171,169,171,171,169],0.033,[169,173,124,237,171,169,171,171,169],0.397,[173,169,124,239,171,169,171,171,169],1.624,[173,173,124,241,171,169,171,171,169],16.48,[180,169,124,243,171,169,171,171,169],0.231,[180,173,124,245,171,169,171,171,169],4.181,[169,169,247,248,171,169,171,171,169],6,0.076,[169,173,247,250,171,169,171,171,169],2.911,[173,169,247,252,171,169,171,171,169],14.04,[173,173,247,254,171,169,171,171,169],75.21,[180,169,247,256,171,169,171,171,169],0.455,[180,173,247,258,171,169,171,171,169],4.046,[169,169,260,261,171,169,171,171,169],7,0.043,[169,173,260,263,171,169,171,171,169],0.402,[173,169,260,265,171,169,171,171,169],27.36,[173,173,260,267,171,169,171,171,169],138.9,[180,169,260,269,171,169,171,171,169],0.126,[180,173,260,271,171,169,171,171,169],2.952,[169,169,273,197,171,169,171,171,169],8,[169,173,273,275,171,169,171,171,169],0.632,[173,169,273,277,171,169,171,171,169],19.34,[173,173,273,279,171,169,171,171,169],36.5,[180,169,273,281,171,169,171,171,169],0.836,[180,173,273,283,171,169,171,171,169],4.286,[],[129],[],[],[289],"HKUST office (SLABIM F03-F05), handheld Livox Mid-360; GT trajectories from SLABIM; baselines use points sampled from the same BIM",{"slug":291,"group":292,"sourceId":5,"sourceLabel":6,"table":293,"selfRows":294,"metrics":295,"seqs":298,"entrants":308,"cells":312,"outcomes":360,"locators":361,"hardware":362,"wordings":363,"notes":364},"bimloc2026-table-4","bimloc2026:Table 4","Table 4",9,[296],{"label":297,"unit":134,"statistic":135,"alignment":104},"RMSE of scan-to-BIM distance errors (truncated at 0.2 m)",[299,300,301,302,303,304,305,306,307],{"dataset":90,"sequence":141,"environment":142},{"dataset":90,"sequence":144,"environment":142},{"dataset":90,"sequence":146,"environment":142},{"dataset":90,"sequence":148,"environment":142},{"dataset":90,"sequence":150,"environment":142},{"dataset":90,"sequence":152,"environment":142},{"dataset":90,"sequence":154,"environment":142},{"dataset":90,"sequence":156,"environment":142},{"dataset":90,"sequence":158,"environment":142},[309,310,311],{"name":161,"methodId":5,"linkable":162,"proposed":162,"self":162},{"name":164,"methodId":51,"linkable":75,"proposed":75,"self":75},{"name":166,"methodId":51,"linkable":75,"proposed":75,"self":75},[313,315,317,319,321,323,325,327,328,330,331,333,335,337,339,341,343,344,345,347,349,350,352,353,355,356,358],[169,169,169,314,171,169,171,171,169],0.052,[173,169,169,316,171,169,171,171,169],0.067,[180,169,169,318,171,169,171,171,169],0.077,[169,169,173,320,171,169,171,171,169],0.037,[173,169,173,322,171,169,171,171,169],0.062,[180,169,173,324,171,169,171,171,169],0.065,[169,169,180,326,171,169,171,171,169],0.044,[173,169,180,316,171,169,171,171,169],[180,169,180,329,171,169,171,171,169],0.061,[169,169,209,326,171,169,171,171,169],[173,169,209,332,171,169,171,171,169],0.102,[180,169,209,334,171,169,171,171,169],0.073,[169,169,222,336,171,169,171,171,169],0.047,[173,169,222,338,171,169,171,171,169],0.063,[180,169,222,340,171,169,171,171,169],0.068,[169,169,124,342,171,169,171,171,169],0.045,[173,169,124,340,171,169,171,171,169],[180,169,124,329,171,169,171,171,169],[169,169,247,346,171,169,171,171,169],0.054,[173,169,247,348,171,169,171,171,169],0.085,[180,169,247,316,171,169,171,171,169],[169,169,260,351,171,169,171,171,169],0.039,[173,169,260,324,171,169,171,171,169],[180,169,260,354,171,169,171,171,169],0.066,[169,169,273,342,171,169,171,171,169],[173,169,273,357,171,169,171,171,169],0.082,[180,169,273,359,171,169,171,171,169],0.081,[],[293],[],[],[365],"HKUST office; per-scan point-to-BIM distance RMSE, distances \u003C 0.2 m only; reference is the prior BIM itself",{"slug":367,"group":368,"sourceId":5,"sourceLabel":6,"table":369,"selfRows":294,"metrics":370,"seqs":372,"entrants":392,"cells":401,"outcomes":464,"locators":466,"hardware":467,"wordings":468,"notes":469},"bimloc2026-table-5","bimloc2026:Table 5","Table 5",[371],{"label":297,"unit":134,"statistic":135,"alignment":104},[373,376,378,380,382,384,386,388,390],{"dataset":94,"sequence":374,"environment":375},"Floor-06 (Mid-360)","active construction site (indoor floors)",{"dataset":94,"sequence":377,"environment":375},"Floor-08 (Mid-360)",{"dataset":94,"sequence":379,"environment":375},"Floor-06 (Ouster)",{"dataset":94,"sequence":381,"environment":375},"Floor-07 (Ouster)",{"dataset":94,"sequence":383,"environment":375},"Floor-08 (Ouster)",{"dataset":94,"sequence":385,"environment":375},"Floor-09 (Ouster)",{"dataset":94,"sequence":387,"environment":375},"Floor-10 (Ouster)",{"dataset":94,"sequence":389,"environment":375},"Floor-11 (Ouster)",{"dataset":94,"sequence":391,"environment":375},"Floor-12 (Ouster)",[393,394,395,396,399],{"name":161,"methodId":5,"linkable":162,"proposed":162,"self":162},{"name":164,"methodId":51,"linkable":75,"proposed":75,"self":75},{"name":166,"methodId":51,"linkable":75,"proposed":75,"self":75},{"name":397,"methodId":398,"linkable":162,"proposed":75,"self":75},"LIO-BIM","stuhrenberg2025liobim",{"name":400,"methodId":51,"linkable":75,"proposed":75,"self":75},"CAD-Mesher",[402,404,406,408,409,410,412,414,416,417,418,419,421,422,423,424,426,427,428,430,432,434,436,437,439,440,441,442,444,445,446,448,450,451,452,453,454,455,456,457,458,459,461,462,463],[169,169,169,403,171,169,171,171,169],0.036,[173,169,169,405,171,169,171,171,169],0.08,[180,169,169,407,171,169,171,171,169],0.087,[209,169,169,51,169,169,171,171,169],[222,169,169,51,169,169,171,171,169],[169,169,173,411,171,169,171,171,169],0.038,[173,169,173,413,171,169,171,171,169],0.07,[180,169,173,415,171,169,171,171,169],0.057,[209,169,173,51,169,169,171,171,169],[222,169,173,51,169,169,171,171,169],[169,169,180,342,171,169,171,171,169],[173,169,180,420,171,169,171,171,169],0.078,[180,169,180,334,171,169,171,171,169],[209,169,180,329,171,169,171,171,169],[222,169,180,322,171,169,171,171,169],[169,169,209,425,171,169,171,171,169],0.046,[173,169,209,248,171,169,171,171,169],[180,169,209,340,171,169,171,171,169],[209,169,209,429,171,169,171,171,169],0.059,[222,169,209,431,171,169,171,171,169],0.064,[169,169,222,433,171,169,171,171,169],0.041,[173,169,222,435,171,169,171,171,169],0.072,[180,169,222,431,171,169,171,171,169],[209,169,222,438,171,169,171,171,169],0.056,[222,169,222,324,171,169,171,171,169],[169,169,124,326,171,169,171,171,169],[173,169,124,334,171,169,171,171,169],[180,169,124,443,171,169,171,171,169],0.06,[209,169,124,429,171,169,171,171,169],[222,169,124,324,171,169,171,171,169],[169,169,247,447,171,169,171,171,169],0.042,[173,169,247,449,171,169,171,171,169],0.074,[180,169,247,431,171,169,171,171,169],[209,169,247,438,171,169,171,171,169],[222,169,247,322,171,169,171,171,169],[169,169,260,326,171,169,171,171,169],[173,169,260,248,171,169,171,171,169],[180,169,260,316,171,169,171,171,169],[209,169,260,429,171,169,171,171,169],[222,169,260,322,171,169,171,171,169],[169,169,273,447,171,169,171,171,169],[173,169,273,460,171,169,171,171,169],0.071,[180,169,273,322,171,169,171,171,169],[209,169,273,443,171,169,171,171,169],[222,169,273,443,171,169,171,171,169],[465],"not_run",[369],[],[],[470],"CityU active construction site, handheld LiDAR; no GT trajectories; scan-to-BIM RMSE (\u003C 0.2 m) against the prior BIM",{"slug":472,"group":473,"sourceId":5,"sourceLabel":6,"table":474,"selfRows":273,"metrics":475,"seqs":486,"entrants":489,"cells":494,"outcomes":511,"locators":512,"hardware":513,"wordings":515,"notes":516},"bimloc2026-table-8","bimloc2026:Table 8","Table 8",[476,480,482,484],{"label":477,"unit":478,"statistic":479,"alignment":104},"Mean runtime duration of module (Multi-Hit Ray Casting)","ms","mean",{"label":481,"unit":478,"statistic":479,"alignment":104},"Mean runtime duration of module (Factor Generation)",{"label":483,"unit":478,"statistic":479,"alignment":104},"Mean runtime duration of module (Trajectory Optimization)",{"label":485,"unit":478,"statistic":479,"alignment":104},"Mean runtime duration of module (Discrepancy Detection)",[487],{"dataset":488,"sequence":104,"environment":375},"CityU construction benchmark (ablation context, App. C.1)",[490,492],{"name":491,"methodId":5,"linkable":162,"proposed":162,"self":162},"BIM-Loc (w\u002F discrepancy detection)",{"name":493,"methodId":5,"linkable":162,"proposed":162,"self":162},"BIM-Loc (w\u002Fo discrepancy detection)",[495,497,499,501,503,505,507,509],[169,169,169,496,171,169,169,171,169],114.92,[173,169,169,498,171,169,169,171,169],140.11,[169,173,169,500,171,169,169,171,169],6.68,[173,173,169,502,171,169,169,171,169],10.24,[169,180,169,504,171,169,169,171,169],20.85,[173,180,169,506,171,169,169,171,169],29.87,[169,209,169,508,171,169,169,171,169],22.6,[173,209,169,510,171,169,169,171,169],44.3,[],[474],[514],"Mini-PC with Intel Core i9-12900 CPU, CPU only (Sec. 4)",[],[517],"Ablation (App. C.1): mean runtime of each BIM-Loc module with and without the discrepancy module; module given in metric_as_written; the unit of work (frame or batch) is not stated in the table; App. C.1 presents Table 8 together with Fig. 19 (CityU Floors 06 and 08, Livox Mid-360)",[519],{"group":520,"slug":521,"sourceLabel":6,"table":522,"selfRows":124,"datasets":523},"bimloc2026:Table 2","bimloc2026-table-2","Table 2",[524],"BIM-robot simulation benchmark (CityU-02)",1790510657539]