[{"data":1,"prerenderedAt":186},["ShallowReactive",2],{"method-moura2021bimslam":3},{"method":4,"reference":50,"equipment":70,"figures":84,"results":85},{"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":31,"platform":35,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":43,"mapRepresentation":44,"prior":45,"outputGeometry":46,"compute":41,"codeUrl":47,"codeLicense":48,"relatedVersions":49},"moura2021bimslam","Moura et al., 2021","BIM-based localization and mapping (COBOLLEAGUE)","BIM-based Localization and Mapping for Mobile Robots in Construction",2021,"recent","C11b","localization_in_prior_map_or_bim","作者在歐盟 COBOLLEAGUE 專案中提出把 BIM 轉成 SLAM 位姿圖的介面。IFC 模型先依樓層（IfcStorey 高程）拆分，排除門、窗與空間後轉成網格、體素化並存成八元樹；再由樓層八元樹投影出可通行的二維佔據格，以 Voronoi 路網與覆蓋路徑規劃產生虛擬機器人的軌跡，在每個路點以光線投射產生虛擬掃描、里程計與 IMU 資料，組成不需最佳化的 Cartographer 狀態檔。實際機器人載入此凍結的 BIM 位姿圖後，可在沒有先行探勘的情況下重新定位，並把新掃描加入新軌跡以記錄與模型不同的現況。作者在 Gazebo 模擬與 Eurecat 工業實驗室的實測中示範重新定位與地圖更新。","Converts an IFC model, floor by floor, into octrees and then into a frozen Cartographer pose-graph state built from virtual scans along coverage paths, so a construction robot can relocalize in the BIM frame without prior exploration and append new trajectories that expose deviations from the model; shown in Gazebo and an industrial laboratory.","full_text_reviewed","peer_reviewed_published","supplementary","以施工機器人（重型工具搬運平台）為應用目標，提出可標記現況與 BIM 差異的 BIM 位姿圖；實測場地是工業實驗室而非施工中工地，模型只是測試區的基本 IFC（Sec. II、IV）。",[20,21],"simulation","completed_building",[23,24,25,26],"Relocalization in the BIM-derived map after 11.94 s and 10.34 m in simulation and after 43.29 s and 7.77 m in the real test, with no later jumps (Sec. V)","Final position accuracy below 0.1 m when the robot returned to its start in the real test (Sec. V-B1)","Matched map portions lie within 1 cm average cloud-to-mesh distance of the model, and unmodelled features are flagged for model updates (Sec. V-B2)","Pipeline is faster, memory-efficient, automatic and ROS-independent compared with a Gazebo-based simulation pipeline (Sec. III-B)",[28,29,30],"Assumes Manhattan-world buildings without inclined planes or curved surfaces (Sec. III-A, VI)","Prior tuning of the SLAM algorithm is required; poorly optimized trajectories yield poor matching (Sec. V-B1)","Robot must start in a mapped zone similar to the model before moving to update its surroundings (Sec. V-B1)",[32,33,34],"3D LiDAR (model not reported)","odometry encoders","IMU",[36,37],"simulation (Gazebo)","wheeled UGV with 3D LiDAR in an industrial laboratory (model not reported)","Google Cartographer 3D graph SLAM with its global solver matching new trajectory data to frozen BIM-derived submaps (default configuration, lowered global localization minimum score) (Sec. III-C)","Cartographer scan-to-submap matching and global constraint search against the BIM-derived submaps (Sec. III-C)","as in Cartographer (not discussed)","not_reported","Cartographer global constraints between the new trajectory and the frozen BIM trajectory (inter-submap constraints) (Sec. V-B1)","Cartographer pose-graph optimization with the BIM-derived trajectory frozen (Sec. III-C)","BIM-derived serialized Cartographer state (.pbstream): per-floor trajectories of virtual scans generated from an octree of the voxelized IFC model; new sessions append trajectories that can be exported as point clouds (Sec. III)","IFC model split per storey with IFC++, converted by ifc_convert to OBJ (doors, windows and spaces excluded), voxelized with binvox, converted to Octomap octrees (Sec. III-A)","robot pose in the BIM frame and an updated 3D point-cloud map; deviations from the model highlighted by cloud-to-mesh distance (Sec. V-B2)",null,"not_applicable",[],{"id":5,"kind":51,"shortName":7,"title":8,"authors":52,"year":9,"venue":56,"venueType":57,"publisher":58,"volumeIssuePages":59,"doi":60,"arxivId":47,"url":61,"firstPublicDate":62,"publicationStatus":16,"metadataStatus":63,"fulltextStatus":15,"era":10,"classicReason":48,"codeUrl":47,"cluster":11,"topics":64,"mdpi":65,"verification":66,"label":6,"fulltextRoute":67,"versionRead":68,"addedByCensus":69},"method",[53,54,55],"Mateus Sanches Moura","Carlos Rizzo","Daniel Serrano","2021 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)","conference","IEEE","pp. 12-18","10.1109\u002Ficarsc52212.2021.9429779","https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9429779","2021-04-28","metadata_verified",[11],false,"corrected","NTU institutional (Chrome)","version of record, ICARSC 2021 pp. 12-18 (IEEE Xplore HTML full text)",true,[71,77,80],{"category":72,"model":73,"canonical":32,"role":74,"dataset":47,"specs":75,"locator":76},"lidar","3D LIDAR (model not reported)","method input","on the ground mobile robot used in the validation tests","Sec. IV",{"category":78,"model":33,"canonical":33,"role":74,"dataset":47,"specs":79,"locator":76},"wheel_or_leg_odometry","used with IMU and scans in Cartographer",{"category":81,"model":82,"canonical":82,"role":74,"dataset":47,"specs":83,"locator":76},"imu","IMU (model not reported)","used in Cartographer",[],{"totalRows":86,"groupCount":87,"groups":88,"others":185},6,3,[89,133,161],{"slug":90,"group":91,"sourceId":5,"sourceLabel":6,"table":92,"selfRows":87,"metrics":93,"seqs":102,"entrants":109,"cells":112,"outcomes":123,"locators":125,"hardware":127,"wordings":128,"notes":129},"moura2021bimslam-text-sec-v-b1","moura2021bimslam:Text Sec.V-B1","Text Sec.V-B1",[94,97,100],{"label":95,"unit":96,"statistic":41,"alignment":48},"time until first match with the model","s",{"label":98,"unit":99,"statistic":41,"alignment":48},"distance moved until first match with the model","m",{"label":101,"unit":99,"statistic":41,"alignment":41},"localization accuracy (initial versus final position), stated as less than 0.1 m",[103,107],{"dataset":104,"sequence":105,"environment":106},"Eurecat real test","relocalization run","industrial laboratory building (uncontrolled)",{"dataset":104,"sequence":108,"environment":106},"closed run",[110],{"name":111,"methodId":5,"linkable":69,"proposed":69,"self":69},"Cartographer with BIM-derived pose graph",[113,117,120],[114,114,114,115,116,114,116,116,114],0,43.29,-1,[114,118,114,119,116,114,116,116,118],1,7.77,[114,121,118,122,114,114,116,116,121],2,0.1,[124],"other: upper bound stated in text ('less than 0.1 m')",[126],"Sec. V-B1",[],[],[130,131,132],"Real test on the lower floor of Eurecat's industrial laboratory with a basic IFC model; many non-structural objects (furniture, protection nets)","Real test, same run","Real test: robot returned to its initial position; accuracy obtained by comparing initial and final positions",{"slug":134,"group":135,"sourceId":5,"sourceLabel":6,"table":136,"selfRows":121,"metrics":137,"seqs":142,"entrants":146,"cells":148,"outcomes":153,"locators":154,"hardware":156,"wordings":157,"notes":158},"moura2021bimslam-text-sec-v-a","moura2021bimslam:Text Sec.V-A","Text Sec.V-A",[138,140],{"label":139,"unit":96,"statistic":41,"alignment":48},"time until the robot recognized its pose in the global frame",{"label":141,"unit":99,"statistic":41,"alignment":48},"distance traversed until relocalization",[143],{"dataset":144,"sequence":105,"environment":145},"Gazebo simulation (office building IFC model)","simulated office building",[147],{"name":111,"methodId":5,"linkable":69,"proposed":69,"self":69},[149,151],[114,114,114,150,116,114,116,116,114],11.94,[114,118,114,152,116,114,116,116,118],10.34,[],[155],"Sec. V-A",[],[],[159,160],"Gazebo simulation of an office building ground floor with the BIM-derived .pbstream loaded in a frozen state; robot started at a random indoor location","Gazebo simulation, same run",{"slug":162,"group":163,"sourceId":5,"sourceLabel":6,"table":164,"selfRows":118,"metrics":165,"seqs":170,"entrants":173,"cells":175,"outcomes":177,"locators":179,"hardware":181,"wordings":182,"notes":183},"moura2021bimslam-text-sec-v-b2","moura2021bimslam:Text Sec.V-B2","Text Sec.V-B2",[166],{"label":167,"unit":168,"statistic":169,"alignment":41},"average cloud-to-mesh (C2M) distance to the model, stated as less than 1 cm","cm","mean",[171],{"dataset":104,"sequence":172,"environment":106},"matched map portions (blue)",[174],{"name":111,"methodId":5,"linkable":69,"proposed":69,"self":69},[176],[114,114,114,118,114,114,116,116,114],[178],"other: upper bound stated in text ('less than 1cm')",[180],"Sec. V-B2; Fig. 11",[],[],[184],"New SLAM session map compared with the reference IFC model in CloudCompare; matched portions only",[],1790510661059]