[{"data":1,"prerenderedAt":115},["ShallowReactive",2],{"method-cole_newman2006_3dslam":3},{"method":4,"reference":54,"equipment":74,"figures":81,"results":82},{"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":32,"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},"cole_newman2006_3dslam","Cole & Newman, 2006","Cole-Newman 3D laser SLAM with an oscillating 2D scanner","Using laser range data for 3D SLAM in outdoor environments",2006,"classic","C01","full_slam_with_global_correction","本文把 2D 延遲狀態（掃描匹配式）SLAM 延伸為戶外起伏地形的 6 自由度 SLAM。一台 SICK 2D 雷射以 0.6 Hz 繞水平軸來回擺動，車輛行進時持續取得 3D 資料，再依里程計行駛距離與姿態變化門檻把資料流切成各自參考一個車輛位姿的點雲，不必停車掃描。狀態向量是一串過去的位姿，里程計負責擴增狀態，相鄰點雲以帶 Geman-McClure 穩健核、並用 Levenberg-Marquardt 最小化的 ICP 式配準提供觀測。作者另以最近鄰距離直方圖訓練高斯分類器，在配準後判斷是否落入錯誤的局部極小值。","Delayed-state EKF 6-DoF SLAM from a continuously oscillating 2D laser, with odometry-based segmentation into pose-referenced clouds, robust-kernel Levenberg-Marquardt registration and a learned post-registration integrity check.","full_text_reviewed","peer_reviewed_published","background","未在營建工地驗證；實驗是車輛繞行一棟中型建築外部的平滑但不平坦路面，點雲中可辨識立面、窗戶、欄杆、逃生梯與腳踏車架（Sec. VII；Figs. 10-12）。以擺動 2D 雷射在行進中取得建物外部點雲並做迴圈修正，是行動式外牆掃描的早期形式；但論文沒有與獨立測量比對幾何精度（推論）。",[20],"completed_building",[22,23,24,25],"Data are gathered continuously while driving, avoiding the stop-acquire-move cycle of earlier 3D laser mapping (Sec. II).","A single loop-closure observation updates the entire delayed state and redistributes errors probabilistically (Sec. I; Sec. VII).","The integrity classifier detects scan matches that converged to incorrect local minima, which matters when initial estimates are poor (Sec. V; Sec. VIII).","After the loop-closure registration was accepted, the observation updated the whole delayed state; the corrected poses and reduced covariance ellipsoids are shown, with first and last poses not lining up exactly because the vehicle returned to a slightly different position (Sec. VII; Figs. 8-9).",[27,28,29,30,31],"An average registration covariance is used instead of a per-match estimate (Sec. III.B, footnote 1).","The Geman-McClure sigma is chosen by experimentation without an analytic method (Fig. 5 caption).","Uncertainty-based loop detection may trigger falsely or miss loops because the maintained Gaussian diverges from the true PDF (Sec. VI; Sec. VIII).","The integrity check needs supervised, hand-labelled training data (Sec. I; Sec. V).","The first loop-closure registration was poor because of the large accumulated error and needed repeated perturbation (Sec. VII).",[33,34],"custom 3D laser range finder: a standard 2D SICK scanner oscillating at 0.6 Hz about a horizontal axis (model not reported)","wheel odometry",[36],"vehicle (research vehicle; type not reported)","delayed-state (view-based) EKF whose state is a stack of past 6-DoF vehicle poses (x, y, z, roll, pitch, yaw); odometry augments the state and registration-derived inter-pose transforms are EKF observations (Sec. III)","ICP-like nearest-neighbour point matching with a Geman-McClure robust kernel minimized by Levenberg-Marquardt, approximate k-d tree queries, odometry transform as the initial estimate (Sec. IV; Algorithm 1)","discrete poses (one base pose per segmented point cloud)","within each segment, scans are transformed into the base pose frame with odometry; a segment ends early when an orientation-change threshold is exceeded and is kept only if it has enough points (Sec. II)","prompted when a past pose falls within the current pose uncertainty; the loop registration is re-seeded by perturbation until the integrity check accepts it (Sec. VI; Sec. VII); a companion paper handles robust detection","EKF update of the whole delayed-state vector with the loop-closure observation, redistributing error around the loop (Sec. I; Sec. III.B)","state vector of past 6-DoF poses with attached 3D point clouds","none (supervised training data for the integrity classifier)","6-DoF trajectory with marginal covariances and the attached point clouds rendered together (Figs. 10-12)","not_reported",null,"not_applicable",[50],{"relation":51,"title":52,"doi_or_url":53},"companion_paper","Newman, Cole and Ho, Outdoor SLAM using visual appearance and laser ranging, ICRA 2006 (loop detection; not read)","not_verified",{"id":5,"kind":55,"shortName":7,"title":8,"authors":56,"year":9,"venue":59,"venueType":60,"publisher":61,"volumeIssuePages":62,"doi":63,"arxivId":47,"url":64,"firstPublicDate":65,"publicationStatus":16,"metadataStatus":66,"fulltextStatus":15,"era":10,"classicReason":67,"codeUrl":47,"cluster":11,"topics":68,"mdpi":69,"verification":70,"label":6,"fulltextRoute":71,"versionRead":72,"addedByCensus":73},"method",[57,58],"David M. Cole","Paul M. Newman","Proceedings 2006 IEEE International Conference on Robotics and Automation (ICRA 2006), Orlando, FL","conference","IEEE","pp. 1556-1563","10.1109\u002Frobot.2006.1641929","https:\u002F\u002Fdoi.org\u002F10.1109\u002FROBOT.2006.1641929","2006-05","metadata_verified","necessary technical node: continuous-acquisition 3D laser SLAM on a moving vehicle with a probabilistic delayed-state back end and a learned registration-failure check; the paper contrasts it with the stop-acquire-move 3D scanning of Surmann et al. [surmann2003_kurt3d] and 6D SLAM (Sec. II, IV).",[11],false,"corrected","NTU institutional (curl)","IEEE Xplore version of record PDF (ICRA 2006, pp. 1556-1563, 8 pp.)",true,[75],{"category":76,"model":77,"canonical":77,"role":78,"dataset":47,"specs":79,"locator":80},"lidar","SICK scanner","method input","standard 2D scanner oscillating at 0.6 Hz about a horizontal axis to sweep a series of elevations (custom 3D laser range finder)","Sec. II; Fig. 1",[],{"totalRows":83,"groupCount":83,"groups":84,"others":114},1,[85],{"slug":86,"group":87,"sourceId":5,"sourceLabel":6,"table":88,"selfRows":83,"metrics":89,"seqs":94,"entrants":99,"cells":102,"outcomes":107,"locators":108,"hardware":110,"wordings":111,"notes":112},"cole-newman2006-3dslam-text-sec-vii","cole_newman2006_3dslam:Text Sec. VII","Text Sec. VII",[90],{"label":91,"unit":92,"statistic":46,"alignment":93},"vertical discrepancy between the first and last pose caused by accumulated error","m","first-pose",[95],{"dataset":96,"sequence":97,"environment":98},"authors' oscillating-SICK data","building-exterior loop","outdoor, around a building",[100],{"name":101,"methodId":5,"linkable":73,"proposed":73,"self":73},"delayed-state EKF 3D SLAM before loop closure",[103],[104,104,104,105,106,104,106,106,104],0,2.2,-1,[],[109],"Sec. VII; Fig. 8",[],[],[113],"Vehicle driven around the exterior of a medium-sized building on a smooth but non-flat surface; discrepancy between the first and last pose immediately before loop closure although the vehicle was in approximately the same place",[],1790510662563]