[{"data":1,"prerenderedAt":599},["ShallowReactive",2],{"method-dynablox2023":3},{"method":4,"reference":50,"equipment":72,"figures":93,"results":94},{"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":23,"limitations":28,"sensors":32,"platform":34,"estimator":36,"association":37,"timeModel":38,"deskew":39,"loopClosure":38,"globalOptimization":38,"mapRepresentation":40,"prior":41,"outputGeometry":42,"compute":43,"codeUrl":44,"codeLicense":45,"relatedVersions":46},"dynablox2023","Schmid et al., 2023","Dynablox","Dynablox: Real-Time Detection of Diverse Dynamic Objects in Complex Environments",2023,"recent","C06","map_representation_or_reconstruction","Dynablox 延伸 Voxblox 的雜湊區塊體素地圖，在機器人運作中逐步估計「高信心自由空間」，並同時建模感測雜訊與稀疏性、狀態估計漂移及地圖不完整；落入高信心自由空間的點即判定為移動點，再以其為種子擴張叢集。方法不假設物體外觀或類別，可偵測搬運物品的人、擺動的門等多樣動態物。","Dynablox detects moving points online as those falling into conservatively estimated high-confidence free space in a volumetric map, accounting for noise, sparsity, drift and incomplete mapping.","full_text_reviewed","peer_reviewed_published","main_body","作者以多層建築與樓梯等複雜室內場景做定性示範（abstract）；無工地測試。窗戶等反射面與細薄物體為已報告失效（Sec. VII-F），與施工中建築的玻璃、鷹架、防護網相關（推論）。",[20,21,22],"public_benchmark","completed_building","simulation",[24,25,26,27],"86.0% IoU over all DOALS sequences with a 20 m range and 83.8% at full range (up to 172.7 m), above the learning-based baselines and below the offline Occupancy upper bound of 88% (Table I, Sec. VII-A)","58.1 ms per frame (17.2 FPS) at 20 m integration distance on an AMD 4800U NUC, about 39% (38.8%) above conventional TSDF mapping (Sec. VII-D)","Recall largely independent of simulated drift and still 72% in the worst case; precision loss under drift mitigated by τr, whose correct setting improves performance by up to 88% (Sec. VII-C, Fig. 4)","Class-agnostic: detected people carrying boxes, rolling cases or surfboards, rolling balls and swinging doors on stairs and across storeys (Sec. VII-B, Fig. 3)",[29,30,31],"Thin, sparsely measured objects, reflective surfaces such as windows, and strong occlusions cause failures (Sec. VII-F)","Relies on dense mapping requiring sufficiently high data rates for the sensor speed (Sec. VII-F)","Stated in follow-up work by theory-based analysis (not an experiment): cannot handle non-sequential data such as static survey scans (dufomap2024 Sec. V-B2)",[33],"3D LiDAR",[35],"not_verified","not_applicable (uses external state estimate, e.g., FAST-LIO2 in new sequences)","a voxel is occupied if its TSDF distance is below 1.5 voxel sizes or a current point falls in it, with a sparsity compensation of 2 frames; it becomes high-confidence free only after 5 frames unoccupied for itself and all observed neighbours; points in or next to free voxels seed clusters grown over connected voxels, clusters under 20 voxels discarded; slowly re-occupied voxels are reset after τr frames derived from the expected drift rate (Sec. IV-C, IV-D)","not_applicable","not_reported","Voxblox hashed voxel blocks (16^3 voxels per block, voxel size 0.2 m) holding a TSDF; each voxel additionally stores the last occupied frame, the occupancy duration and a high-confidence free flag; voxels in dynamic clusters are overwritten rather than averaged at the next update (Sec. IV-A, IV-D)","online state estimate with a drift-tolerance parameter","per-point dynamic labels during online mapping; static volumetric map","real-time on a NUC with laptop-grade AMD 4800U CPU: pre-processing constant at 13.0 ms; total 58.1 ms per frame (17.2 FPS) at 20 m integration distance; TSDF integration and free-space update scale with the number of updated blocks, so unbounded range is slower in large open spaces such as the Station scenes (Sec. V, VII-D, Fig. 5)","https:\u002F\u002Fgithub.com\u002Fethz-asl\u002Fdynablox","BSD-3-Clause (LICENSE file)",[47],{"relation":48,"title":49,"doi_or_url":44},"code_release","ethz-asl\u002Fdynablox",{"id":5,"kind":51,"shortName":7,"title":8,"authors":52,"year":9,"venue":58,"venueType":59,"publisher":60,"volumeIssuePages":61,"doi":62,"arxivId":63,"url":64,"firstPublicDate":65,"publicationStatus":16,"metadataStatus":66,"fulltextStatus":15,"era":10,"classicReason":38,"codeUrl":44,"cluster":11,"topics":67,"mdpi":68,"verification":69,"label":6,"fulltextRoute":70,"versionRead":71,"addedByCensus":68},"method",[53,54,55,56,57],"Lukas Schmid","Olov Andersson","Aurelio Sulser","Patrick Pfreundschuh","Roland Siegwart","IEEE Robotics and Automation Letters","journal","IEEE","8(10):6259-6266","10.1109\u002Flra.2023.3305239","2304.10049","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.10049","2023-04-20","metadata_verified",[11],false,"corrected","arXiv","arXiv v3 (2023-09-26), accepted RA-L preprint (accepted August 2023); IEEE version of record 8(10):6259-6266 not read",[73,81,87],{"category":74,"model":75,"canonical":76,"role":77,"dataset":78,"specs":79,"locator":80},"lidar","OS1 64","Ouster OS1-64","dataset sensor","DOALS","high-range, high-resolution, 10 Hz; 8 sequences in 4 environments","Sec. VI",{"category":74,"model":82,"canonical":82,"role":83,"dataset":84,"specs":85,"locator":86},"Ouster OS0","method input","Dynablox newly recorded sequences","128 beams (written 'OS0 128' in Sec. VI and '128-beam Ouster OS0' in Sec. IV-C), high-range, high-resolution, 90 deg vertical FoV, 10 Hz; state estimates from FAST-LIO2","Sec. IV-C, Sec. VI",{"category":88,"model":89,"canonical":89,"role":90,"dataset":91,"specs":92,"locator":80},"compute","NUC with laptop-grade AMD-4800U CPU","compute for runtime",null,"also used in some of the authors' aerial and ground robots; all experiments",[],{"totalRows":95,"groupCount":96,"groups":97,"others":576},46,8,[98,302,430,533],{"slug":99,"group":100,"sourceId":101,"sourceLabel":102,"table":103,"selfRows":104,"metrics":105,"seqs":114,"entrants":130,"cells":147,"outcomes":296,"locators":297,"hardware":298,"wordings":299,"notes":300},"dufomap2024-table-i","dufomap2024:Table I","dufomap2024","Duberg et al., 2024","Table I",12,[106,110,112],{"label":107,"unit":108,"statistic":39,"alignment":109},"SA (static accuracy, share of static points correctly kept)","%","none",{"label":111,"unit":108,"statistic":39,"alignment":109},"DA (dynamic accuracy, share of dynamic points correctly labelled)",{"label":113,"unit":108,"statistic":39,"alignment":109},"AA (associated accuracy, sqrt(SA x DA))",[115,119,122,126],{"dataset":116,"sequence":117,"environment":118},"KITTI (SemanticKITTI labels and poses)","00 small town","small town (HDL-64E)",{"dataset":116,"sequence":120,"environment":121},"01 highway","highway (HDL-64E)",{"dataset":123,"sequence":124,"environment":125},"Argoverse 2","big city","urban big city (two VLP-32C)",{"dataset":127,"sequence":128,"environment":129},"Semi-indoor (self-collected)","semi-indoor","highly structured semi-indoor area, sparse 16-channel LiDAR (VLP-16)",[131,135,138,141,143,145],{"name":132,"methodId":133,"linkable":134,"proposed":68,"self":68},"Removert [8]","removert2020",true,{"name":136,"methodId":137,"linkable":134,"proposed":68,"self":68},"ERASOR [9]","erasor2021",{"name":139,"methodId":140,"linkable":134,"proposed":68,"self":68},"OctoMap [16]","hornung2013octomap",{"name":142,"methodId":101,"linkable":134,"proposed":134,"self":68},"DUFOMap (Ours)",{"name":144,"methodId":5,"linkable":134,"proposed":68,"self":134},"Dynablox [17]",{"name":146,"methodId":101,"linkable":134,"proposed":134,"self":68},"DUFOMap* (Ours, online)",[148,152,155,158,160,162,164,166,168,170,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,248,251,253,255,257,259,261,263,265,266,268,270,272,275,277,279,281,283,285,287,289,291,293,295],[149,149,149,150,151,149,151,151,149],0,99.44,-1,[149,153,149,154,151,149,151,151,149],1,41.53,[149,156,149,157,151,149,151,151,149],2,64.26,[149,149,153,159,151,149,151,151,149],97.81,[149,153,153,161,151,149,151,151,149],39.56,[149,156,153,163,151,149,151,151,149],62.2,[149,149,156,165,151,149,151,151,149],98.97,[149,153,156,167,151,149,151,151,149],31.16,[149,156,156,169,151,149,151,151,149],55.53,[149,149,171,172,151,149,151,151,149],3,99.96,[149,153,171,174,151,149,151,151,149],12.15,[149,156,171,176,151,149,151,151,149],34.85,[153,149,149,178,151,149,151,151,149],66.7,[153,153,149,180,151,149,151,151,149],98.54,[153,156,149,182,151,149,151,151,149],81.07,[153,149,153,184,151,149,151,151,149],98.12,[153,153,153,186,151,149,151,151,149],90.94,[153,156,153,188,151,149,151,151,149],94.46,[153,149,156,190,151,149,151,151,149],77.51,[153,153,156,192,151,149,151,151,149],99.18,[153,156,156,194,151,149,151,151,149],87.68,[153,149,171,196,151,149,151,151,149],94.9,[153,153,171,198,151,149,151,151,149],66.26,[153,156,171,200,151,149,151,151,149],79.3,[156,149,149,202,151,149,151,151,149],68.05,[156,153,149,204,151,149,151,151,149],99.69,[156,156,149,206,151,149,151,151,149],82.37,[156,149,153,208,151,149,151,151,149],55.55,[156,153,153,210,151,149,151,151,149],99.59,[156,156,153,212,151,149,151,151,149],74.38,[156,149,156,214,151,149,151,151,149],69.04,[156,153,156,216,151,149,151,151,149],97.5,[156,156,156,218,151,149,151,151,149],82.04,[156,149,171,220,151,149,151,151,149],88.97,[156,153,171,222,151,149,151,151,149],82.18,[156,156,171,224,151,149,151,151,149],85.51,[171,149,149,226,151,149,151,151,149],97.96,[171,153,149,228,151,149,151,151,149],98.72,[171,156,149,230,151,149,151,151,149],98.34,[171,149,153,232,151,149,151,151,149],98.09,[171,153,153,234,151,149,151,151,149],94.2,[171,156,153,236,151,149,151,151,149],96.12,[171,149,156,238,151,149,151,151,149],96.67,[171,153,156,240,151,149,151,151,149],88.9,[171,156,156,242,151,149,151,151,149],92.7,[171,149,171,244,151,149,151,151,149],99.64,[171,153,171,246,151,149,151,151,149],83,[171,156,171,186,151,149,151,151,149],[249,149,149,250,151,149,151,151,149],4,96.76,[249,153,149,252,151,149,151,151,149],90.68,[249,156,149,254,151,149,151,151,149],93.67,[249,149,153,256,151,149,151,151,149],96.33,[249,153,153,258,151,149,151,151,149],68.01,[249,156,153,260,151,149,151,151,149],80.94,[249,149,156,262,151,149,151,151,149],96.08,[249,153,156,264,151,149,151,151,149],92.87,[249,156,156,188,151,149,151,151,149],[249,149,171,267,151,149,151,151,149],98.81,[249,153,171,269,151,149,151,151,149],36.49,[249,156,171,271,151,149,151,151,149],60.05,[273,149,149,274,151,149,151,151,149],5,98.37,[273,153,149,276,151,149,151,151,149],92.37,[273,156,149,278,151,149,151,151,149],95.31,[273,149,153,280,151,149,151,151,149],98.48,[273,153,153,282,151,149,151,151,149],81.34,[273,156,153,284,151,149,151,151,149],89.5,[273,149,156,286,151,149,151,151,149],98.66,[273,153,156,288,151,149,151,151,149],73.98,[273,156,156,290,151,149,151,151,149],85.43,[273,149,171,292,151,149,151,151,149],99.94,[273,153,171,294,151,149,151,151,149],54.76,[273,156,171,288,151,149,151,151,149],[],[103],[],[],[301],"Point-wise dynamic point removal accuracy (%) following the DynamicMap benchmark protocol; Removert, ERASOR, OctoMap and DUFOMap evaluated offline, Dynablox and DUFOMap* online (each scan classified with the map built so far); DUFOMap uses the same parameters for all data (voxel 0.1 m, ds 0.2 m, dp 1), Removert and ERASOR per-dataset optimized parameters; KITTI labels and poses from SemanticKITTI",{"slug":303,"group":304,"sourceId":5,"sourceLabel":6,"table":103,"selfRows":305,"metrics":306,"seqs":310,"entrants":322,"cells":341,"outcomes":423,"locators":425,"hardware":426,"wordings":427,"notes":428},"dynablox2023-table-i","dynablox2023:Table I",10,[307],{"label":308,"unit":108,"statistic":309,"alignment":109},"Dynamic point detection IoU [%]","mean",[311,314,316,318,320],{"dataset":78,"sequence":312,"environment":313},"Station","DOALS environment as named",{"dataset":78,"sequence":315,"environment":313},"Shopville",{"dataset":78,"sequence":317,"environment":313},"HG",{"dataset":78,"sequence":319,"environment":313},"Niederdorf",{"dataset":78,"sequence":321,"environment":313},"All",[323,325,327,329,331,333,335,337,339],{"name":324,"methodId":91,"linkable":68,"proposed":68,"self":68},"Occupancy [10] (Offline)",{"name":326,"methodId":91,"linkable":68,"proposed":68,"self":68},"DOALS-3DMiniNet [10,28]",{"name":328,"methodId":91,"linkable":68,"proposed":68,"self":68},"4DMOS [14]",{"name":330,"methodId":91,"linkable":68,"proposed":68,"self":68},"LMNet [8] (Original)",{"name":332,"methodId":91,"linkable":68,"proposed":68,"self":68},"LMNet [8] (Refit)",{"name":334,"methodId":91,"linkable":68,"proposed":68,"self":68},"MotionSeg3D [9]",{"name":336,"methodId":5,"linkable":134,"proposed":134,"self":134},"Ours",{"name":338,"methodId":91,"linkable":68,"proposed":68,"self":68},"LC Free Space [22] (20m)",{"name":340,"methodId":5,"linkable":134,"proposed":134,"self":134},"Ours (20m)",[342,344,346,348,350,351,353,355,356,358,359,361,363,365,367,369,371,373,375,376,378,380,382,384,386,388,389,390,391,392,393,395,397,399,401,403,406,408,410,412,414,416,418,420,422],[149,149,149,343,151,149,151,151,149],91,[149,149,153,345,151,149,151,151,149],85,[149,149,156,347,151,149,151,151,149],88,[149,149,171,349,151,149,151,151,149],87,[149,149,249,347,151,149,151,151,149],[153,149,149,352,151,149,151,151,149],84,[153,149,153,354,151,149,151,151,149],82,[153,149,156,354,151,149,151,151,149],[153,149,171,357,151,149,151,151,149],80,[153,149,249,354,151,149,151,151,149],[156,149,149,360,151,149,151,151,149],38.8,[156,149,153,362,151,149,151,151,149],50.6,[156,149,156,364,151,149,151,151,149],71.1,[156,149,171,366,151,149,151,151,149],40.2,[156,149,249,368,151,149,151,151,149],50.2,[171,149,149,370,151,149,151,151,149],6,[171,149,153,372,151,149,151,151,149],7.5,[171,149,156,374,151,149,151,151,149],4.6,[171,149,171,171,151,149,151,151,149],[171,149,249,377,151,149,151,151,149],5.2,[249,149,149,379,151,149,151,151,149],19.9,[249,149,153,381,151,149,151,151,149],18.9,[249,149,156,383,151,149,151,151,149],27.4,[249,149,171,385,151,149,151,151,149],40.1,[249,149,249,387,151,149,151,151,149],26.6,[273,149,149,91,149,149,151,151,149],[273,149,153,91,149,149,151,151,149],[273,149,156,91,149,149,151,151,149],[273,149,171,91,149,149,151,151,149],[273,149,249,91,149,149,151,151,149],[370,149,149,394,151,149,151,151,149],86.2,[370,149,153,396,151,149,151,151,149],83.2,[370,149,156,398,151,149,151,151,149],84.1,[370,149,171,400,151,149,151,151,149],81.6,[370,149,249,402,151,149,151,151,149],83.8,[404,149,149,405,151,149,151,151,149],7,48.7,[404,149,153,407,151,149,151,151,149],31.9,[404,149,156,409,151,149,151,151,149],24.7,[404,149,171,411,151,149,151,151,149],17.7,[404,149,249,413,151,149,151,151,149],30.7,[96,149,149,415,151,149,151,151,149],87.3,[96,149,153,417,151,149,151,151,149],87.8,[96,149,156,419,151,149,151,151,149],86,[96,149,171,421,151,149,151,151,149],83.1,[96,149,249,419,151,149,151,151,149],[424],"no meaningful result (marked x in table)",[103],[],[],[429],"DOALS (OS1 64 at 10 Hz, 8 sequences in 4 environments): IoU (%) between detected and annotated dynamic points, mean over the 10 annotated frames per sequence; full range up to 172.7 m unless marked (20m); Occupancy is offline with past and future scans (upper limit); DOALS-3DMiniNet trained on the other DOALS environments; 4DMOS, LMNet and MotionSeg3D pre-trained on KITTI, 'Refit' refits model statistics on DOALS; NUC with AMD 4800U",{"slug":431,"group":432,"sourceId":101,"sourceLabel":102,"table":433,"selfRows":434,"metrics":435,"seqs":439,"entrants":447,"cells":454,"outcomes":527,"locators":528,"hardware":529,"wordings":530,"notes":531},"dufomap2024-table-iii","dufomap2024:Table III","Table III",9,[436,437,438],{"label":107,"unit":108,"statistic":39,"alignment":109},{"label":111,"unit":108,"statistic":39,"alignment":109},{"label":113,"unit":108,"statistic":39,"alignment":109},[440,443,445],{"dataset":441,"sequence":442,"environment":118},"KITTI (SemanticKITTI labels)","00 (KITTI GT poses)",{"dataset":441,"sequence":444,"environment":118},"00 (SuMa poses (SemanticKITTI))",{"dataset":441,"sequence":446,"environment":118},"00 (KISS-ICP poses)",[448,449,450,452,453],{"name":132,"methodId":133,"linkable":134,"proposed":68,"self":68},{"name":136,"methodId":137,"linkable":134,"proposed":68,"self":68},{"name":451,"methodId":140,"linkable":134,"proposed":68,"self":68},"Octomap [16]",{"name":144,"methodId":5,"linkable":134,"proposed":68,"self":134},{"name":142,"methodId":101,"linkable":134,"proposed":134,"self":68},[455,456,458,460,461,462,463,465,467,469,471,473,475,476,477,478,480,482,484,486,488,490,491,492,493,495,497,499,501,503,504,505,506,507,509,511,513,515,517,518,519,520,521,523,525],[149,149,149,192,151,149,151,151,149],[149,153,149,457,151,149,151,151,149],41.71,[149,156,149,459,151,149,151,151,149],64.32,[149,149,153,150,151,149,151,151,149],[149,153,153,154,151,149,151,151,149],[149,156,153,157,151,149,151,151,149],[149,149,156,464,151,149,151,151,149],99.55,[149,153,156,466,151,149,151,151,149],41.45,[149,156,156,468,151,149,151,151,149],64.23,[153,149,149,470,151,149,151,151,149],63.83,[153,153,149,472,151,149,151,151,149],98.35,[153,156,149,474,151,149,151,151,149],79.23,[153,149,153,178,151,149,151,151,149],[153,153,153,180,151,149,151,151,149],[153,156,153,182,151,149,151,151,149],[153,149,156,479,151,149,151,151,149],67.86,[153,153,156,481,151,149,151,151,149],98.68,[153,156,156,483,151,149,151,151,149],81.83,[156,149,149,485,151,149,151,151,149],54.81,[156,153,149,487,151,149,151,151,149],99.56,[156,156,149,489,151,149,151,151,149],73.87,[156,149,153,202,151,149,151,151,149],[156,153,153,204,151,149,151,151,149],[156,156,153,206,151,149,151,151,149],[156,149,156,494,151,149,151,151,149],62.28,[156,153,156,496,151,149,151,151,149],99.85,[156,156,156,498,151,149,151,151,149],78.85,[171,149,149,500,151,149,151,151,149],95.5,[171,153,149,502,151,149,151,151,149],89.34,[171,156,149,276,151,149,151,151,149],[171,149,153,250,151,149,151,151,149],[171,153,153,252,151,149,151,151,149],[171,156,153,254,151,149,151,151,149],[171,149,156,508,151,149,151,151,149],98.31,[171,153,156,510,151,149,151,151,149],90.97,[171,156,156,512,151,149,151,151,149],94.57,[249,149,149,514,151,149,151,151,149],92.57,[249,153,149,516,151,149,151,151,149],98.52,[249,156,149,500,151,149,151,151,149],[249,149,153,226,151,149,151,151,149],[249,153,153,228,151,149,151,151,149],[249,156,153,230,151,149,151,151,149],[249,149,156,522,151,149,151,151,149],99.33,[249,153,156,524,151,149,151,151,149],98.73,[249,156,156,526,151,149,151,151,149],99.03,[],[433],[],[],[532],"Influence of the pose source on dynamic point removal, KITTI sequence 00: KITTI odometry ground-truth poses, SemanticKITTI poses estimated by SuMa, and KISS-ICP poses; SA, DA, AA in %",{"slug":534,"group":535,"sourceId":5,"sourceLabel":6,"table":536,"selfRows":404,"metrics":537,"seqs":540,"entrants":542,"cells":556,"outcomes":570,"locators":571,"hardware":572,"wordings":573,"notes":574},"dynablox2023-table-ii","dynablox2023:Table II","Table II",[538],{"label":539,"unit":108,"statistic":309,"alignment":109},"IoU [%] at 20 m",[541],{"dataset":78,"sequence":321,"environment":313},[543,544,546,548,550,552,554],{"name":336,"methodId":5,"linkable":134,"proposed":134,"self":134},{"name":545,"methodId":5,"linkable":134,"proposed":134,"self":134},"Dynablox (w\u002Fo Occupancy Cue)",{"name":547,"methodId":5,"linkable":134,"proposed":134,"self":134},"Dynablox (w\u002Fo TSDF Cue)",{"name":549,"methodId":5,"linkable":134,"proposed":134,"self":134},"Dynablox (w\u002Fo temporal window τw)",{"name":551,"methodId":5,"linkable":134,"proposed":134,"self":134},"Dynablox (w\u002Fo Sparsity Comp. τs)",{"name":553,"methodId":5,"linkable":134,"proposed":134,"self":134},"Dynablox (w\u002Fo Spatial Margin N)",{"name":555,"methodId":5,"linkable":134,"proposed":134,"self":134},"Dynablox (w\u002Fo Cluster Filter τc)",[557,558,560,562,564,566,568],[149,149,149,419,151,149,151,151,149],[153,149,149,559,151,149,151,151,149],85.6,[156,149,149,561,151,149,151,151,149],23.6,[171,149,149,563,151,149,151,151,149],11.6,[249,149,149,565,151,149,151,151,149],83.3,[273,149,149,567,151,149,151,151,149],38.1,[370,149,149,569,151,149,151,151,149],85.3,[],[536],[],[],[575],"Ablation of the modelled components at 20 m range on DOALS (IoU %, all sequences)",[577,583,588,593],{"group":578,"slug":579,"sourceLabel":6,"table":580,"selfRows":249,"datasets":581},"dynablox2023:Text Sec.VII-D","dynablox2023-text-sec-vii-d","Text Sec.VII-D",[582],"not named for the timing (Fig. 5 'different datasets'; the DOALS Station environment is named in Sec. VII-D)",{"group":584,"slug":585,"sourceLabel":102,"table":536,"selfRows":156,"datasets":586},"dufomap2024:Table II","dufomap2024-table-ii",[587,127],"KITTI",{"group":589,"slug":590,"sourceLabel":102,"table":591,"selfRows":153,"datasets":592},"dufomap2024:Text Sec.V-A2","dufomap2024-text-sec-v-a2","Text Sec.V-A2",[127],{"group":594,"slug":595,"sourceLabel":6,"table":596,"selfRows":153,"datasets":597},"dynablox2023:Text Sec.VII-C","dynablox2023-text-sec-vii-c","Text Sec.VII-C",[598],"DOALS with simulated drift",1790510664910]