[{"data":1,"prerenderedAt":215},["ShallowReactive",2],{"method-adalio2023":3},{"method":4,"reference":52,"equipment":75,"figures":83,"results":84},{"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":27,"sensors":32,"platform":35,"estimator":37,"association":38,"timeModel":39,"deskew":40,"loopClosure":41,"globalOptimization":41,"mapRepresentation":42,"prior":41,"outputGeometry":43,"compute":44,"codeUrl":45,"codeLicense":46,"relatedVersions":47},"adalio2023","Lim et al., 2023","AdaLIO","AdaLIO: Robust Adaptive LiDAR-Inertial Odometry in Degenerate Indoor Environments",2023,"recent","C05","odometry_with_local_mapping","AdaLIO 以 Faster-LIO 為基礎，針對螺旋樓梯與走廊等狹窄室內空間中固定參數導致對應點驟減而發散的問題，加入自適應參數策略：當體素降取樣後的點數少於一般情況且多數佔用體素靠近感測器原點時，判定為類走廊的退化場景，改用較小的體素（0.2 m 改為 0.1 m）、較小的法向量搜尋半徑（3.0 m 改為 2.0 m）與較嚴格的平面殘差門檻（0.05 m 改為 0.025 m），以保留足夠且可靠的點到平面對應。濾波器、去畸變與體素地圖仍沿用 Faster-LIO。","Faster-LIO-based LIO that detects corridor-like degenerate scenes from a low voxelized point count with occupied voxels near the sensor and then switches to a smaller voxel size, search radius and plane residual margin to keep enough reliable point-to-plane correspondences.","full_text_reviewed","peer_reviewed_published","main_body","論文明確以營建工地與建物測繪為動機，並在 HILTI-Oxford 驗證集 Exp01 至 Exp06 上評估；依本資料庫 [zhang2023hiltioxford]，這些序列位於施工中的營建工地，參考值為毫米級控制點。AdaLIO 讓 Faster-LIO 在 Exp03 施工樓梯下行至地下停車場時不再發散，並在 Exp11 狹窄螺旋梯中維持追蹤。以 AdaLIO 為前端並加入 Quatro 迴圈偵測與 GTSAM 因子圖的 KAIST URL 團隊，在 Hilti SLAM Challenge 2023 單次作業 LiDAR 組排名第一（1177.64 分，RMSE ATE 0.033 m，控制點涵蓋 100%）[nair2024hilti2023]，但該成績來自完整 SLAM 系統，不能直接歸於本文的純里程計。",[20,21,22],"public_benchmark","real_construction_site","independent_reference",[24,25,26],"Passed the narrow spiral staircase of HILTI-Oxford Exp11 where Faster-LIO diverged (Sec. IV-B, Figs. 1 and 3)","Total validation score 354 versus 264 for Faster-LIO on Exp01 to Exp06; Faster-LIO diverged on Exp03 while AdaLIO scored 81 (Table II)","Same score as Faster-LIO on Exp02 and Exp04 without narrow spaces, so the adaptation does not degrade open-space results (Sec. IV-C)",[28,29,30,31],"Only compared against Faster-LIO; no runtime, trajectory ATE or other baselines reported (Sec. IV)","No marker was within 1 cm for either method in any validation sequence (Table II)","Degeneracy test uses unstated thresholds on point count and voxel distance; the two parameter sets are fixed values (Sec. III-C, Table I)","Authors leave a degeneracy-robust SLAM framework and tests on other robot platforms to future work (Sec. V)",[33,34],"3D LiDAR","IMU (HILTI-Oxford dataset sensors; models not named in the paper)",[36],"handheld (HILTI-Oxford sequences carried by a surveyor)","iterated error-state Kalman filter on manifold inherited from Faster-LIO, with IMU forward and backward propagation (Sec. III-B)","Faster-LIO nearest-neighbour search and point-to-plane residuals on a voxelized scan; when degeneracy is detected the voxel size (0.2 to 0.1 m), search radius (3.0 to 2.0 m) and plane residual margin (0.05 to 0.025 m) are reduced (Sec. III-C, Table I)","discrete poses with per-point IMU back-propagation (Faster-LIO) (Sec. III-B)","IMU forward and backward propagation (Sec. III-B)","none","global voxel map from Faster-LIO (incremental voxels) (Sec. III-B, Fig. 2)","odometry and accumulated point map (Fig. 4)","not_reported",null,"not_applicable (no public code found)",[48],{"relation":49,"title":50,"doi_or_url":51},"preprint","arXiv 2304.12577 v1 (2023-04-25), only version","https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.12577",{"id":5,"kind":53,"shortName":7,"title":8,"authors":54,"year":9,"venue":59,"venueType":60,"publisher":61,"volumeIssuePages":62,"doi":63,"arxivId":64,"url":65,"firstPublicDate":66,"publicationStatus":16,"metadataStatus":67,"fulltextStatus":15,"era":10,"classicReason":68,"codeUrl":45,"cluster":11,"topics":69,"mdpi":70,"verification":71,"label":6,"fulltextRoute":72,"versionRead":73,"addedByCensus":74},"method",[55,56,57,58],"Hyungtae Lim","Daebeom Kim","Beomsoo Kim","Hyun Myung","2023 20th International Conference on Ubiquitous Robots (UR)","conference","IEEE","pp. 48-53","10.1109\u002Fur57808.2023.10202252","2304.12577","https:\u002F\u002Fdoi.org\u002F10.1109\u002FUR57808.2023.10202252","2023-04-25","metadata_verified","not_applicable",[11],false,"confirmed","arXiv","arXiv v1 (2023-04-25; only version); IEEE UR 2023 version of record not read",true,[76],{"category":77,"model":78,"canonical":78,"role":79,"dataset":80,"specs":81,"locator":82},"platform","hand-carried HILTI-Oxford sensor rig (not described in the paper)","dataset sensor","HILTI-Oxford dataset","a surveyor descends stairs while carrying the device","Sec. IV-B; Sec. IV-C",[],{"totalRows":85,"groupCount":86,"groups":87,"others":214},28,1,[88],{"slug":89,"group":90,"sourceId":5,"sourceLabel":6,"table":91,"selfRows":85,"metrics":92,"seqs":103,"entrants":120,"cells":126,"outcomes":207,"locators":209,"hardware":210,"wordings":211,"notes":212},"adalio2023-table-ii","adalio2023:Table II","Table II",[93,96,98,100],{"label":94,"unit":95,"statistic":44,"alignment":44},"number of markers within 1 cm","count",{"label":97,"unit":95,"statistic":44,"alignment":44},"number of markers within 10 cm",{"label":99,"unit":95,"statistic":44,"alignment":44},"number of markers within 100 cm",{"label":101,"unit":102,"statistic":44,"alignment":44},"Score","points",[104,108,110,112,114,116,118],{"dataset":105,"sequence":106,"environment":107},"HILTI-Oxford dataset (HILTI SLAM Challenge 2022 validation set)","Exp01","construction-site building interiors, handheld",{"dataset":105,"sequence":109,"environment":107},"Exp02",{"dataset":105,"sequence":111,"environment":107},"Exp03",{"dataset":105,"sequence":113,"environment":107},"Exp04",{"dataset":105,"sequence":115,"environment":107},"Exp05",{"dataset":105,"sequence":117,"environment":107},"Exp06",{"dataset":105,"sequence":119,"environment":107},"Total",[121,124],{"name":122,"methodId":123,"linkable":74,"proposed":70,"self":70},"Faster-LIO [17]","fasterlio2022",{"name":125,"methodId":5,"linkable":74,"proposed":74,"self":74},"AdaLIO (Ours)",[127,130,132,135,138,139,141,143,145,146,147,148,149,150,152,153,155,157,158,159,161,162,163,164,165,166,168,170,172,173,175,176,178,179,180,181,182,183,184,186,188,189,190,191,192,193,194,195,196,197,198,199,200,201,203,205],[128,128,128,128,129,128,129,129,128],0,-1,[128,86,128,131,129,128,129,129,128],8,[128,133,128,134,129,128,129,129,128],2,5,[128,136,128,137,129,128,129,129,128],3,63,[128,128,86,128,129,128,129,129,128],[128,86,86,140,129,128,129,129,128],12,[128,133,86,142,129,128,129,129,128],10,[128,136,86,144,129,128,129,129,128],102,[128,128,133,45,128,128,129,129,128],[128,86,133,45,128,128,129,129,128],[128,133,133,45,128,128,129,129,128],[128,136,133,45,128,128,129,129,128],[128,128,136,128,129,128,129,129,128],[128,86,136,151,129,128,129,129,128],6,[128,133,136,86,129,128,129,129,128],[128,136,136,154,129,128,129,129,128],39,[128,128,156,128,129,128,129,129,128],4,[128,86,156,156,129,128,129,129,128],[128,133,156,133,129,128,129,129,128],[128,136,156,160,129,128,129,129,128],30,[128,128,134,128,129,128,129,129,128],[128,86,134,136,129,128,129,129,128],[128,133,134,156,129,128,129,129,128],[128,136,134,160,129,128,129,129,128],[128,128,151,128,129,128,129,129,128],[128,86,151,167,129,128,129,129,128],33,[128,133,151,169,129,128,129,129,128],22,[128,136,151,171,129,128,129,129,128],264,[86,128,128,128,129,128,129,129,128],[86,86,128,174,129,128,129,129,128],9,[86,133,128,156,129,128,129,129,128],[86,136,128,177,129,128,129,129,128],66,[86,128,86,128,129,128,129,129,128],[86,86,86,140,129,128,129,129,128],[86,133,86,142,129,128,129,129,128],[86,136,86,144,129,128,129,129,128],[86,128,133,128,129,128,129,129,128],[86,86,133,142,129,128,129,129,128],[86,133,133,185,129,128,129,129,128],7,[86,136,133,187,129,128,129,129,128],81,[86,128,136,128,129,128,129,129,128],[86,86,136,151,129,128,129,129,128],[86,133,136,86,129,128,129,129,128],[86,136,136,154,129,128,129,129,128],[86,128,156,128,129,128,129,129,128],[86,86,156,134,129,128,129,129,128],[86,133,156,86,129,128,129,129,128],[86,136,156,167,129,128,129,129,128],[86,128,134,128,129,128,129,129,128],[86,86,134,156,129,128,129,129,128],[86,133,134,136,129,128,129,129,128],[86,136,134,167,129,128,129,129,128],[86,128,151,128,129,128,129,129,128],[86,86,151,202,129,128,129,129,128],46,[86,133,151,204,129,128,129,129,128],26,[86,136,151,206,129,128,129,129,128],354,[208],"diverged",[91],[],[],[213],"HILTI-Oxford validation sequences with millimetre-level marker poses; each marker scored 10, 6 or 3 if the closest estimated pose is within 1, 10 or 100 cm; x = trajectory diverged",[],1790510657564]