[{"data":1,"prerenderedAt":543},["ShallowReactive",2],{"method-kissslam2025":3},{"method":4,"reference":59,"equipment":83,"figures":131,"results":132},{"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":33,"platform":35,"estimator":39,"association":40,"timeModel":41,"deskew":42,"loopClosure":43,"globalOptimization":44,"mapRepresentation":45,"prior":46,"outputGeometry":47,"compute":48,"codeUrl":49,"codeLicense":50,"relatedVersions":51},"kissslam2025","Guadagnino et al., 2025a","KISS-SLAM","KISS-SLAM: A Simple, Robust, and Accurate 3D LiDAR SLAM System With Enhanced Generalization Capabilities",2025,"recent","C05","full_slam_with_global_correction","KISS-SLAM 將 KISS-ICP 延伸為完整 LiDAR-only SLAM：依行進距離切分局部地圖，以關鍵位姿作為位姿圖節點。迴圈偵測將局部地圖地面對齊後投影成鳥瞰密度影像，以 ORB 描述子比對，再以 3D 配準與重疊率（門檻 40%）驗證後加入位姿圖最佳化。處理完成後另做離線細粒度位姿圖最佳化，將殘餘漂移分配到局部軌跡。","Extends KISS-ICP to LiDAR-only SLAM with distance-based local maps, BEV density-image ORB loop detection verified by 3D overlap, and pose-graph optimization, emphasizing minimal tuning.","full_text_reviewed","peer_reviewed_published","main_body","not_reported（評估為道路、校園與辦公室環境；辦公室僅用於導航定位測試）",[20,21],"public_benchmark","controlled_experiment",[23,24,25,26],"Same parameter configuration across MulRan, HeLiPR (Aeva, Avia and Ouster; VLP-16 excluded), Apollo, NCLT and Newer College (Sec. IV-A)","Only method with a result in every reported sequence; zero parameter changes across HeLiPR sensors and Newer College, versus 7 to 25 for PIN-SLAM, SuMa and CT-ICP; MULLS needed 0 changes between HeLiPR Avia and Ouster and 25 from Ouster to NCD-2020, with no working parameter set for pairs involving Aeva (Sec. IV-B; Sec. IV-C; Table VI)","Lower ATE than KISS-ICP odometry on all MulRan scenes, e.g. Sejong 178.88 m versus 316.20 m (version-of-record Table II)","Map output usable for 2D occupancy-grid global localization on a real robot; authors report no significant difference from a GMapping map, although pose-tracking ATE RMS was higher in the dynamic sequences (Sec. IV-D; Table VII)",[28,29,30,31,32],"Velodyne VLP-16 HeLiPR sequences excluded due to self-occlusion (Sec. IV-A)","Maximum range reduced from 100 m to 50 m for the office navigation experiment (Sec. IV-D)","Highest ATE among methods that ran on Newer College 2021 stairs (3.58 m) and 2021 cloister (0.40 m) (Table V)","Large absolute errors remain on HeLiPR Bridge (Aeva 98.61 m, Avia 148.88 m) and MulRan Sejong (178.88 m) (Tables II-III)","Loop closure relies on ground alignment and BEV projection (inference: may be less suited to multi-storey interiors without distinct floor layouts)",[34],"3D LiDAR only",[36,37,38],"vehicle","wheeled UGV","handheld","KISS-ICP odometry; pose graph over local-map keyposes; offline fine-grained pose graph over scan poses after processing","point-to-point ICP (odometry); loop verification by registration of voxel mean-and-normal clouds","discrete poses with constant-velocity deskew (KISS-ICP)","constant-velocity per-point deskew inherited from KISS-ICP","ground alignment, bird's-eye-view density images, ORB descriptors with database search, RANSAC 2D alignment, then 3D registration and overlap check (accepted above 40%)","pose graph optimization of local-map keyposes on accepted closures; final offline fine-grained PGO redistributing drift within local maps","keypose-anchored local maps (voxel grids) split by travelled distance; output 3D occupancy grid","none","globally corrected trajectory, local point maps and 3D occupancy grid (0.05 m voxels in navigation experiment)","faster than sensor frame rate on robot Intel NUC (i7, 32 GB RAM) (Sec. IV-D)","https:\u002F\u002Fgithub.com\u002FPRBonn\u002Fkiss-slam","MIT (LICENSE file checked)",[52,56],{"relation":53,"title":54,"doi_or_url":55},"preprint","KISS-SLAM (arXiv v1)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.12660",{"relation":57,"title":58,"doi_or_url":49},"code_release","PRBonn\u002Fkiss-slam",{"id":5,"kind":60,"shortName":7,"title":8,"authors":61,"year":9,"venue":68,"venueType":69,"publisher":70,"volumeIssuePages":71,"doi":72,"arxivId":73,"url":74,"firstPublicDate":75,"publicationStatus":16,"metadataStatus":76,"fulltextStatus":15,"era":10,"classicReason":77,"codeUrl":49,"cluster":11,"topics":78,"mdpi":79,"verification":80,"label":6,"fulltextRoute":81,"versionRead":82,"addedByCensus":79},"method",[62,63,64,65,66,67],"Tiziano Guadagnino","Benedikt Mersch","Saurabh Gupta","Ignacio Vizzo","Giorgio Grisetti","Cyrill Stachniss","2025 IEEE\u002FRSJ International Conference on Intelligent Robots and Systems (IROS)","conference","IEEE","pp. 5363-5370","10.1109\u002Firos60139.2025.11246613","2503.12660","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002FIROS60139.2025.11246613","2025-03-16","metadata_verified","not_applicable",[11],false,"corrected","NTU institutional (Chrome)","IEEE IROS 2025 version of record (pp. 5363-5370) read in full via NTU institutional access in Chrome; arXiv v1 (2503.12660v1) also read in full",[84,91,96,99,103,109,113,117,120,126],{"category":85,"model":86,"canonical":86,"role":87,"dataset":88,"specs":89,"locator":90},"lidar","Aeva","dataset sensor","HeLiPR","HeLiPR sensor with different ranging technology and scan pattern","Sec. IV-A; Table III; Table VI caption",{"category":85,"model":92,"canonical":93,"role":87,"dataset":88,"specs":94,"locator":95},"Avia","Livox Avia","HeLiPR sensor; non-repetitive pattern shown in Fig. 1","Fig. 1; Table III",{"category":85,"model":97,"canonical":97,"role":87,"dataset":88,"specs":98,"locator":95},"Ouster","HeLiPR scanner, called 'the Ouster scanner'; model not stated",{"category":85,"model":100,"canonical":100,"role":87,"dataset":88,"specs":101,"locator":102},"Velodyne VLP-16","excluded because of self-occlusion by surrounding sensors","Sec. IV-A",{"category":85,"model":104,"canonical":104,"role":105,"dataset":106,"specs":107,"locator":108},"Hesai XT-32","method input",null,"3D LiDAR used for mapping; max range processed reduced to 50 m indoors","Sec. IV-D; Fig. 3",{"category":110,"model":111,"canonical":111,"role":105,"dataset":106,"specs":112,"locator":108},"platform","Clearpath Husky","mapping robot carrying the Hesai XT-32",{"category":110,"model":114,"canonical":114,"role":115,"dataset":106,"specs":116,"locator":108},"Clearpath Dingo","compared device","second robot localized on the sliced 2D map; also recorded data for the GMapping baseline map",{"category":85,"model":118,"canonical":118,"role":115,"dataset":106,"specs":119,"locator":108},"SICK TiM781S","2D LiDAR mounted 0.16 m above ground on the Dingo",{"category":121,"model":122,"canonical":106,"role":123,"dataset":106,"specs":124,"locator":125},"camera","not_reported","reference or ground truth","upward-looking camera detecting AprilTags on the office ceiling to give ground-truth poses; model not stated","Sec. IV-D",{"category":127,"model":128,"canonical":128,"role":129,"dataset":106,"specs":130,"locator":125},"compute","Intel NUC","compute for runtime","Intel i7 processor, 32 GB RAM; KISS-SLAM ran faster than the sensor frame rate on board",[],{"totalRows":133,"groupCount":134,"groups":135,"others":530},33,6,[136,278,378,475],{"slug":137,"group":138,"sourceId":5,"sourceLabel":6,"table":139,"selfRows":140,"metrics":141,"seqs":145,"entrants":165,"cells":181,"outcomes":271,"locators":273,"hardware":274,"wordings":275,"notes":276},"kissslam2025-table-iii","kissslam2025:Table III","Table III",9,[142],{"label":143,"unit":144,"statistic":122,"alignment":122},"ATE [m] (evo)","m",[146,149,151,153,155,157,159,161,163],{"dataset":88,"sequence":147,"environment":148},"Bridge Aeva","urban driving with Aeva, Avia and Ouster LiDARs",{"dataset":88,"sequence":150,"environment":148},"Bridge Avia",{"dataset":88,"sequence":152,"environment":148},"Bridge Ouster",{"dataset":88,"sequence":154,"environment":148},"Roundabout Aeva",{"dataset":88,"sequence":156,"environment":148},"Roundabout Avia",{"dataset":88,"sequence":158,"environment":148},"Roundabout Ouster",{"dataset":88,"sequence":160,"environment":148},"Town Aeva",{"dataset":88,"sequence":162,"environment":148},"Town Avia",{"dataset":88,"sequence":164,"environment":148},"Town Ouster",[166,170,173,176,179],{"name":167,"methodId":168,"linkable":169,"proposed":79,"self":79},"PIN-SLAM","pinslam2024",true,{"name":171,"methodId":172,"linkable":169,"proposed":79,"self":79},"SuMa","suma2018",{"name":174,"methodId":175,"linkable":169,"proposed":79,"self":79},"CT-ICP","cticp2022",{"name":177,"methodId":178,"linkable":169,"proposed":79,"self":79},"MULLS","mulls2021",{"name":180,"methodId":5,"linkable":169,"proposed":169,"self":169},"Ours (KISS-SLAM)",[182,185,188,191,193,196,199,201,204,207,208,209,211,212,213,215,217,218,219,220,222,224,226,228,230,232,234,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269],[183,183,183,106,183,183,184,184,183],0,-1,[183,183,186,187,184,183,184,184,183],1,365.72,[183,183,189,190,184,183,184,184,183],2,19.23,[183,183,192,106,183,183,184,184,183],3,[183,183,194,195,184,183,184,184,183],4,7.02,[183,183,197,198,184,183,184,184,183],5,1.47,[183,183,134,200,184,183,184,184,183],41.19,[183,183,202,203,184,183,184,184,183],7,11.4,[183,183,205,206,184,183,184,184,183],8,2.55,[186,183,183,106,183,183,184,184,183],[186,183,186,106,183,183,184,184,183],[186,183,189,210,184,183,184,184,183],140.01,[186,183,192,106,183,183,184,184,183],[186,183,194,106,183,183,184,184,183],[186,183,197,214,184,183,184,184,183],14.88,[186,183,134,216,184,183,184,184,183],132.17,[186,183,202,106,183,183,184,184,183],[186,183,205,106,183,183,184,184,183],[189,183,183,106,183,183,184,184,183],[189,183,186,221,184,183,184,184,183],41.47,[189,183,189,223,184,183,184,184,183],579.62,[189,183,192,225,184,183,184,184,183],10.04,[189,183,194,227,184,183,184,184,183],3.36,[189,183,197,229,184,183,184,184,183],1.81,[189,183,134,231,184,183,184,184,183],65.29,[189,183,202,233,184,183,184,184,183],63.72,[189,183,205,106,183,183,184,184,183],[192,183,183,236,184,183,184,184,183],356.06,[192,183,186,238,184,183,184,184,183],321.87,[192,183,189,240,184,183,184,184,183],52.65,[192,183,192,242,184,183,184,184,183],19.08,[192,183,194,244,184,183,184,184,183],16.39,[192,183,197,246,184,183,184,184,183],2.65,[192,183,134,248,184,183,184,184,183],39.82,[192,183,202,250,184,183,184,184,183],14.93,[192,183,205,252,184,183,184,184,183],4.45,[194,183,183,254,184,183,184,184,183],98.61,[194,183,186,256,184,183,184,184,183],148.88,[194,183,189,258,184,183,184,184,183],19.47,[194,183,192,260,184,183,184,184,183],6.06,[194,183,194,262,184,183,184,184,183],3.84,[194,183,197,264,184,183,184,184,183],1.18,[194,183,134,266,184,183,184,184,183],14.44,[194,183,202,268,184,183,184,184,183],12.01,[194,183,205,270,184,183,184,184,183],1.99,[272],"failed ('-': error exceeded a sequence-specific threshold)",[139],[],[],[277],"ATE from evo; the paired relative KITTI metric (%) is omitted; '-' means the run failed because errors exceeded a sequence-specific threshold (version of record); same KISS-SLAM configuration for all runs; values averaged over three runs per scene",{"slug":279,"group":280,"sourceId":5,"sourceLabel":6,"table":281,"selfRows":202,"metrics":282,"seqs":284,"entrants":301,"cells":307,"outcomes":372,"locators":373,"hardware":374,"wordings":375,"notes":376},"kissslam2025-table-iv","kissslam2025:Table IV","Table IV",[283],{"label":143,"unit":144,"statistic":122,"alignment":122},[285,289,291,293,295,297,299],{"dataset":286,"sequence":287,"environment":288},"Apollo","BTS 2018-10-12","urban driving",{"dataset":286,"sequence":290,"environment":288},"CP 2018-10-11",{"dataset":286,"sequence":292,"environment":288},"H237 2018-10-12",{"dataset":286,"sequence":294,"environment":288},"MAVE 2018-10-12",{"dataset":286,"sequence":296,"environment":288},"SB 2018-10-03",{"dataset":286,"sequence":298,"environment":288},"SJD 2018-10-11 1",{"dataset":286,"sequence":300,"environment":288},"SJD 2018-10-11 2",[302,303,304,305,306],{"name":167,"methodId":168,"linkable":169,"proposed":79,"self":79},{"name":171,"methodId":172,"linkable":169,"proposed":79,"self":79},{"name":174,"methodId":175,"linkable":169,"proposed":79,"self":79},{"name":177,"methodId":178,"linkable":169,"proposed":79,"self":79},{"name":180,"methodId":5,"linkable":169,"proposed":169,"self":169},[308,310,312,314,316,318,320,322,324,325,327,329,330,331,332,334,336,338,340,342,344,346,348,350,352,354,355,357,359,361,363,365,367,369,370],[183,183,183,309,184,183,184,184,183],6.1,[183,183,186,311,184,183,184,184,183],0.64,[183,183,189,313,184,183,184,184,183],97.11,[183,183,192,315,184,183,184,184,183],7.06,[183,183,194,317,184,183,184,184,183],2.23,[183,183,197,319,184,183,184,184,183],1.86,[183,183,134,321,184,183,184,184,183],1.15,[186,183,183,323,184,183,184,184,183],181.19,[186,183,186,106,183,183,184,184,183],[186,183,189,326,184,183,184,184,183],366.66,[186,183,192,328,184,183,184,184,183],79.68,[186,183,194,106,183,183,184,184,183],[186,183,197,106,183,183,184,184,183],[186,183,134,106,183,183,184,184,183],[189,183,183,333,184,183,184,184,183],10.81,[189,183,186,335,184,183,184,184,183],0.97,[189,183,189,337,184,183,184,184,183],258.87,[189,183,192,339,184,183,184,184,183],61.39,[189,183,194,341,184,183,184,184,183],667.28,[189,183,197,343,184,183,184,184,183],0.78,[189,183,134,345,184,183,184,184,183],1.09,[192,183,183,347,184,183,184,184,183],104.14,[192,183,186,349,184,183,184,184,183],47.03,[192,183,189,351,184,183,184,184,183],354.21,[192,183,192,353,184,183,184,184,183],182.59,[192,183,194,106,183,183,184,184,183],[192,183,197,356,184,183,184,184,183],13.38,[192,183,134,358,184,183,184,184,183],11.41,[194,183,183,360,184,183,184,184,183],3.74,[194,183,186,362,184,183,184,184,183],0.8,[194,183,189,364,184,183,184,184,183],30.16,[194,183,192,366,184,183,184,184,183],9.08,[194,183,194,368,184,183,184,184,183],2.51,[194,183,197,189,184,183,184,184,183],[194,183,134,371,184,183,184,184,183],0.66,[272],[281],[],[],[377],"ATE from evo; the paired relative KITTI metric (%) is omitted; '-' means the run failed because errors exceeded a sequence-specific threshold (version of record); same KISS-SLAM configuration for all runs",{"slug":379,"group":380,"sourceId":5,"sourceLabel":6,"table":381,"selfRows":202,"metrics":382,"seqs":384,"entrants":401,"cells":407,"outcomes":470,"locators":471,"hardware":472,"wordings":473,"notes":474},"kissslam2025-table-v","kissslam2025:Table V","Table V",[383],{"label":143,"unit":144,"statistic":122,"alignment":122},[385,389,391,393,395,397,399],{"dataset":386,"sequence":387,"environment":388},"Newer College","2020 01-short","handheld campus, including 2021 stairs and underground",{"dataset":386,"sequence":390,"environment":388},"2020 02-long",{"dataset":386,"sequence":392,"environment":388},"2021 cloister",{"dataset":386,"sequence":394,"environment":388},"2021 math easy",{"dataset":386,"sequence":396,"environment":388},"2021 quad easy",{"dataset":386,"sequence":398,"environment":388},"2021 stairs",{"dataset":386,"sequence":400,"environment":388},"2021 underground easy",[402,403,404,405,406],{"name":167,"methodId":168,"linkable":169,"proposed":79,"self":79},{"name":171,"methodId":172,"linkable":169,"proposed":79,"self":79},{"name":174,"methodId":175,"linkable":169,"proposed":79,"self":79},{"name":177,"methodId":178,"linkable":169,"proposed":79,"self":79},{"name":180,"methodId":5,"linkable":169,"proposed":169,"self":169},[408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,441,442,444,445,446,448,450,452,453,454,456,458,460,462,464,465,466,468],[183,183,183,409,184,183,184,184,183],0.42,[183,183,186,411,184,183,184,184,183],0.31,[183,183,189,413,184,183,184,184,183],0.15,[183,183,192,415,184,183,184,184,183],0.08,[183,183,194,417,184,183,184,184,183],0.09,[183,183,197,419,184,183,184,184,183],0.06,[183,183,134,421,184,183,184,184,183],0.07,[186,183,183,423,184,183,184,184,183],2.06,[186,183,186,425,184,183,184,184,183],5.77,[186,183,189,427,184,183,184,184,183],0.17,[186,183,192,429,184,183,184,184,183],0.16,[186,183,194,431,184,183,184,184,183],0.21,[186,183,197,433,184,183,184,184,183],1.85,[186,183,134,435,184,183,184,184,183],0.11,[189,183,183,437,184,183,184,184,183],0.63,[189,183,186,439,184,183,184,184,183],25.06,[189,183,189,427,184,183,184,184,183],[189,183,192,417,184,183,184,184,183],[189,183,194,443,184,183,184,184,183],0.19,[189,183,197,106,183,183,184,184,183],[189,183,134,413,184,183,184,184,183],[192,183,183,447,184,183,184,184,183],0.47,[192,183,186,449,184,183,184,184,183],8.47,[192,183,189,451,184,183,184,184,183],0.13,[192,183,192,451,184,183,184,184,183],[192,183,194,429,184,183,184,184,183],[192,183,197,455,184,183,184,184,183],1.82,[192,183,134,457,184,183,184,184,183],0.69,[194,183,183,459,184,183,184,184,183],0.3,[194,183,186,461,184,183,184,184,183],1.58,[194,183,189,463,184,183,184,184,183],0.4,[194,183,192,413,184,183,184,184,183],[194,183,194,429,184,183,184,184,183],[194,183,197,467,184,183,184,184,183],3.58,[194,183,134,469,184,183,184,184,183],0.12,[272],[381],[],[],[377],{"slug":476,"group":477,"sourceId":5,"sourceLabel":6,"table":478,"selfRows":197,"metrics":479,"seqs":484,"entrants":497,"cells":503,"outcomes":524,"locators":525,"hardware":526,"wordings":527,"notes":528},"kissslam2025-table-vii","kissslam2025:Table VII","Table VII",[480],{"label":481,"unit":482,"statistic":483,"alignment":122},"ATE translation RMS [cm] (mean over 10 runs)","cm","RMSE",[485,489,491,493,495],{"dataset":486,"sequence":487,"environment":488},"authors' office sequences","Static Sequence 1","office (static and dynamic scenes)",{"dataset":486,"sequence":490,"environment":488},"Static Sequence 2",{"dataset":486,"sequence":492,"environment":488},"Static Sequence 3",{"dataset":486,"sequence":494,"environment":488},"Dynamic Sequence 1",{"dataset":486,"sequence":496,"environment":488},"Dynamic Sequence 2",[498,501],{"name":499,"methodId":500,"linkable":169,"proposed":79,"self":79},"GMapping map","gmapping2007",{"name":502,"methodId":5,"linkable":169,"proposed":169,"self":169},"Ours (KISS-SLAM map)",[504,506,508,510,512,514,516,518,520,522],[183,183,183,505,184,183,184,184,183],9.48,[186,183,183,507,184,183,184,184,183],9.71,[183,183,186,509,184,183,184,184,183],9.88,[186,183,186,511,184,183,184,184,183],9.26,[183,183,189,513,184,183,184,184,183],9.68,[186,183,189,515,184,183,184,184,183],8.51,[183,183,192,517,184,183,184,184,183],5.71,[186,183,192,519,184,183,184,184,183],9.57,[183,183,194,521,184,183,184,184,183],7.43,[186,183,194,523,184,183,184,184,183],10.42,[],[478],[],[],[529],"2D Monte-Carlo localization (RVP-Loc, Clearpath Dingo with SICK TiM781S) on a 2D map sliced from the KISS-SLAM 3D occupancy grid versus a GMapping map; pose-tracking ATE translation RMS, mean of 10 runs; ground truth from ceiling AprilTags seen by an upward camera; success rate and convergence time columns omitted",[531,537],{"group":532,"slug":533,"sourceLabel":6,"table":534,"selfRows":194,"datasets":535},"kissslam2025:Table II","kissslam2025-table-ii","Table II",[536],"MulRan",{"group":538,"slug":539,"sourceLabel":6,"table":540,"selfRows":186,"datasets":541},"kissslam2025:Table I","kissslam2025-table-i","Table I",[542],"NCLT",1790510654074]