[{"data":1,"prerenderedAt":178},["ShallowReactive",2],{"method-kayhani2022tagvio":3},{"method":4,"reference":53,"equipment":74,"figures":105,"results":106},{"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":34,"platform":37,"estimator":40,"association":41,"timeModel":42,"deskew":43,"loopClosure":44,"globalOptimization":45,"mapRepresentation":46,"prior":47,"outputGeometry":48,"compute":49,"codeUrl":50,"codeLicense":51,"relatedVersions":52},"kayhani2022tagvio","Kayhani et al., 2022","Tag-based VIO for indoor construction UAVs","Tag-based visual-inertial localization of unmanned aerial vehicles in indoor construction environments using an on-manifold extended Kalman filter",2022,"recent","C11b","localization_in_prior_map_or_bim","作者為低成本商用無人機提出以平面標籤輔助的視覺慣性定位。AprilTag 的尺寸、編號與在 BIM 座標系中的位姿事先已知，濾波器以機上里程計提供的平移與旋轉速度做預測，並直接把每個偵測到的標籤四個角點的像素座標當作量測來修正，而不是使用偵測器輸出的相機對標籤位姿；狀態以 SE(3) 表示並在流形上以擴展卡爾曼濾波傳遞不確定性。作者也建立可由 BIM 產生施工場景與標籤的 Parrot-Sphinx 與 Gazebo 模擬環境，並在 Vicon 實驗室及模擬中評估位置 RMSE。","On-manifold (SE(3)) EKF that fuses onboard UAV velocity odometry with pixel measurements of AprilTag corners whose poses are known in the BIM frame, giving drift-free global localization for an off-the-shelf Parrot Bebop 2; validated in a Vicon lab and a BIM-enabled photo-realistic simulation.","full_text_reviewed","peer_reviewed_published","supplementary","方法以施工中室內低紋理、反覆變動的環境為動機，並假設標籤位置已登錄在 BIM 中；實際驗證只在 Vicon 實驗室與依 BIM 產生的施工場景模擬中進行，作者把真實工地驗證列為未來工作（Sec. 5、Sec. 8）。",[20,21,22],"simulation","controlled_experiment","independent_reference",[24,25,26,27],"Position RMSE as low as 2 to 5 cm in laboratory and simulation experiments (Abstract; Sec. 8)","Handles tag-blind zones by relying on odometry prediction and recovers after the next tag detection while remaining consistent within 3-sigma bounds (Sec. 6.1)","Tag-corner measurements and the on-manifold formulation gave more accurate and smoother estimates than an Euler-angle EKF using direct tag poses (Sec. 7.2, Fig. 19)","Requires only a camera and IMU on a compact commercial UAV and no mapping session (Sec. 1, 7)",[29,30,31,32,33],"Tag measurements become unreliable beyond a distance threshold (under 4 m for 16.5 cm tags, 856 x 480 images, focal length about 520 px) (Sec. 6.2)","Manual tag placement and replacement is tedious and subject to installation errors that are not modelled (Sec. 7.2, 8)","Tags may be occluded or damaged on site; paper tags may curl (Sec. 2.3, 7.1.1)","Estimates in tag-blind zones depend on odometry quality and drift quickly with IMU-only prediction (Sec. 7.1.5)","Not yet validated on an actual construction site; state estimates were not used in the control loop (Sec. 6, 8)",[35,36],"forward-looking monocular camera of the Parrot Bebop 2 (rectified 856 x 480 at about 30 Hz)","onboard IMU and odometry velocities of the Bebop 2 (about 5 Hz, upsampled to the image rate)",[38,39],"UAV (Parrot Bebop 2, off-the-shelf, no hardware modification)","simulation (Parrot-Sphinx with Gazebo)","On-manifold extended Kalman filter on SE(3) with left perturbation; prediction from onboard translational and rotational velocities, correction from pixel coordinates of the four corners of each detected AprilTag whose pose is known in the BIM frame (Sec. 4)","AprilTag detection and ID decoding (AprilRobotics implementation) gives explicit tag-corner correspondences; no natural-feature matching","discrete time steps at the image rate","not_applicable (camera and IMU only)","none (global tag measurements bound drift)","none","no map is built; tag poses in the BIM reference frame serve as landmarks","AprilTag family, size, IDs and global poses known a priori in the BIM coordinate system; camera intrinsics and camera-vehicle extrinsics from calibration","6-DoF UAV pose and covariance in the BIM frame; no point cloud","runs on a ground station in ROS; hardware and timing not reported",null,"not_applicable",[],{"id":5,"kind":54,"shortName":7,"title":8,"authors":55,"year":9,"venue":60,"venueType":61,"publisher":62,"volumeIssuePages":63,"doi":64,"arxivId":50,"url":65,"firstPublicDate":66,"publicationStatus":16,"metadataStatus":67,"fulltextStatus":15,"era":10,"classicReason":51,"codeUrl":50,"cluster":11,"topics":68,"mdpi":69,"verification":70,"label":6,"fulltextRoute":71,"versionRead":72,"addedByCensus":73},"method",[56,57,58,59],"Navid Kayhani","Wenda Zhao","Brenda McCabe","Angela P. Schoellig","Automation in Construction","journal","Elsevier","135:104112","10.1016\u002Fj.autcon.2021.104112","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092658052100563X","2022-01-10","metadata_verified",[11],false,"confirmed","NTU institutional (Chrome)","version of record, Automation in Construction 135:104112 (ScienceDirect HTML full text)",true,[75,81,86,91,97,101],{"category":76,"model":77,"canonical":77,"role":78,"dataset":50,"specs":79,"locator":80},"platform","Parrot Bebop2","method input","compact off-the-shelf UAV with onboard flight controller, IMU, sonar and vertical camera for height, forward-looking camera; no hardware modification","Sec. 5.1",{"category":82,"model":83,"canonical":83,"role":78,"dataset":50,"specs":84,"locator":85},"camera","Bebop2 forward-looking camera","rectified 856 x 480 images at about 30 Hz; focal length about 520 px","Sec. 5.1.1, Sec. 6.2",{"category":87,"model":88,"canonical":88,"role":78,"dataset":50,"specs":89,"locator":90},"imu","Bebop2 onboard IMU (odometry velocities)","onboard odometry about 5 Hz, boosted to the image rate","Sec. 5.1, 5.1.1",{"category":92,"model":93,"canonical":93,"role":94,"dataset":50,"specs":95,"locator":96},"other","Vicon motion capture system","reference or ground truth","sub-millimetre accuracy, above 200 Hz; used as ground truth and for closed-loop control","Sec. 5.2.1",{"category":92,"model":98,"canonical":98,"role":78,"dataset":50,"specs":99,"locator":100},"AprilTag 36h11 tags (6)","0.165 m x 0.165 m, letter-size paper, global pose in BIM frame known a priori","Table 3",{"category":92,"model":102,"canonical":102,"role":78,"dataset":50,"specs":103,"locator":104},"Parrot-Sphinx simulator with Gazebo","photo-realistic BIM-enabled simulation with simulated IMU, ultrasound, vertical and front cameras","Sec. 5.1.2, Sec. 5.2.2",[],{"totalRows":107,"groupCount":108,"groups":109,"others":177},4,2,[110,146],{"slug":111,"group":112,"sourceId":5,"sourceLabel":6,"table":113,"selfRows":108,"metrics":114,"seqs":120,"entrants":127,"cells":130,"outcomes":138,"locators":139,"hardware":141,"wordings":142,"notes":143},"kayhani2022tagvio-text-sec-6-1","kayhani2022tagvio:Text Sec.6.1","Text Sec.6.1",[115],{"label":116,"unit":117,"statistic":118,"alignment":119},"RMSE of 3D position estimates","m","RMSE","not_reported",[121,125],{"dataset":122,"sequence":123,"environment":124},"BIM-enabled simulation (Parrot-Sphinx + Gazebo)","Planar (exp. 3), including take-off and landing","simulated indoor construction environment",{"dataset":122,"sequence":126,"environment":124},"Planar (exp. 3), take-off and landing excluded",[128],{"name":129,"methodId":5,"linkable":73,"proposed":73,"self":73},"proposed tag-based on-manifold EKF",[131,135],[132,132,132,133,134,132,134,134,132],0,0.0198,-1,[132,132,136,137,134,132,134,134,136],1,0.0177,[],[140],"Sec. 6.1",[],[],[144,145],"Simulation, planar trajectory with a tag-blind zone (experiment 3), BIM-enabled Parrot-Sphinx and Gazebo environment, six 0.165 m 36h11 AprilTags, camera-to-tag distance 1.5 to 4.5 m","Same planar simulation run with take-off and landing disruptions excluded",{"slug":147,"group":148,"sourceId":5,"sourceLabel":6,"table":149,"selfRows":108,"metrics":150,"seqs":153,"entrants":160,"cells":162,"outcomes":167,"locators":170,"hardware":172,"wordings":173,"notes":174},"kayhani2022tagvio-text-sec-6-2","kayhani2022tagvio:Text Sec.6.2","Text Sec.6.2",[151],{"label":152,"unit":117,"statistic":118,"alignment":119},"RMSE in position",[154,158],{"dataset":155,"sequence":156,"environment":157},"laboratory flight arena with Vicon","3D circular (exp. 5), as labelled 'including take-off and landing'","indoor laboratory",{"dataset":155,"sequence":159,"environment":157},"3D circular (exp. 5), as labelled 'excluding take-off and landing'",[161],{"name":129,"methodId":5,"linkable":73,"proposed":73,"self":73},[163,165],[132,132,132,164,132,132,134,134,132],0.0348,[132,132,136,166,136,132,134,134,136],0.2602,[168,169],"other: the text pairs 0.0348 m with 'including' and 0.2602 m with 'excluding' disruptions, which looks reversed; values kept as written","other: label order appears reversed in the text; kept as written",[171],"Sec. 6.2",[],[],[175,176],"Laboratory, 3D circular trajectory of radius 1 m (experiment 5), Vicon ground truth, camera-to-tag distance 2.2 to 4.2 m; value labelled in the text as 'including' take-off and landing disruptions","Same laboratory 3D circular run; value labelled in the text as 'excluding' take-off and landing disruptions",[],1790510662419]