[{"data":1,"prerenderedAt":127},["ShallowReactive",2],{"method-smsckf2018":3},{"method":4,"reference":57,"equipment":82,"figures":126,"results":98},{"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":26,"sensors":32,"platform":35,"estimator":38,"association":39,"timeModel":40,"deskew":41,"loopClosure":42,"globalOptimization":42,"mapRepresentation":43,"prior":44,"outputGeometry":45,"compute":46,"codeUrl":47,"codeLicense":48,"relatedVersions":49},"smsckf2018","Sun et al., 2018","S-MSCKF (msckf_vio)","Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight",2018,"recent","C08","odometry","S-MSCKF 把多狀態約束卡爾曼濾波（MSCKF）擴充到立體相機，目標是在微型飛行器的筆電等級電腦上以低運算量穩健估計位姿。前端以 FAST 角點與 KLT 光流同時做時間追蹤與左右影像匹配，並以 2 點 RANSAC 與環狀匹配剔除離群；後端以 4 維立體量測更新，不需影像校正，並採可觀測性約束 EKF（OC-EKF）維持一致性。為平均運算負載，每隔一次更新移除兩個相機狀態。","S-MSCKF is an open-source stereo MSCKF VIO with a KLT-based front end for temporal and stereo matching, an observability-constrained EKF, and a steady two-state removal scheme, delivering accuracy similar to OKVIS and VINS-Mono at lower CPU load for fast MAV flight.","full_text_reviewed","peer_reviewed_published","background","論文未在營建工地測試；除 EuRoC 外，飛行實驗在機場跑道、樹林與倉庫進行，並把 S-MSCKF 位姿用來拼接雷射點雲，700 m 往返終點漂移約 3 m。這顯示低運算量立體視覺 VIO 可作為無人機在室內外轉換場域（如大型倉儲或施工中建物）的位姿來源，但未報告點雲幾何精度（推論）。",[20,21],"public_benchmark","independent_reference",[23,24,25],"Accuracy similar to OKVIS and VINS-Mono on EuRoC (except V2_03, where S-MSCKF fails), while ROVIO has larger errors on the machine-hall sequences","filter-based methods have the lowest CPU load (Sec. IV-A","Fig. 2, plotted)",[27,28,29,30,31],"Diverges on EuRoC V2_03 because brightness inconsistency between the stereo images breaks KLT stereo matching (Sec. IV-A)","Global position and yaw are unobservable, so uncertainty grows and the estimate may jump or diverge once the prior uncertainty is large (Sec. V)","Frequent removal of camera states discards some valid observations (Sec. III-D)","KLT stereo matching is reliable for corners deeper than about 1 m with a 20 cm baseline (Sec. III-E)","Front-end cost rises with higher image rate and resolution and short feature lifetimes during aggressive flight (Sec. IV-B)",[33,34],"stereo camera","IMU",[36,37],"UAV (3 kg FALCON quadrotor; fast flights up to 17.5 m\u002Fs over a runway; autonomous flight through woods and a warehouse)","UAV (EuRoC MAV)","stereo multi-state-constraint EKF: IMU state with camera-IMU extrinsics plus a window of left-camera poses; RK4 propagation; 4-D stereo measurement that does not require rectification; nullspace projection of feature errors; observability-constrained EKF (OC-EKF) for consistency; two camera states removed every other update, chosen by a two-way keyframe rule (Sec. III)","FAST corners tracked temporally by KLT optical flow and matched across the stereo pair also by KLT; 2-point RANSAC for temporal outliers and circular matching between consecutive stereo pairs (Sec. III-E)","discrete; IMU at 200 Hz, cameras at 20 Hz (EuRoC) or 40 Hz (fast flight) synchronised by the IMU trigger (Sec. IV)","not_applicable","none","none in the filter; features are marginalised by nullspace projection (MSCKF)","offline camera-IMU calibration supplied in the experiments; left-right stereo extrinsics assumed known (Secs. III, IV)","IMU pose and velocity; in the field test the poses were used to register a laser point cloud (laser used for mapping only) (Sec. IV-C; Fig. 6)","filter about 10% of one core at 20 Hz, with about 80% of computation in the front end (EuRoC); CPU load measured on NUC6i7KYK (quad-core i7-6770HQ); runs onboard an Intel NUC5i7RYH on the FALCON robot (Sec. IV-A; Fig. 1)","https:\u002F\u002Fgithub.com\u002FKumarRobotics\u002Fmsckf_vio","Penn Software MSCKF_VIO licence (University of Pennsylvania): use, copy and modify for non-profit research purposes only (LICENSE.txt)",[50,54],{"relation":51,"title":52,"doi_or_url":53},"preprint","Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight (arXiv v3, RA-L accepted version)","https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.00036",{"relation":55,"title":56,"doi_or_url":47},"code_release","KumarRobotics\u002Fmsckf_vio (also hosts the fast-flight dataset on its wiki)",{"id":5,"kind":58,"shortName":7,"title":8,"authors":59,"year":9,"venue":68,"venueType":69,"publisher":70,"volumeIssuePages":71,"doi":72,"arxivId":73,"url":53,"firstPublicDate":74,"publicationStatus":16,"metadataStatus":75,"fulltextStatus":15,"era":10,"classicReason":41,"codeUrl":47,"cluster":11,"topics":76,"mdpi":77,"verification":78,"label":6,"fulltextRoute":79,"versionRead":80,"addedByCensus":81},"method",[60,61,62,63,64,65,66,67],"Ke Sun","Kartik Mohta","Bernd Pfrommer","Michael Watterson","Sikang Liu","Yash Mulgaonkar","Camillo J. Taylor","Vijay Kumar","IEEE Robotics and Automation Letters","journal","IEEE","3(2):965-972","10.1109\u002Flra.2018.2793349","1712.00036","2017-11-30","metadata_verified",[11],false,"corrected","arXiv","arXiv v3 (2018-01-10), marked 'RA-L preprint version, accepted December 2017'; IEEE version of record not read",true,[83,90,95,101,106,111,118,123],{"category":84,"model":85,"canonical":85,"role":86,"dataset":87,"specs":88,"locator":89},"stereo_camera","PointGrey CM3-U3-13Y3M-CS (two, forward-looking)","method input","fast flight dataset (KumarRobotics msckf_vio wiki)","40 Hz, 960 x 800, synchronised by the IMU trigger, external auto-exposure controller applying identical shutter and gain; Sec. III-E mentions a 20 cm baseline stereo configuration when discussing KLT stereo matching, without naming the rig","Secs. III-E, IV-B",{"category":91,"model":92,"canonical":92,"role":86,"dataset":87,"specs":93,"locator":94},"imu","VectorNav VN-100 Rugged","200 Hz","Sec. IV-B",{"category":96,"model":97,"canonical":97,"role":86,"dataset":98,"specs":99,"locator":100},"platform","FALCON quadrotor",null,"3 kg; synchronised stereo cameras and IMU, a laser scanner and a downward-facing lidar; only stereo and IMU used for estimation","Fig. 1",{"category":102,"model":103,"canonical":103,"role":104,"dataset":98,"specs":105,"locator":100},"compute","Intel NUC5i7RYH","compute for runtime","onboard computer of the FALCON robot",{"category":102,"model":107,"canonical":107,"role":104,"dataset":108,"specs":109,"locator":110},"NUC6i7KYK (quad-core i7-6770HQ)","EuRoC MAV","used to measure CPU load on EuRoC","Sec. IV-A",{"category":112,"model":113,"canonical":113,"role":114,"dataset":115,"specs":116,"locator":117},"lidar","laser scanner on FALCON (model not reported)","dataset sensor","autonomous flight experiment","used for mapping only; global laser point cloud registered with S-MSCKF poses","Fig. 1; Sec. IV-C; Fig. 6",{"category":119,"model":120,"canonical":120,"role":121,"dataset":87,"specs":122,"locator":94},"gnss","GPS (model not reported)","reference or ground truth","x-y position reference for fast-flight RMSE",{"category":84,"model":124,"canonical":124,"role":114,"dataset":108,"specs":125,"locator":110},"VI sensor (EuRoC)","synchronised 20 Hz stereo images and 200 Hz IMU",[],1790510656162]