1. TANDEM:Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo慕尼黑工业大学 Daniel Cremers 团队实时单目跟踪稠密建图纯视觉SLAM采用Realsense D455深度传感器IMU但只用RGB。项目地址https://vision.in.tum.de/research/vslam/tandem论文地址https://arxiv.org/pdf/2111.07418.pdf源码地址https://github.com/tum-vision/tandem2. MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera慕尼黑工业大学Daniel Cremers团队半监督单目稠密重建纯视觉SLAM项目地址https://vision.in.tum.de/research/monorec论文地址https://arxiv.org/pdf/2011.11814.pdf源码地址https://github.com/Brummi/MonoRec3. Range-MCL: Range Image-based LiDAR Localization for Autonomous Vehicles波恩大学 Cyrill Stachniss 团队3D LiDAR户外激光SLAM采用Passion表面重建和蒙特卡洛定位框架项目地址https://www.ipb.uni-bonn.de/research/https://www.ipb.uni-bonn.de/data-software论文地址https://arxiv.org/pdf/2105.12121.pdf源码地址https://github.com/PRBonn/range-mcl4. MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least SquareETH苏黎世联邦理工学院、EPFL洛桑联邦理工学院、禾赛科技激光SLAM项目地址https://baug.ethz.ch/en/https://www.hesaitech.com/zh/https://sti.epfl.ch论文地址https://arxiv.org/pdf/2102.03771.pdf源码地址https://github.com/YuePanEdward/MULLS5. LiLi-OM: Towards High-Performance Solid-State-LiDAR-Inertial Odometry and MappingKIT德国卡尔斯鲁厄理工学院实时紧耦合激光雷达惯性里程计SLAM特征提取参考固态激光雷达 Livox Horizon 与机械激光雷达 Velodyne A-LOAM (HKUST-Aerial-Robotics)可先参考开源VINS-Fusion (https://github.com/HKUST-Aerial-Robotics/VINS-Fusion) 和 LIO-mapping (https://github.com/hyye/lio-mapping)。项目地址https://isas.iar.kit.edu论文地址https://arxiv.org/pdf/2010.13150v3源码地址https://github.com/KIT-ISAS/lili-om6. FAST-LIO2: Fast Direct LiDAR-inertial OdometryFAST-LIO: A Fast, Robust LiDAR-inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter香港大学张富团队在 FAST-LIO高效鲁棒性LiDAR、惯性里程库融合LiDAR特征点和IIMU数据紧耦合快速EKF迭代基础上采用 ikd-Tree (https://github.com/hku-mars/ikd-Tree) 增量建图原始LiDAR点直接计算里程支持外部IMU并支持ARM平台。项目地址https://mars.hku.hk论文地址https://arxiv.org/pdf/2107.06829v1.pdf源码地址https://github.com/hku-mars/FAST_LIO相关工作ikd-Tree:A state-of-art dynamic KD-Tree for 3D kNN search. https://github.com/hku-mars/ikd-TreeIKFOM:A Toolbox for fast and high-precision on-manifold Kalman filter. https://github.com/hku-mars/IKFoMUAV Avoiding Dynamic Obstacles:One of the implementation of FAST-LIO in robots planning.https://github.com/hku-mars/dyn_small_obs_avoidanceR2LIVE:A high-precision LiDAR-inertial-Vision fusion work using FAST-LIO as LiDAR-inertial front-end.https://github.com/hku-mars/r2liveUGV Demo:Model Predictive Control for Trajectory Tracking on Differentiable Manifolds.https://www.youtube.com/watch?vwikgrQbE6CsFAST-LIO-SLAM:The integration of FAST-LIO with Scan-Context loop closure module.https://github.com/gisbi-kim/FAST_LIO_SLAMFAST-LIO-LOCALIZATION:The integration of FAST-LIO with Re-localization function module.https://github.com/HViktorTsoi/FAST_LIO_LOCALIZATION7. R3LIVE: A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package香港大学张富团队在R2LIVEFAST-LIO 与 VIO基础上LiDAR、惯导、视觉多传感器融合SLAM项目地址https://mars.hku.hk/论文地址https://arxiv.org/pdf/2109.07982.pdf源码地址https://github.com/hku-mars/r3live相关工作数据集https://github.com/ziv-lin/r3live_datasetR2LIVE:A robust, real-time tightly-coupled multi-sensor fusion package.https://github.com/hku-mars/r2liveFAST-LIO:A computationally efficient and robust LiDAR-inertial odometry package.https://github.com/hku-mars/FAST_LIOikd-Tree:A state-of-art dynamic KD-Tree for 3D kNN search.https://github.com/hku-mars/ikd-Tree LOAM-Livox: A robust LiDAR Odometry and Mapping (LOAM) package for Livox-LiDAR.https://github.com/hku-mars/loam_livoxopenMVS:A library for computer-vision scientists and especially targeted to the Multi-View Stereo reconstruction community.https://github.com/cdcseacave/openMVSVCGlib:An open source, portable, header-only Visualization and Computer Graphics Library.https://github.com/cnr-isti-vclab/vcglibCGAL:A C Computational Geometry Algorithms Library.https://www.cgal.org/,https://github.com/CGAL/cgal8. GVINS: tightly coupled GNSS-visual-inertial fusion for smooth and consistent state estimation香港科技大学沈邵劼团队之前开源 VINS-Mono (https://github.com/HKUST-Aerial-Robotics/VINS-Mono)VINS-Fusion (https://github.com/HKUST-Aerial-Robotics/VINS-Fusion)GVINS 是基于GNSS、视觉、惯导紧耦合多传感器融合平滑一致状态估计。项目地址https://uav.hkust.edu.hk论文地址https://arxiv.org/pdf/2103.07899.pdf源码地址https://github.com/HKUST-Aerial-Robotics/GVINS相关资源http://www.rtklib.com/ 系统框架及VIO部分采用VINS-Mono相机建模采用camodocal (https://github.com/hengli/camodocal)ceres (http://ceres-solver.org/) 优化。RTKLIB: An Open Source Program Package for GNSS PositioningAn Open Source Program Package for GNSS Positioning9. LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and MappingMIT麻省理工学院TixiaoShan之前开源LIO-SAMhttps://github.com/TixiaoShan/LIO-SAM激光、视觉、惯性紧耦合多传感器融合SLAM里程计建图系统层联合LIO-SAM与Vins-Mono优势依赖与ROS、gtsam、Ceres库。项目地址https://git.io/lvi-samhttps://dusp.mit.edu/https://senseable.mit.edu/https://www.ams-institute.org/论文地址https://arxiv.org/pdf/2104.10831.pdf源码地址https://github.com/TixiaoShan/LVI-SAM10. DSP-SLAM: Object Oriented SLAM with Deep Shape Priors伦敦大学基于ORB-SLAM2面向对象语义SLAM项目地址https://jingwenwang95.github.io/dsp-slam论文地址https://arxiv.org/pdf/2108.09481v2.pdf源码地址https://github.com/JingwenWang95/DSP-SLAM11. UV-SLAM: Unconstrained Line-based SLAM Using Vanishing Points for Structural MappingKAIST韩国科学技术院采用消隐点实现无约束线特征结构化建图克服传统线重投影测量模型中仅利用 Plücker 坐标线法向量。论文地址https://arxiv.org/pdf/2112.13515.pdf源码地址https://github.com/url-kaist/UV-SLAM源码即将上传相关研究Avoiding Degeneracy for Monocular Visual SLAM with Point and Line FeaturesALVIO:Adaptive Line and Point Feature-Based Visual Inertial Odometry for Robust Localization in Indoor Environments源码未上传 https://github.com/ankh88324/ALVIO12. Autonomous Navigation System from Simultaneous Localization and Mapping克拉克森大学基于slam室内导航软件架构应用于智能轮椅论文地址https://arxiv.org/pdf/2112.07723.pdf源码地址https://github.com/michealcarac/VSLAM-Mapping13. MegBA: A High-Performance and Distributed Library for Large-Scale Bundle Adjustment爱丁堡大学、旷视科技大规模BA算法GPU分布式计算论文地址https://arxiv.org/pdf/2112.01349v2.pdf源码地址https://github.com/MegviiRobot/MegBA14. Fast Direct Stereo Visual SLAM明尼苏达大学快速准确立体视觉SLAM不依赖于特征探测与匹配。作者从单目DSO扩展到双目系统通过3D点最小光度误差优化双目配置尺度。论文地址https://arxiv.org/pdf/2112.01890.pdf源码地址https://github.com/IRVLab/direct_stereo_slam相关工作Direct Sparse OdometryA Photometrically Calibrated Benchmark For Monocular Visual Odometryhttps://github.com/JakobEngel/dso15. MSC-VO: Exploiting Manhattan and Structural Constraints for Visual Odometry巴利阿里群岛大学基于RGB-D视觉里程计融合点与线特征结构化约束。论文地址https://arxiv.org/pdf/2111.03408.pdf源码地址https://github.com/joanpepcompany/MSC-VO