Skip to content

Track Advancement of SLAM 跟踪SLAM前沿动态【2020 version】

Notifications You must be signed in to change notification settings

lichenchen1205/Recent_SLAM_Research

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 

Repository files navigation

Recent_SLAM_Research_2020

【回馈社区】跟踪SLAM前沿动态2019, 2018版 .去年大概收录了500篇关于SLAM的论文,因为本人在企业重点研究的是VSLAM以及多传感器融合,所以并没有把全部论文精读,难免有漏的或者差的。今年重点是求精以及做好分类,继续做好本圈儿的服务工作。 欢迎在Issues里发布招聘信息。

------------ ICRA 2020

------------ ICRA 2020 终止线 ----------

------------ CVPR 2020

------------ CVPR 2020 终止线 ----------

------------ ECCV 2020

------------ ECCV 2020 终止线 ----------

------------ IROS 2020

------------ IROS 2020 终止线 ----------

------------ ICCV 2020

------------ ICCV 2020 终止线 ----------

SLAM

1. [Semantic SLAM] 2020-01-13-Visual Semantic SLAM with Landmarks for Large-Scale Outdoor Environment Only label the point clouds with semantic segmentation info, no improvement in accuarcy. code

4. [Deep SLAM] 2020-01-13-AD-VO: SCALE-RESILIENT VISUAL ODOMETRY USING ATTENTIVE DISPARITY MAP Learned based frame to frame VO with the input as disparity map.

5. [Lidar Deep SLAM] 2020-01-13-CAE-LO: LiDAR Odometry Leveraging Fully Unsupervised Convolutional Auto-Encoder for Interest Point Detection and Feature Description Auto-Encoder based LiDAR Odometry (CAE-LO) that detects interest points from spherical ring data using 2D CAE and extracts features from multi-resolution voxel model using 3D CAE. code

6. [VSLAM] 2020-01-13-Good Feature Matching: Towards Accurate, Robust VO/VSLAM with Low Latency Introduction of an efficient good feature selection algorithm using the Max-logDet metric, which is an order of magnitude faster than state-of-the-art feature selection approaches. code

7. [VSLAM] 2020-01-13-Direct Sparse Visual-Inertial Odometry with Stereo Cameras Quantitative evaluation demonstrates that the proposed Stereo VI-DSO is superior to Stereo DSO both in terms of tracking accuracy and robustness. But the result is worse than VINS.

9. [VSLAM] 2020-01-14-A Stereo Visual-Inertial SLAM Approach for Indoor Mobile Robots in Unknown Environments Without Occlusions Use one-circle feature-matching method, which refers to a sequence of the circle matching for the time after space (STCM), and an STCM-based visual-inertial simultaneous localization and mapping (STCM-SLAM) technique.

13. [Deep SLAM] 2020-01-22-Learning Topometric Semantic Maps from Occupancy Grids 2D laser semantic map.

14. [VSLAM] 2020-01-22-Temporal Delay Estimation of Sparse Direct Visual Inertial Odometry for Mobile Robots Calibrate the time offset between IMU and Camera.

15. [IMU] 2020-02-06-A Lightweight and Accurate Localization Algorithm Using Multiple Inertial Measurement Units The overall performance of SLAM can be further improved by using multiple IMUs.

16. [Lidar SLAM] 2020-02-10-Localization of Map Changes by Exploiting SLAM Residuals identify changes in maps constructed by SLAM.

17. [VSLAM] 2020-02-10-Bidirectional Trajectory Computation for Odometer-Aided Visual-Inertial SLAM not only solves the problem of the unobservability of accelerometer bias and extrinsic parameters before the first turning, but also results in more accurate trajectories in comparison with the state-of-the-art approaches.

18. [EKF] 2020-02-10-A Code for Unscented Kalman Filtering on Manifolds (UKF-M) a novel methodology for Unscented Kalman Filtering (UKF) on manifolds that extends our previous work about UKF on Lie groups.

19. [New sensor] 2020-02-10-Corners positioning for binocular ultra-wide angle long-wave infrared camera calibration calibrating binocular ultra-wide angle long-wave infrared camera.

21. [Semantic] 2020-02-12-Edge Assisted Mobile Semantic Visual SLAM edgeSLAM leverages the state-of-the-art semantic segmentation algorithm to enhance localization and mapping accuracy, and speeds up the computation-intensive SLAM and semantic segmentation algorithms by computation offloading.

22. [lidar SLAM] 2020-02-12-Online LiDAR-SLAM for Legged Robots with Robust Registration and Deep-Learned Loop ClosureIn this paper, we present a factor-graph LiDARSLAM system which incorporates a state-of-the-art deeply learned feature-based loop closure detector to enable a legged robot to localize and map in industrial environments.

23. [Semantic] 2020-02-14-Tightly Coupled Semantic RGB-D Inertial Odometry for Accurate Long-Term Localization and Mapping utilize semantically enhanced feature matching and visual inertial bundle adjustment to improve the robustness of odometry especially in feature-sparse environments.

24. [VIO] 2020-02-14-Visual-Inertial Ego-Motion Estimation using Rolling-Shutter Camera in autonomous driving interpolate the IMU pose between consecutive poses and set up a novel feature measurement error model to cover the time delay issues.

25. [VIO] 2020-02-14-EIP-VIO: Edge-Induced Points Based Monocular Visual-Inertial Odometry propose an improved and practical monocular visual-inertial odometry method based on selective edge points.

26. [Event camera] 2020-02-14-Sepia, Tarsier, and Chameleon: A Modular C++ Framework for Event-Based Computer Vision A framework to process Event camera. code

27. [Multimodal localization] 2020-02-14-Multimodal localization: Stereo over LiDAR map Visual localization in lidar map.

28. [2D SLAM] 2020-02-15-x A Triangle Feature Based Map-to-map Matching and Loop Closure for 2D Graph SLAM We propose a geometric environment descriptor called a Triangle Feature (TF). It exploits the Euclidean distance constraint any three feature points in a submap can form.

30. [Multirobots] 2020-02-15-Statistical Outlier Identification in Multi-robot Visual SLAM using Expectation Maximization This paper presents a probabilistic approach for detecting incorrect orientation measurements prior to pose graph optimization by checking the geometric consistency of rotation measurements.

33. [VSLAM] 2020-02-16-DeepFactors: Real-Time Probabilistic Dense Monocular SLAM use of a learned compact depth map representation and reformulating three different types of errors: photometric, reprojection and geometric, which we make use of within standard factor graph software. code

39. [VSLAM] 2020-03-02-Dynamic SLAM: The Need For Speedfeature-based, model-free, object-aware dynamic SLAM algorithm that exploits semantic segmentation to allow estimation of motion of rigid objects in a scene without the need to estimate the object poses or have any prior knowledge of their 3D models.

40. [VSLAM] 2020-03-04-Monocular Direct Sparse Localization in a Prior 3D Surfel Map tracking the pose of a monocular camera in a prior surfel map.

42. [Math] 2020-03-04-Least Squares Optimization: from Theory to Practice a unified methodology to design and develop efficient Least-Squares Optimization algorithms, focusing on the structures and patterns of each specific domain.code

45. [Deep SLAM] 2020-03-05-Self-Supervised Deep Pose Corrections for Robust Visual Odometry uses data-driven learning to regress pose corrections that account for systematic errors due to violations of modelling assumptions. code

58. [VSLAM] 2020-03-16-Voxel Map for Visual SLAM

3D Reconstruction

3. [Deep Reconstruction] 2020-04-03-Atlas: End-to-End 3D Scene Reconstruction from Posed Images from magicleap

Path Planning

3. [End-to-end navi] 2020-02-20-BADGR: An Autonomous Self-Supervised Learning-Based Navigation System an end-to-end learning-based mobile robot navigation system. code

Others.

SLAM 能力图

About

Track Advancement of SLAM 跟踪SLAM前沿动态【2020 version】

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published