ICRA 2021| SLAM方向论文汇总

作者丨wanghy@知乎

来源丨https://zhuanlan.zhihu.com/p/371744210

编辑丨3D视觉工坊

最近扫读了下ICRA 2021 SLAM方向相关的文章，由于总结比较广泛，大约有200多篇，本文对论文进行了分类，并给出了目前可以检索到的论文下载地址和开源代码地址，希望对一起做SLAM研究的同行们提供一些有益的参考。

论文、代码地址：在公众号「3D视觉工坊」，后台回复「ICRA  SLAM」，即可直接下载。

后续将在github上持续更新，链接

MichaelWang1028/ICRA2021-SLAM-paper-listgithub.com

语义定位建图：

1. Visual Semantic Localization Based on HD Map for Autonomous Vehicles in Urban Scenarios

2. RoadMap: A Light-Weight Semantic Map for Visual Localization towards Autonomous Driving

3. Road Mapping and Localization Using Sparse Semantic Visual Features https://ieeexplore.ieee.org/document/9387091

4. Kimera-Multi: A System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping https://arxiv.org/abs/2011.04087

5. Semantic SLAM with Autonomous Object-Level Data Association https://arxiv.org/abs/2011.10625

6. Hybrid Bird's-Eye Edge Based Semantic Visual SLAM for Automated Valet Parking (AVP) https://www.zhenzhenxiang.xyz/publication/icra2021/

7. Compositional and Scalable Object SLAM https://arxiv.org/abs/2011.02658

8. Robust Semantic Map Matching Algorithm Based on Probabilistic Registration Model

9. Semantically Guided Multi-View Stereo for Dense 3D Road Mapping

10. Robust Improvement in 3D Object Landmark Inference for Semantic Mapping

11. Any Way You Look at It: Semantic Crossview Localization and Mapping with LiDAR https://github.com/iandouglas96/cross_view_slam / https://ieeexplore.ieee.org/document/9361130

12. PSF-LO: Parameterized Semantic Features Based Lidar Odometry https://arxiv.org/abs/2010.13355

13. Point Set Registration with Semantic Region Association Using Cascaded Expectation Maximization

视觉SLAM

Visual SLAM

1. Asynchronous Multi-View SLAM https://arxiv.org/abs/2101.06562

2. B-Splines for Purely Vision-Based Localization and Mapping on Non-Holonomic Ground Vehicles

3. UPSLAM: Union of Panoramas SLAM https://arxiv.org/abs/2101.00585

4. Multi-Parameter Optimization for a Robust RGB-D SLAM System

5. SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes https://arxiv.org/abs/2010.09409

6. MOLTR: Multiple Object Localisation, Tracking and Reconstruction from Monocular RGB Videos https://arxiv.org/abs/2012.05360

7. ManhattanSLAM: Robust Planar Tracking and Mapping Leveraging Mixture of Manhattan Frames https://arxiv.org/abs/2103.15068

8. Markov Parallel Tracking and Mapping for Probabilistic SLAM

9. Avoiding Degeneracy for Monocular Visual SLAM with Point and Line Features https://arxiv.org/abs/2103.01501

10. Learning a State Representation and Navigation in Cluttered and Dynamic Environments https://arxiv.org/pdf/2103.04351

11. TT-SLAM: Dense Monocular SLAM for Planar Environments https://hal.inria.fr/hal-03169199/

12. OV2SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications https://arxiv.org/abs/2102.04060

13. DOT: Dynamic Object Tracking for Visual SLAM https://arxiv.org/abs/2010.00052

14. DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences (I) https://arxiv.org/abs/1908.08918

15. RGB-D SLAM with Structural Regularities https://arxiv.org/abs/2010.07997

16. RigidFusion: Robot Localisation and Mapping in Environments with Large Dynamic Rigid Objects

17. CAROM - Vehicle Localization and Traffic Scene Reconstruction from Monocular Cameras on Road Infrastructures https://arxiv.org/abs/2104.00893

18. VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enough https://arxiv.org/abs/2104.06800

19. Kimera-Multi: A System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping https://arxiv.org/abs/2011.04087

VO:

1. Accurate and Robust Scale Recovery for Monocular Visual Odometry Based on Plane Geometry https://arxiv.org/abs/2101.05995

2. Accurate and Robust Stereo Direct Visual Odometry for Agricultural Environment

3. Deep Online Correction for Monocular Visual Odometry https://arxiv.org/abs/2103.10029

4. A Heteroscedastic Likelihood Model for Two-Frame Optical Flow https://arxiv.org/abs/2010.06871

5. Learning Optical Flow with R-CNN for Visual Odometry

6. Optimizing RGB-D Fusion for Accurate 6DoF Pose Estimation https://ieeexplore.ieee.org/abstract/document/9361135/

7. Tight Integration of Feature-Based Relocalization in Monocular Direct Visual Odometry https://arxiv.org/abs/2102.01191

8. Continuous Scale-Space Direct Image Alignment for Visual Odometry from RGB-D Images https://hal.archives-ouvertes.fr/hal-03130945/document

9. A Front-End for Dense Monocular SLAM Using a Learned Outlier Mask Prior

Visual Mapping:

1. Structure Reconstruction Using Ray-Point-Ray Features: Representation and Camera Pose Estimation

2. Hough2Map – Iterative Event-Based Hough Transform for High-Speed Railway Mapping https://arxiv.org/pdf/2102.08145.pdf / https://github.com/ethz-asl/Hough2Map

3. Lightweight Semantic Mesh Mapping for Autonomous Vehicles

4. Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior https://arxiv.org/abs/2102.05212

5. Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D Learning https://arxiv.org/abs/2101.01844

6. Direct Sparse Mapping (I)https://arxiv.org/abs/1904.06577 / https://github.com/jzubizarreta/dsm

7. HyperMap: Compressed 3D Map for Monocular Camera Registration https://www.cs.cmu.edu/~kaess/pub/Chang21icra.pdf

8. Probabilistic Multi-View Fusion of Active Stereo Depth Maps for Robotic Bin-Picking https://arxiv.org/abs/2103.10968

9. Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments https://arxiv.org/abs/2103.16095

VIO：

1. UVIP: Robust UWB Aided Visual-Inertial Positioning System for Complex Indoor Environments

2. Range-Focused Fusion of Camera-IMU-UWB for Accurate and Drift-Reduced Localization https://ieeexplore.ieee.org/abstract/document/9350155

3. CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth https://arxiv.org/abs/2012.10133

4. Direct Sparse Stereo Visual-Inertial Global Odometry

5. Collaborative Visual Inertial SLAM for Multiple Smart Phones

6. VID-Fusion: Robust Visual-Inertial-Dynamics Odometry for Accurate External Force Estimation https://arxiv.org/abs/2011.03993

7. Run Your Visual-Inertial Odometry on NVIDIA Jetson: Benchmark Tests on a Micro Aerial Vehicle https://arxiv.org/abs/2103.01655

8. Bidirectional Trajectory Computation for Odometer-Aided Visual-Inertial SLAM https://arxiv.org/abs/2002.00195

9. Optimization-Based Visual-Inertial SLAM Tightly Coupled with Raw GNSS Measurements https://arxiv.org/abs/2010.11675

10. An Equivariant Filter for Visual Inertial Odometry https://arxiv.org/abs/2104.03532

11. Revisiting Visual-Inertial Structure-From-Motion for Odometry and SLAM Initialization https://arxiv.org/abs/2006.06017

12. Cooperative Visual-Inertial Odometry https://hal.inria.fr/hal-02427991/document #####Tracking:

13. Tracking 6-DoF Object Motion from Events and Frames https://arxiv.org/abs/2103.15568

14. Visual Tracking of Deforming Objects Using Physics-Based Models https://hal.inria.fr/hal-03179253/document

15. Deep 6-DoF Tracking of Unknown Objects for Reactive Grasping https://arxiv.org/abs/2103.05401

16. TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction

深度：

1. Robust Monocular Visual-Inertial Depth Completion for Embedded Systems http://udel.edu/~pgeneva/downloads/papers/c19.pdf

2. Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation https://arxiv.org/abs/2103.02451

3. SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments https://arxiv.org/abs/2011.04977

4. Stereo-Augmented Depth Completion from a Single RGB-LiDAR Image

5. PENet: Towards Precise and Efficient Image Guided Depth Completion https://arxiv.org/abs/2103.00783 / https://github.com/JUGGHM/PENet_ICRA2021

6. Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation https://arxiv.org/abs/2103.12964

7. PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation https://arxiv.org/abs/2006.02068

8. Bidirectional Attention Network for Monocular Depth Estimation https://arxiv.org/abs/2009.00743

9. Self-Guided Instance-Aware Network for Depth Completion and Enhancement

10. Deep Multi-View Depth Estimation with Predicted Uncertainty https://arxiv.org/abs/2011.09594

11. MultiViewStereoNet: Fast Multi-View Stereo Depth Estimation Using Incremental Viewpoint-Compensated Feature Extraction

12. Linear Inverse Problem for Depth Completion with RGB Image and Sparse LIDAR Fusion

13. Toward Robust and Efficient Online Adaptation for Deep Stereo Depth Estimation

视觉场景识别：

1. Intelligent Reference Curation for Visual Place Recognition Via Bayesian Selective Fusion https://arxiv.org/abs/2010.09228

2. Appearance-Based Loop Closure Detection Via Bidirectional Manifold Representation Consensus

3. SoftMP: Attentive Feature Pooling for Joint Local Feature Detection and Description for Place Recognition in Changing Environments

4. Simultaneous Multi-Level Descriptor Learning and Semantic Segmentation for Domain-Specific Relocalization

5. Resolving Place Recognition Inconsistencies Using Intra-Set Similarities https://ieeexplore.ieee.org/abstract/document/9359453/

6. Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems https://arxiv.org/abs/2104.10067

7. Retrieval and Localization with Observation Constraints

8. A Flexible and Efficient Loop Closure Detection Based on Motion Knowledge

9. Semantic Reinforced Attention Learning for Visual Place Recognition

10. STA-VPR: Spatio-Temporal Alignment for Visual Place Recognition https://arxiv.org/abs/2103.13580

11. Visual Place Recognition Via Local Affine Preserving Matching

激光场景识别：

1. DiSCO: Differentiable Scan Context with Orientation https://arxiv.org/abs/2010.10949

2. Robust Place Recognition Using an Imaging Lidar https://arxiv.org/abs/2103.02111

3. Locus: LiDAR-Based Place Recognition Using Spatiotemporal Higher-Order Pooling https://arxiv.org/abs/2011.14497

4. Resolving Place Recognition Inconsistencies Using Intra-Set Similarities https://ieeexplore.ieee.org/document/9359453/

5. Beyond ANN: Exploiting Structural Knowledge for Efficient Place Recognition https://arxiv.org/abs/2103.08366

6. Place Recognition in Forests with Urquhart Tessellations http://arxiv.org/pdf/2010.03026

多传感器融合定位：

1. LVI-SAM: Tightly-Coupled Lidar-Visual-Inertial Odometry Via Smoothing and Mapping https://arxiv.org/abs/2104.10831 / https://github.com/TixiaoShan/LVI-SAM

2. MSTSL: Multi-Sensor Based Two-Step Localization in Geometrically Symmetric Environments

3. LatentSLAM: Unsupervised Multi-Sensor Representation Learning for Localization and Mapping https://arxiv.org/abs/2105.03265

4. Visual-Laser-Inertial SLAM Using a Compact 3D Scanner for Confined Space

5. Efficient Multi-Sensor Aided Inertial Navigation with Online Calibration

6. Range-Visual-Inertial Odometry: Scale Observability without Excitation https://arxiv.org/pdf/2103.15215

7. Airflow-Inertial Odometry for Resilient State Estimation on Multirotors

8. Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments

9. Interval-Based Visual-LiDAR Sensor Fusion https://www.researchgate.net/publication/349141103_Interval-Based_Visual-LiDAR_Sensor_Fusion

10. CamVox: A Low-Cost and Accurate Lidar-Assisted Visual SLAM System https://arxiv.org/abs/2011.11357

11. Multi-Session Underwater Pose-Graph SLAM Using Inter-Session Opti-Acoustic Two-View Factor https://irap.kaist.ac.kr/publications/hsjang-2021-icra.pdf

12. Simple but Effective Redundant Odometry for Autonomous Vehicles https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/reinke2021icra.pdf

13. Markov Localisation Using Heatmap Regression and Deep Convolutional Odometry https://cvssp.org/Personal/OscarMendez/papers/pdf/MendezICRA2021.pdf

14. Unified Multi-Modal Landmark Tracking for Tightly Coupled Lidar-Visual-Inertial Odometry https://arxiv.org/abs/2011.06838

15. Vanishing Point Aided LiDAR-Visual-Inertial Estimator https://people.inf.ethz.ch/pomarc/pubs/CamposecoICRA15.pdf

16. Any Way You Look at It: Semantic Crossview Localization and Mapping with LiDAR https://github.com/iandouglas96/cross_view_slam / https://ieeexplore.ieee.org/document/9361130

多传感器融合建图：

1. Lidar-Monocular Surface Reconstruction Using Line Segments https://arxiv.org/abs/2104.02761

2. Automatic Mapping of Tailored Landmark Representations for Automated Driving and Map Learning

激光SLAM

lidar SLAM

1. SA-LOAM: Semantic-Aided LiDAR SLAM with Loop Closure

2. Greedy-Based Feature Selection for Efficient LiDAR SLAM https://arxiv.org/abs/2103.13090

3. Inertial Aided 3D LiDAR SLAM with Hybrid Geometric Primitives in Large-Scale Environments

4. π-LSAM: LiDAR Smoothing and Mapping with Planes

5. R-LOAM: Improving LiDAR Odometry and Mapping with Point-To-Mesh Features of a Known 3D Reference Object https://ieeexplore.ieee.org/document/9357902

6. LoLa-SLAM: Low-Latency LiDAR SLAM Using Continuous Scan Slicing https://ieeexplore.ieee.org/document/9359468

7. LiTAMIN2: Ultra Light LiDAR-Based SLAM Using Geometric Approximation Applied with KL-Divergence https://arxiv.org/abs/2103.00784

8. 2D Laser SLAM with Closed Shape Features: Fourier Series Parameterization and Submap Joining

9. Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment https://arxiv.org/abs/2102.03798

10. Online Range-Based SLAM Using B-Spline Surfaces https://welcome.isr.tecnico.ulisboa.pt/wp-content/uploads/2021/03/09359349.pdf

11. MULLS: Versatile LiDAR SLAM Via Multi-Metric Linear Least Square https://arxiv.org/abs/2102.03771 / https://github.com/YuePanEdward/MULLS

12. Dynamic Object Aware LiDAR SLAM Based on Automatic Generation of Training Data https://arxiv.org/abs/2104.03657

13. A FastSLAM Approach Integrating Beamforming Maps for Ultrasound-Based Robotic Inspection of Metal Structures https://hal.archives-ouvertes.fr/hal-03017841/document

lidar localization:

1. Robust LiDAR Feature Localization for Autonomous Vehicles Using Geometric Fingerprinting on Open Datasets https://github.com/dcmlr/fingerprint-localization / https://ieeexplore.ieee.org/abstract/document/9363614/

2. Robust SRIF-Based LiDAR-IMU Localization for Autonomous Vehicles

3. NDT-Transformer: Large-Scale 3D Point Cloud Localisation Using the Normal Distribution Transform Representation https://arxiv.org/abs/2103.12292

4. Connecting Semantic Building Information Models and Robotics: An Application to 2D LiDAR-Based Localization

lidar mapping:

1. BALM: Bundle Adjustment for Lidar Mapping https://arxiv.org/pdf/2010.08215

2. Accelerating Probabilistic Volumetric Mapping Using Ray-Tracing Graphics Hardware https://arxiv.org/abs/2011.10348

3. ERASOR: Egocentric Ratio of Pseudo Occupancy-Based Dynamic Object Removal for Static 3D Point Cloud Map Building https://arxiv.org/abs/2103.04316

4. Multiresolution Representations for Large-Scale Terrain with Local Gaussian Process Regression

5. Kernel-Based 3-D Dynamic Occupancy Mapping with Particle Tracking

6. Poisson Surface Reconstruction for LiDAR Odometry and Mapping https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/vizzo2021icra.pdf

7. Dynamic Occupancy Grid Mapping with Recurrent Neural Networks https://arxiv.org/abs/2011.08659

8. Semantic Mapping of Construction Site from Multiple Daily Airborne LiDAR Data https://ieeexplore.ieee.org/document/9364688/

9. Multi-Resolution 3D Mapping with Explicit Free Space Representation for Fast and Accurate Mobile Robot Motion Planning https://arxiv.org/abs/2010.07929

10. MCMC Occupancy Grid Mapping with a Data-Driven Patch Prior

11. Elastic and Efficient LiDAR Reconstruction for Large-Scale Exploration Tasks https://arxiv.org/abs/2010.09232

LO & LIO:

1. FAST-LIO: A Fast, Robust LiDAR-Inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter https://arxiv.org/abs/2010.08196

2. KFS-LIO: Key-Feature Selection for Lightweight Lidar Inertial Odometry

3. LIRO: Tightly Coupled Lidar-Inertia-Ranging Odometry https://arxiv.org/abs/2010.13072

4. PSF-LO: Parameterized Semantic Features Based Lidar Odometry https://arxiv.org/abs/2010.13355

5. ENCODE: A dEep poiNt Cloud ODometry NEtwork

6. Automatic Hyper-Parameter Tuning for Black-Box LiDAR Odometry

7. Self-Supervised Learning of LiDAR Odometry for Robotic Applications https://arxiv.org/pdf/2011.05418

Point Cloud Registration:

1. PHASER: A Robust and Correspondence-Free Global Pointcloud Registration https://arxiv.org/abs/2102.02767

2. Differential Information Aided 3-D Registration for Accurate Navigation and Scene Reconstruction https://www.researchgate.net/publication/349678605_Differential_Information_Aided_3-D_Registration_for_Accurate_Navigation_and_Scene_Reconstruction/link/603be223299bf1cc26fbc4c3/download

3. Robust Motion Averaging under Maximum Correntropy Criterion https://arxiv.org/pdf/2004.09829

4. Toward a Unified Framework for Point Set Registration http://cvl.ist.osaka-u.ac.jp/wp-content/uploads/2021/03/li_icra2021.pdf

5. Voxelized GICP for Fast and Accurate 3D Point Cloud Registration https://easychair.org/publications/preprint/ftvV

6. Probabilistic Scan Matching: Bayesian Pose Estimation from Point Clouds

7. Learning the Next Best View for 3D Point Clouds Via Topological Features https://arxiv.org/abs/2103.02789

8. A New Framework for Registration of Semantic Point Clouds from Stereo and RGB-D Cameras https://arxiv.org/abs/2012.03683

feature:

1. SKD: Keypoint Detection for Point Clouds Using Saliency Estimation https://arxiv.org/abs/1912.04943

2. Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator https://arxiv.org/pdf/2102.11261

固态激光：

1. Lightweight 3-D Localization and Mapping for Solid-State LiDAR https://arxiv.org/abs/2102.03800

点云压缩：

1. Deep Compression for Dense Point Cloud Maps https://github.com/PRBonn/deep-point-map-compression / https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/wiesmann2021ral.pdf

全局定位：

1. Robust LiDAR Feature Localization for Autonomous Vehicles Using Geometric Fingerprinting on Open Datasets https://github.com/dcmlr/fingerprint-localization / https://ieeexplore.ieee.org/document/9363614

2. Learned Uncertainty Calibration for Visual Inertial Localization

3. Deep Samplable Observation Model for Global Localization and Kidnapping https://arxiv.org/abs/2009.00211

4. Camera Relocalization Using Deep Point Cloud Generation and Hand-Crafted Feature Refinement

5. Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment https://arxiv.org/abs/2010.09297

6. LiDAR-Based Initial Global Localization Using Two-Dimensional (2D) Submap Projection Image (SPI)

7. Global Aerial Localisation Using Image and Map Embeddings

8. Range Image-Based LiDAR Localization for Autonomous Vehicles https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/chen2021icra.pdf

9. RadarLoc: Learning to Relocalize in FMCW Radar https://arxiv.org/abs/2103.11562

10. Freetures: Localization in Signed Distance Function Maps https://arxiv.org/abs/2010.09378

11. Self-Supervised Learning of Domain-Invariant Local Features for Robust Visual Localization under Challenging Conditions https://ieeexplore.ieee.org/abstract/document/9354898/

12. Learning to Localize in New Environments from Synthetic Training Data https://arxiv.org/abs/2011.04539

13. Tightly-Coupled Multi-Sensor Fusion for Localization with LiDAR Feature Maps

14. Robust Dual Quadric Initialization for Forward-Translating Camera Movements https://ieeexplore.ieee.org/document/9384189

15. 3D Surfel Map-Aided Visual Relocalization with Learned Descriptors https://arxiv.org/abs/2104.03856

学习：

1. End-To-End Semi-Supervised Learning for Differentiable Particle Filters https://arxiv.org/abs/2011.05748

2. Initialisation of Autonomous Aircraft Visual Inspection Systems Via CNN-Based Camera Pose Estimation

Radar：

1. Do We Need to Compensate for Motion Distortion and Doppler Effects in Spinning Radar Navigation? https://github.com/keenan-burnett/yeti_radar_odometry / https://www.semanticscholar.org/paper/Do-We-Need-to-Compensate-for-Motion-Distortion-and-Burnett-Schoellig/1f20dab73a7e04c4f8dc801bd1de104b808a07db / https://arxiv.org/pdf/2011.03512

2. RadarLoc: Learning to Relocalize in FMCW Radar https://arxiv.org/abs/2103.11562

3. A Normal Distribution Transform-Based Radar Odometry Designed for Scanning and Automotive Radars

定位与建图（不确定传感器）

1. Simultaneous Estimation and Modeling of Robotic Systems with Non-Gaussian State Belief

数据关联：

1. CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multiview Data Association (I) https://arxiv.org/abs/1902.02256

2. ROBIN: A Graph-Theoretic Approach to Reject Outliers in Robust Estimation Using Invariants https://arxiv.org/abs/2011.03659

3. CLIPPER: A Graph-Theoretic Framework for Robust Data Association https://arxiv.org/abs/2011.10202

后端：

1. NF-iSAM: Incremental Smoothing and Mapping Via Normalizing Flows

2. A Switching-Coupled Backend for Simultaneous Localization and Dynamic Object Tracking

分布式SLAM：

1. Distributed Client-Server Optimization for SLAM with Limited On-Device Resources https://arxiv.org/abs/2103.14303

2. Invariant Extended Kalman Filtering Using Two Position Receivers for Extended Pose Estimation https://arxiv.org/abs/2104.14711

3. Compartmentalized Covariance Interp: A Novel Filter Architecture for Distributed Localization

4. Towards Robust State Estimation by Boosting the Maximum Correntropy Criterion Kalman Filter with Adaptive Behaviors https://arxiv.org/abs/2103.15354

5. Vehicle-To-Vehicle Collaborative Graph-Based Proprioceptive Localization https://scholar.google.com/scholar?oi=bibs&hl=es&cluster=16177649896940716005

long-term:

1. Lifelong Localization in Semi-Dynamic Environment

标定：

1. Extrinsic Calibration of Multiple LiDARs of Small FoV in Targetless Environments https://www.researchgate.net/publication/348894700_Extrinsic_Calibration_of_a_Small_FoV_LiDAR_and_a_Camera/link/601920b245851517ef32114f/download

2. Efficient Online Calibration for Autonomous Vehicle's Longitudinal Dynamical System: A Gaussian Model Approach

3. Automated Extrinsic Calibration for 3D LiDARs with Range Offset Correction Using an Arbitrary Planar Board

4. Targetless Multiple Camera-LiDAR Extrinsic Calibration Using Object Pose Estimation

5. Online Photometric Calibration of Automatic Gain Thermal Infrared Cameras https://arxiv.org/abs/2012.14292

6. A Continuous-Time Approach for 3D Radar to Camera Extrinsic Calibration https://arxiv.org/abs/2103.07505

7. Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching https://arxiv.org/abs/2102.04341

8. Auto-Calibration Method Using Stop Signs for Urban Autonomous Driving Applications https://arxiv.org/abs/2010.07441

UWB：

1. Bias Compensated UWB Anchor Initialization Using Information-Theoretic Supported Triangulation Points https://www.aau.at/wp-content/uploads/2021/03/UWB_Initialization_ICRA_CNS.pdf

2. Relative Position Estimation between Two UWB Devices with IMUs https://arxiv.org/abs/2104.10730

3. UWB Indoor Global Localisation for Nonholonomic Robots with Unknown Offset Compensation

4. Consistent State Estimation on Manifolds for Autonomous Metal Structure Inspection https://www.researchgate.net/profile/Alessandro-Fornasier/publication/350459466_Consistent_State_Estimation_on_Manifolds_for_Autonomous_Metal_Structure_Inspection/links/6061b364a6fdccbfea147687/Consistent-State-Estimation-on-Manifolds-for-Autonomous-Metal-Structure-Inspection.pdf

数学相关：

1. Efficient Modification of the Upper Triangular Square Root Matrix on Variable Reordering https://www.researchgate.net/publication/347950562_Efficient_Modification_of_the_Upper_Triangular_Square_Root_Matrix_on_Variable_Reordering/link/6009d60a92851c13fe2a8084/download

2. Robust 360-8PA: Redesigning the Normalized 8-Point Algorithm for 360-FoV Images https://arxiv.org/abs/2104.10900

数据集：

1. RADIATE: A Radar Dataset for Automotive Perception in Bad Weather https://arxiv.org/pdf/2010.09076

2. Cirrus: A Long-Range Bi-Pattern LiDAR Dataset https://arxiv.org/abs/2012.02938

3. VIODE: A Simulated Dataset to Address the Challenges of Visual-Inertial Odometry in Dynamic Environments https://github.com/kminoda/VIODE / https://www.semanticscholar.org/paper/VIODE%3A-A-Simulated-Dataset-to-Address-the-of-in-Minoda-Schilling/2f339961731cbaedf54d71f874541a5894ef5a15

4. A Multi-Spectral Dataset for Evaluating Motion Estimation Systems https://arxiv.org/abs/2007.00622

5. PicoVO: A Lightweight RGB-D Visual Odometry Targeting Resource-Constrained IoT Devices

6. Are We Ready for Unmanned Surface Vehicles in Inland Waterways? the USVInland Multisensor Dataset and Benchmark https://arxiv.org/abs/2103.05383

7. DSEC: A Stereo Event Camera Dataset for Driving Scenarios https://arxiv.org/abs/2103.06011

8. AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild https://github.com/African-Robotics-Unit/AcinoSet / https://arxiv.org/abs/2103.13282

医学定位：

1. Robotically Surgical Vessel Localization Using Robust Hybrid Video Motion Magnification https://ieeexplore.ieee.org/document/9353981

声源定位：

1. GCC-PHAT with Speech-Oriented Attention for Robotic Sound Source Localization

GNSS：

1. Towards Robust GNSS Positioning and Real-Time Kinematic Using Factor Graph Optimization

UAV：

1. Tracking and Relative Localization of Drone Swarms with a Vision-Based Headset https://ieeexplore.ieee.org/document/9324934

2. UAV Localization Using Autoencoded Satellite Images https://arxiv.org/abs/2102.05692

3. Learning-Based Bias Correction for Time Difference of Arrival Ultra-Wideband Localization of Resource-Constrained Mobile Robots https://arxiv.org/abs/2103.01885

4. Sensing Via Collisions: A Smart Cage for Quadrotors with Applications to Self-Localization

机器人定位建图：

1. Improving Ranging-Based Location Estimation with Rigidity-Constrained CRLB-Based Motion Planning

2. Relative Position Estimation in Multi-Agent Systems Using Attitude-Coupled Range Measurements

3. Rover Relocalization for Mars Sample Return by Virtual Template Synthesis and Matching https://arxiv.org/abs/2103.03395

4. A Comparison between Joint Space and Task Space Mappings for Dynamic Teleoperation of an Anthropomorphic Robotic Arm in Reaction Tests https://arxiv.org/abs/2011.02508

5. State Estimation for Hybrid Wheeled-Legged Robots Performing Mobile Manipulation Tasks

6. Robust Localization for Planar Moving Robot in Changing Environment: A Perspective on Density of Correspondence and Depth https://arxiv.org/abs/2011.00439

PPA：

1. Weighted Node Mapping and Localisation on a Pixel Processor Array https://www.researchgate.net/publication/350187131_Weighted_Node_Mapping_and_Localisation_on_a_Pixel_Processor_Array/link/6054d443299bf17367550a00/download

Sonar:

1. Predictive 3D Sonar Mapping of Underwater Environments Via Object-Specific Bayesian Inference https://arxiv.org/abs/2104.03203

触觉SLAM：

1. Tactile SLAM: Real-Time Inference of Shape and Pose from Planar Pushing https://arxiv.org/abs/2011.07044

主动SLAM：

1. Invariant EKF Based 2D Active SLAM with Exploration Task

IMU：

1. IMU Data Processing for Inertial Aided Navigation: A Recurrent Neural Network Based Approach https://arxiv.org/abs/2103.14286

2. Highly Efficient Line Segment Tracking with an IMU-KLT Prediction and a Convex Geometric Distance Minimization

3. IMU/Vehicle Calibration and Integrated Localization for Autonomous Driving

4. Reinforcement Learning for Orientation Estimation Using Inertial Sensors with Performance Guarantee https://arxiv.org/abs/2103.0235

本文仅做学术分享，如有侵权，请联系删文。

下载1

在「3D视觉工坊」公众号后台回复：3D视觉，即可下载 3D视觉相关资料干货，涉及相机标定、三维重建、立体视觉、SLAM、深度学习、点云后处理、多视图几何等方向。

下载2

在「3D视觉工坊」公众号后台回复：3D视觉github资源汇总，即可下载包括结构光、标定源码、缺陷检测源码、深度估计与深度补全源码、点云处理相关源码、立体匹配源码、单目、双目3D检测、基于点云的3D检测、6D姿态估计源码汇总等。

下载3

在「3D视觉工坊」公众号后台回复：相机标定，即可下载独家相机标定学习课件与视频网址；后台回复：立体匹配，即可下载独家立体匹配学习课件与视频网址。

重磅！3DCVer-学术论文写作投稿 交流群已成立

扫码添加小助手微信，可申请加入3D视觉工坊-学术论文写作与投稿 微信交流群，旨在交流顶会、顶刊、SCI、EI等写作与投稿事宜。

同时也可申请加入我们的细分方向交流群，目前主要有3D视觉、CV&深度学习、SLAM、三维重建、点云后处理、自动驾驶、多传感器融合、CV入门、三维测量、VR/AR、3D人脸识别、医疗影像、缺陷检测、行人重识别、目标跟踪、视觉产品落地、视觉竞赛、车牌识别、硬件选型、学术交流、求职交流、ORB-SLAM系列源码交流、深度估计等微信群。

一定要备注：研究方向+学校/公司+昵称，例如：”3D视觉 + 上海交大 + 静静“。请按照格式备注，可快速被通过且邀请进群。原创投稿也请联系。

▲长按加微信群或投稿

▲长按关注公众号

3D视觉从入门到精通知识星球：针对3D视觉领域的视频课程（三维重建系列、三维点云系列、结构光系列、手眼标定、相机标定、orb-slam3等视频课程）、知识点汇总、入门进阶学习路线、最新paper分享、疑问解答五个方面进行深耕，更有各类大厂的算法工程人员进行技术指导。与此同时，星球将联合知名企业发布3D视觉相关算法开发岗位以及项目对接信息，打造成集技术与就业为一体的铁杆粉丝聚集区，近2000星球成员为创造更好的AI世界共同进步，知识星球入口：

学习3D视觉核心技术，扫描查看介绍，3天内无条件退款

 圈里有高质量教程资料、可答疑解惑、助你高效解决问题

觉得有用，麻烦给个赞和在看~