wanghuayou1028 / IROS2021-SLAM-paper-list

IROS 2021 SLAM paper list

IROS2021-SLAM-paper-list

IROS 2021 SLAM, autonomous driving paper list

All the classified papers can be download from Baidu cloud Disk: Link：https://pan.baidu.com/s/1GdwaNrH80mgem4xbZKdZ-Q passwork：384o

IROS2021_SLAM_paper_list

VSLAM:

1. A Comparison of Modern General-Purpose Visual SLAM Approaches
2. A General Framework for Lifelong Localization and Mapping in Changing Environment
3. Accurate Visual-Inertial SLAM by Manhattan Frame Re-Identification
4. AcousticFusion Fusing Sound Source Localization to Visual SLAM in Dynamic Environments
5. CodeMapping Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations
6. DeepRelativeFusion Dense Monocular SLAM Using Single-Image Relative Depth Prediction
7. Direct Near-Infrared-Depth Visual SLAM with Active Lighting
8. Efficient Multimodal Belief Propagation for Robust SLAM Using Clustering Based Reparameterization
9. Geometry-Based Graph Pruning for Lifelong SLAM
10. Hierarchical Segment-Based Optimization for SLAM
11. Line Flow Based Simultaneous Localization and Mapping
12. Moving SLAM Fully Unsupervised Deep Learning in Non-Rigid Scenes
13. Phase-SLAM Mobile Structured Light Illumination for Full Body 3D Scanning
14. Robust Initialization of Multi-Camera SLAM with Limited View Overlaps and Inaccurate Extrinsic Calibration
15. Stereo Plane SLAM Based on Intersecting Lines

VO:

1. Deep Unsupervised Learning Based Visual Odometry with Multi-Scale Matching and Latent Feature Constraint
2. DPLVO Direct Point-Line Monocular Visual Odometry
3. Feature-Aided Bundle Adjustment Learning Framework for Self-Supervised Monocular Visual Odometry
4. MDN-VO Estimating Visual Odometry with Confidence
5. Reactive Visual Odometry Scheduling Based on Noise Analysis Using an Adaptive Extended Kalman Filter

VIO:

1. A Visual Inertial Odometry Framework for 3D Points, Lines and Planes
2. Accurate Visual-Inertial SLAM by Feature Re-Identification
3. An Analytical Solution to the IMU Initialization Problem for Visual-Inertial Systems
4. An Open-Source, Fiducial-Based, Underwater Stereo Visual-Inertial Localization Method with Refraction Correction
5. Extended VINS-Mono A Systematic Approach for Absolute and Relative Vehicle Localization in Large-Scale Outdoor Environments
6. Multi-Layer VI-GNSS Global Positioning Framework with Numerical Solution Aided MAP Initialization
7. PLF-VINS Real-Time Monocular Visual-Inertial SLAM with Point-Line Fusion and Parallel-Line Fusion
8. RP-VIO Robust Plane-based Visual-Inertial Odometry for Dynamic Environments
9. Sampson Distance A New Approach to Improving Visual-Inertial Odometry's Accuracy
10. Stereo Visual Inertial Odometry for Robots with Limited Computational Resources

Visual localization:

1. DistillPose Lightweight Camera Localization Using Auxiliary Learning
2. Efficient Localisation Using Images and OpenStreetMaps
3. Finding Robust 2D-To-3D Correspondence with LSTM Score Estimation for Camera Localization
4. High Accuracy Three-Dimensional Self-Localization Using Visual Markers and Inertia Measurement Unit
5. Real-Time Geo-Localization Using Satellite Imagery and Topography for Unmanned Aerial Vehicles
6. Recalling Direct 2D-3D Matches for Large-Scale Visual Localization

Semantic localization and mapping:

1. A Multi-Hypothesis Approach to Pose Ambiguity in Object-Based SLAM
2. Automatic Construction of Lane-Level HD Maps for Urban Scenes
3. AVP-Loc Surround View Localization and Relocalization Based on HD Vector Map for Automated Valet Parking
4. BSP-MonoLoc Basic Semantic Primitives Based Monocular Localization on Roads
5. Coarse-To-Fine Semantic Localization with HD Map for Autonomous Driving in Structural Scenes
6. Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAM
7. DT-Loc Monocular Visual Localization on HD Vector Map Using Distance Transforms of 2D Semantic Detections
8. Monte-Carlo Localization in Underground Parking Lots Using Parking Slot Numbers
9. Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness
10. Robust LiDAR Localization on an HD Vector Map without a Separate Localization Layer
11. Robust Multi-Camera SLAM with Manhattan Constraint Toward Automated Valet Parking
12. Semantic Image Alignment for Vehicle Localization
13. SemSegMap - 3D Segment-Based Semantic Localization
14. Topology Aware Object-Level Semantic Mapping towards More Robust Loop Closure
15. TUPPer-Map Temporal and Unified Panoptic Perception for 3D Metric-Semantic Mapping

Back-end:

1. Cross-Layer Configuration Optimization for Localization on Resource-Constrained Devices
2. Differentiable Factor Graph Optimization for Learning Smoothers
3. Direct Bundle Adjustment for 3D Image Fusion with Application to Transesophageal Echocardiography
4. Distributed Certifiably Correct Pose-Graph Optimization
5. Random Fourier Features Based SLAM
6. Robust Rank Deficient SLAM
7. Some Research Questions for SLAM in Deformable Environments

Feature and matching:

1. RaP-Net A Region-Wise and Point-Wise Weighting Network to Extract Robust Features for Indoor Localization
2. Refractive Light-Field Features for Curved Transparent Objects in Structure from Motion
3. RoRD Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching
4. Superline A Robust Line Segment Feature for Visual SLAM

Lidar SLAM:

1. CLMM-Net Robust Cascaded LiDAR Map Matching Based onMulti-Level Intensity Map
2. F-LOAM Fast LiDAR Odometry and Mapping
3. LiDAR SLAM with Plane Adjustment for Indoor Environment
4. LiDAR-Based Object-Level SLAM for Autonomous Vehicles
5. Low-Drift Odometry, Mapping and Ground Segmentation Using a Backpack LiDAR System
6. Map Compressibility Assessment for LiDAR Registration
7. Shipborne Sea-Ice Field Mapping Using a LiDAR

LIO:

1. Adaptive Hyperparameter Tuning for Black-Box LiDAR Odometry
2. CLINS Continuous-Time Trajectory Estimation for LiDAR Inertial System
3. Real-Time Multi-Adaptive-Resolution-Surfel 6D LiDAR Odometry Using Continuous-Time Trajectory Optimization
4. RF-LIO Removal-First Tightly-Coupled Lidar Inertial Odometry in High Dynamic Environments
5. What's in My LiDAR Odometry Toolbox

Mapping and reconstruction:

1. An Efficient and Continuous Representation for Occupancy Mapping with Random Mapping
2. Dynamic Domain Adaptation for Single-View 3D Reconstruction
3. Endo-Depth-and-Motion Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints
4. Local to Global Plane Regularity Aggregation for Dense Surfel Mapping
5. Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization
6. What's Best for My Mesh Convex or Non-Convex Regularisation for Mesh Optimisation

Multi robot SLAM:

1. A Collaborative Visual SLAM Framework for Service Robots
2. Coxgraph Multi-Robot Collaborative, Globally Consistent, Online Dense Reconstruction System
3. Distributed Visual-Inertial Cooperative Localization
4. MR-iSAM2 Incremental Smoothing and Mapping with Multi-Root Bayes Tree for Multi-Robot SLAM
5. ORBBuf A Robust Buffering Method for Remote Visual SLAM

Multi sensor fusion:

1. GR-Fusion Multi-Sensor Fusion SLAM for Ground Robots with High Robustness and Low Drift
2. Lvio-Fusion A Self-Adaptive Multi-Sensor Fusion SLAM Framework Using Actor-Critic Method
3. Modular Multi-Sensor Fusion A Collaborative State Estimation Perspective
4. R2LIVE A Robust, Real-Time, LiDAR-Inertial-Visual Tightly-Coupled State Estimator and Mapping
5. Radar Visual Inertial Odometry and Radar Thermal Inertial Odometry Robust Navigation even in Challenging Visual Conditions
6. Super Odometry IMU-Centric LiDAR-Visual-Inertial Estimator for Challenging Environments

Place recognition:

1. A Hierarchical Dual Model of Environment and Place-Specific Utility for Visual Place Recognition
2. A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition
3. CORAL Colored Structural Representation for Bi-Modal Place Recognition
4. Evaluation of Long-Term LiDAR Place Recognition
5. EventVLAD Visual Place Recognition with Reconstructed Edges from Event Cameras
6. Motion Field Consensus with Locality Preservation A Geometric Confirmation Strategy for Loop Closure Detection
7. MV-FractalDB Formula-Driven Supervised Learning for Multi-View Image Recognition
8. Object-To-Scene Learning to Transfer Object Knowledge to Indoor Scene Recognition
9. SSC Semantic Scan Context for Large-Scale Place Recognition
10. SymbioLCD Ensemble-Based Loop Closure Detection Using CNN-Extracted Objects and Visual Bag-Of-Words
11. Visual Place Recognition Using LiDAR Intensity Information

Point cloud completion:

1. Graph Guided Deformation for Point Cloud Completion
2. PCTMA-Net Point Cloud Transformer with Morphing Atlas-Based Point Generation Network for Dense Point Cloud Completion

Point cloud registration:

1. Geometry Guided Network for Point Cloud Registration
2. Keypoint Matching for Point Cloud Registration Using Multiplex Dynamic Graph Attention Networks
3. Robust and Accurate Point Set Registration with Generalized Bayesian Coherent Point Drift

Calibration:

1. A Two-Step Optimization for Extrinsic Calibration of Multiple Camera System (MCS) Using Depth-Weighted Normalized Points
2. Annotation-Free Camera-LiDAR Calibration with Semantic Alignment Loss
3. Dynamic Event Camera Calibration
4. Kalibrot A Simple-To-Use Matlab Package for Robot Kinematic Calibration
5. Kinodynamic Model Identification A Unified Geometric Approach
6. Learning to Calibrate - Estimating the Hand-Eye Transformation without Calibration Objects
7. Odometry Model Calibration for Self-Driving Vehicles with Noise Correction
8. Pixel-Level Extrinsic Self Calibration of High Resolution LiDAR and Camera in Targetless Environments
9. Single-Shot Is Enough Panoramic Infrastructure Based Calibration of Multiple Cameras and 3D LiDARs

Dataset:

1. A Dataset for Provident Vehicle Detection at Night
2. Diverse Complexity Measures for Dataset Curation in Self-Driving
3. Drive on Pedestrian Walk. TUK Campus Dataset
4. NYU-VPR Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences
5. Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception
6. The Radar Ghost Dataset � an Evaluation of Ghost Objects in Automotive Radar Data
7. Topo-Boundary A Benchmark Dataset on Topological Road-Boundary Detection Using Aerial Images for Autonomous Driving
8. TUM-VIE The TUM Stereo Visual-Inertial Event Dataset

Depth:

1. Accurate Depth Estimation from a Hybrid Event-RGB Stereo Setup
2. ADAADepth Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
3. Bootstrapped Self-Supervised Training with Monocular Video for Semantic Segmentation and Depth Estimation
4. Improving Monocular Depth Estimation by Semantic Pre-Training
5. Self Attention Guided Depth Completion Using RGB and SparseLiDAR Point Clouds
6. Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation
7. Unsupervised Deep Persistent Monocular Visual Odometry and Depth Estimation in Extreme Environments
8. Unsupervised Learning of Depth Estimation and Visual Odometry for Sparse Light Field Cameras
9. Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints
10. VoluMon Weakly Supervised Volumetric Monocular Estimation with Ellipsoid Representations

Stereo matching:

1. Correlate-And-Excite Real-Time Stereo Matching Via Guided Cost Volume Excitation
2. ORStereo Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images
3. SRH-Net Stacked Recurrent Hourglass Network for Stereo Matching
4. Stereo Matching by Self-Supervision of Multiscopic Vision

MVS:

1. EOMVS Event-Based Omnidirectional Multi-View Stereo

Radar:

1. Angular Super-Resolution Radar SLAM
2. CFEAR Radarodometry - Conservative Filtering for Efficient and Accurate Radar Odometry
3. Continuous-Time Radar-Inertial Odometry for Automotive Radars
4. Ground Encoding Learned Factor Graph-Based Models for Localizing Ground Penetrating Radar
5. Radar Odometry on SE(3) with Constant Velocity Motion Prior

UWB:

1. A Computationally Efficient Moving Horizon Estimator for Ultra-Wideband Localization on Small Quadrotors
2. Heading Estimation Using Ultra-Wideband Received Signal Strength and Gaussian Processes
3. Online Spatio-Temporal Calibration of Tightly-Coupled Ultrawideband-Aided Inertial Localization

IROS2021_autonomous_driving_paper_list:

Perception:

1. 3D Radar Velocity Maps for Uncertain Dynamic Environments
2. A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
3. A Simple and Efficient Multi-Task Network for 3D Object Detection and Road Understanding
4. BEV-Net A Bird's Eye View Object Detection Network for LiDAR Point Cloud
5. CP-Loss Connectivity-Preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images
6. Fine-Grained Off-Road Semantic Segmentation and Mapping Via Contrastive Learning
7. LiDAR-Based Drivable Region Detection for Autonomous Driving
8. Monitoring Object Detection Abnormalities Via Data-Label and Post-Algorithm Abstractions
9. Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography
10. RV-FuseNet Range View Based Fusion of Time-Series LiDAR Data for Joint 3D Object Detection and Motion Forecasting
11. SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving
12. COINet: Adaptive Segmentation with Co-Interactive Network for Autonomous Driving
13. SNE-RoadSeg+ Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection
14. Unsupervised Vehicle Re-Identification Via Self-Supervised Metric Learning Using Feature Dictionary

Prediction:

1. Automated Type-Aware Traffic Speed Prediction Based on Sparse Intelligent Camera System
2. Decoder Fusion RNN Context and Interaction Aware Decoders for Trajectory Prediction
3. Joint Intention and Trajectory Prediction Based on Transformer
4. Maneuver-based Trajectory Prediction for Self-driving Cars Using Spatio-temporal Convolutional Networks
5. Multiple Contextual Cues Integrated Trajectory Prediction for Autonomous Driving

Tracking:

1. Cross-Modal 3D Object Detection and Tracking for Auto-Driving
2. Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving
3. Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
4. Score Refinement for Confidence-Based 3D Multi-Object Tracking

Planning:

1. DeepSIL A Software-In-The-Loop Framework for Evaluating Motion Planning Schemes Using Multiple Trajectory Prediction Networks
2. Diverse Critical Interaction Generation for Planning and Planner Evaluation
3. PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
4. STFP: Simultaneous Traffic Scene Forecasting and Planning for Autonomous Driving
5. A Novel Recursive Smooth Trajectory Generation Method for Unmanned Vehicles

Intention recognition:

1. A Multimodal and Hybrid Framework for Human Navigational Intent Inference
2. An Efficient Understandability Objective for Dynamic Optimal Control
3. CovarianceNet Conditional Generative Model for Correct Covariance Prediction in Human Motion Prediction
4. GRIT Fast, Interpretable, and Verifiable Goal Recognition with Learned Decision Trees for Autonomous Driving
5. Interpretable Goal Recognition in the Presence of Occluded Factors for Autonomous Vehicles
6. Multi-modal Scene-compliant User Intention Estimation in Navigation
7. Safety-Oriented Pedestrian Occupancy Forecasting
8. Simultaneous Prediction of Pedestrian Trajectory and Actions Based on Context Information Iterative Reasoning

Control:

1. Semi-Cooperative Control for Autonomous Emergency Vehicles

Navigation:

1. A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
2. A Kinematic Model for Trajectory Prediction in General Highway Scenarios
3. A Multi-Objective Path Planning and Exploration Framework for Unknown and Unstructured Environments
4. Autonomous Drone Racing with Deep Reinforcement Learning
5. Autonomous Mobile Robot Navigation Independent of Road Boundary Using Driving Recommendation Map
6. Autonomous Vehicle Navigation in Semi-Structured Environments Based on Sparse Waypoints and LiDAR Road-Tracking
7. Connecting Deep-Reinforcement-Learning-Based Obstacle Avoidance with Conventional Global Planners Using Waypoint Generators
8. Context and Orientation Aware Path Tracking
9. Cooperative Autonomous Vehicles That Sympathize with Human Drivers
10. Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows
11. DiGNet Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks
12. Fast Autonomous Robotic Exploration Using the Underlying Graph Structure
13. Gaussian Process-based Interpretable Runtime Adaptation for Safe Autonomous Systems Operations in Unstructured Environments
14. Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graph
15. KB-Tree Learnable and Continuous Monte-Carlo Tree Search for Autonomous Driving Planning
16. Latent Attention Augmentation for Robust Autonomous Driving Policies
17. Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain
18. Learning-Based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
19. LiDAR Degradation Quantification for Autonomous Driving in Rain
20. Map-Aided Train Navigation with IMU Measurements
21. Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning
22. NavTuner Learning a Scene-Sensitive Family of Navigation Policies
23. On Fault Classification in Connected Autonomous Vehicles Using Output-Only Measurements
24. Online High-Level Model Estimation for Efficient Hierarchical Robot Navigation
25. Pallet Detection and Docking Strategy for Autonomous Pallet Truck AGV Operation
26. Reinforcement Learning Based Negotiation-Aware Motion Planning of Autonomous Vehicles
27. Road Graphical Neural Networks for Autonomous Roundabout Driving
28. Robust Policy Search for an Agile Ground Vehicle under Perception Uncertainty
29. Shape Estimation of Negative Obstacles for Autonomous Navigation
30. The Role of the Hercules Autonomous Vehicle During the COVID-19 Pandemic An Autonomous Logistic Vehicle for Contactless Goods Transportation
31. Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs
32. Vulnerability of Connected Autonomous Vehicles Networks to Periodic Time-Varying Communication Delays of Certain Frequency

Modeling:

1. A High-Accuracy Framework for Vehicle Dynamic Modeling in Autonomous Driving
2. The Reasonable Crowd Towards Evidence-Based and Interpretable Models of Driving Behavior

Multi robot system:

1. Cooperative Transportation Robot System Using Risk-Sensitive Stochastic Control

Others:

1. Agent-Aware State Estimation for Autonomous Vehicles
2. Dynamic Lambda-Field A Counterpart of the Bayesian Occupancy Grid for Risk Assessment in Dynamic Environments
3. Finding Failures in High-Fidelity Simulation Using Adaptive Stress Testing and the Backward Algorithm
4. Gridlock-Free Autonomous Parking Lots for Autonomous Vehicles
5. StyleLess Layer Improving Robustness for Real-World Driving
6. Vehicle Dispatch in On-Demand Ride-Sharing with Stochastic Travel Times
7. Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization