ICRA2022论文汇总 | 跟踪/检测/分割/传感器标定/SLAM/轨迹预测/导航规划等

点击下方卡片，关注“自动驾驶之心”公众号

ADAS巨卷干货，即可获取

点击进入→自动驾驶之心技术交流群

后台回复【ECCV2022】获取ECCV2022所有自动驾驶方向论文！

• Robotic Perception and Mapping: Emerging Techniques - Website

• Future of Construction: Build Faster, Better, Safer - Together with Robots - Website

• 6TH WORKSHOP ON LEGGED ROBOTS - Website

• Canonical DIY Tutorials on Non-Gaussian SLAM and Computation - Website

深度估计

1. Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking

2. Full Surround Monodepth from Multiple Cameras

3. Adaptive Cost Volume Fusion Network for Multi-Modal Depth Estimation in Changing Environments

4. Lightweight Monocular Depth Estimation through Guided Decoding

5. UFODepth: Unsupervised Learning with Flow-Based Odometry Optimization for Metric Depth Estimation

6. Monocular Depth Distribution Alignment with Low Computation

7. Improving Depth Estimation Using Map-Based Depth Priors

目标跟踪

1. PF-MOT: Probability Fusion Based 3D Multi-Object Tracking for Autonomous Vehicles

自动驾驶

1. Learning to Remove Bad Weather: Towards Robust Visual Perception for Self-Driving

2. Combined Fast Control of Drifting State and Trajectory Tracking for Autonomous Vehicles Based on MPC Controller

3. Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous Driving

4. De-Snowing LiDAR Point Clouds with Intensity and Spatial-Temporal Features

5. VISTA 2.0: An Open, Data-Driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles

6. Adaptive Cubature Split Covariance Intersection Filter for Multi-Vehicle Cooperative Localization

7. A Two-Stage Optimization-Based Motion Planner for Safe Urban Driving

8. Autonomous Single-Image Drone Exploration with Deep Reinforcement Learning and Mixed Reality

9. Control-Aware Prediction Objectives for Autonomous Driving

10. Localization of a Smart Infrastructure Fisheye Camera in a Prior Map for Autonomous Vehicles

11. Vision-Based Large-Scale 3D Semantic Mapping for Autonomous Driving Applications

3D目标检测

1. Star-Convolution for Image-Based 3D Object Detection

2. Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection in Self-Driving Cars

3. Rethinking LiDAR Object Detection in Adverse Weather Conditions

4. Multi-Class 3D Object Detection with Single-Class Supervision

5. End-to-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization

语义/点云/全景分割

1. Dilated Continuous Random Field for Semantic Segmentation

2. Realtime Global Attention Network for Semantic Segmentation

3. EfficientLPS: Efficient LiDAR Panoptic Segmentation

4. SMAC-Seg: LiDAR Panoptic Segmentation Via Sparse Multi-Directional Attention Clustering

5. Contrastive Instance Association for 4D Panoptic Segmentation for Sequences of 3D LiDAR Scans

多传感器标定融合

1. Extrinsic Calibration and Verification of Multiple Non-Overlapping Field of View Lidar Sensors

2. LB-L2L-Calib: Accurate and Robust Extrinsic Calibration for Multiple 3D LiDARs with Long Baseline and Large Viewpoint Difference

3. Accurate Calibration of Multi-Perspective Cameras from a Generalization of the Hand-Eye Constraint

4. LTSR: Long-Term Semantic Relocalization Based on HD Map for Autonomous Vehicles

5. HDMapNet: An Online HD Map Construction and Evaluation Framework

6. Spatiotemporal Multisensor Calibration Via Gaussian Processes Moving Target Tracking

7. Extrinsic Calibration of Multiple Inertial Sensors from In-Flight Data

8. Information-Theoretic Online Multi-Camera Extrinsic Calibration

9. Self-Supervised Camera Self-Calibration from Video

10. FusionNet: Coarse-To-Fine Extrinsic Calibration Network of LiDAR and Camera with Hierarchical Point-Pixel Fusion

11. Graph-Based Multi-Sensor Fusion for Consistent Localization of Autonomous Construction Robots

视觉SLAM

1. Burst Imaging for Light-Constrained Structure-From-Motion

2. Self-Supervised Depth and Ego-Motion Estimation for Monocular Thermal Video Using Multi-Spectral Consistency Loss

3. LoopNet: Where to Focus? Detecting Loop Closures in Dynamic Scenes

4. SimVODIS++: Neural Semantic Visual Odometry in Dynamic Environments

5. PANet: A Novel Pixel-Level Attention Network for 6D Pose Estimation with Embedding Vector Features

6. Overhead Image Factors for Underwater Sonar-Based SLAM

7. MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

8. Non-Penetration Iterative Closest Points for Single-View Multi-Object 6D Pose Estimation

9. Translating Images into Maps

10. EDPLVO: Efficient Direct Point-Line Visual Odometry

11. DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions

12. Precise 3D Reconstruction of Plants from UAV Imagery Combining Bundle Adjustment and Template Matching

13. ROW-SLAM: Under-Canopy Cornfield Semantic SLAM

14. Loop Closure Detection and SLAM in Vineyards with Deep Semantic Cues

15. Spatial Acoustic Projection for 3D Imaging Sonar Reconstruction

16. Robust Semantic Mapping and Localization on a Free-Flying Robot in Microgravity

17. 360VO: Visual Odometry Using a Single 360 Camera

18. SAGE: SLAM with Appearance and Geometry Prior for Endoscopy

19. Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World

20. Continuous-Time vs. Discrete-Time Vision-Based SLAM: A Comparative Study

21. DKNAS: A Practical Deep Keypoint Extraction Framework Based on Neural Architecture Search

22. Precise 3D Reconstruction of Plants from UAV Imagery Combining Bundle Adjustment and Template Matching

23. MSC-VO: Exploiting Manhattan and Structural Constraints for Visual Odometry

24. A Model for Multi-View Residual Covariances Based on Perspective Deformation

25. Incremental Abstraction in Distributed Probabilistic SLAM Graphs

26. UV-SLAM: Unconstrained Line-Based SLAM Using Vanishing Points for Structural Mapping

27. A Right Invariant Extended Kalman Filter for Object Based SLAM

28. Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth

29. Visual Localization and Mapping Leveraging the Constraints of Local Ground Manifolds

30. Panoptic Multi-TSDFs: A Flexible Representation for Online Multi-Resolution Volumetric Mapping and Long-Term Dynamic Scene Consistency

31. FD-SLAM: 3-D Reconstruction Using Features and Dense Matching

32. AirDOS: Dynamic SLAM Benefits from Articulated Objects

33. A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes

34. Vision-Based Large-Scale 3D Semantic Mapping for Autonomous Driving Applications

35. Efficient and Robust Semantic Mapping for Indoor Environments

36. Asynchronous Optimisation for Event-Based Visual Odometry

37. Optimizing Terrain Mapping and Landing Site Detection for Autonomous UAVs

38. Exploration with Global Consistency Using Real-Time Re-Integration and Active Loop Closure

39. SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints

40. Accurate and Robust Object-Oriented SLAM with 3D Quadric Landmarks in Outdoors

激光SLAM

1. Learning Spatiotemporal Occupancy Grid Maps for Lifelong Navigation in Dynamic Scenes

2. Reconstruction and Synthesis of Lidar Point Clouds of Spray

3. CT-ICP: Real-Time Elastic LiDAR Odometry with Loop Closure

4. GCLO: Ground Constrained LiDAR Odometry with Low-Drifts for GPS-Denied Indoor Environments

5. Robust Self-Supervised LiDAR Odometry Via Representative Structure Discovery and 3D Inherent Error Modeling

6. Direct LiDAR Odometry: Fast Localization with Dense Point Clouds

7. Ensemble Kalman Filter Based LiDAR Odometry for Skewed Point Clouds Using Scan Slicing

8. LLOL: Low-Latency Odometry for Spinning Lidars

9. Performance Guarantees for Spectral Initialization in Rotation Averaging and Pose-Graph SLAM

10. ART-SLAM: Accurate Real-Time 6DoF LiDAR SLAM

11. Performance Models in Robotics with a Use Case on SLAM

12. LT-Mapper: A Modular Framework for LiDAR-Based Lifelong Mapping

13. DynamicFilter: An Online Dynamic Objects Removal Framework for Highly Dynamic Environments

14. Memory-Efficient Gaussian Fitting for Depth Images in Real Time

15. Reconstructing Occluded Elevation Information in Terrain Maps with Self-Supervised Learning

点云配准

1. Translation Invariant Global Estimation of Heading Angle Using Sinogram of LiDAR Point Cloud

2. Generalized 3D Rigid Point Set Registration with Anisotropic Positional Error Based on Bayesian Coherent Point Drift

3. Fast and Robust Registration of Partially Overlapping Point Clouds

4. Deep Bayesian ICP Covariance Estimation

5. A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments

6. K-Closest Points and Maximum Clique Pruning for Efficient and Effective 3-D Laser Scan Matching

7. FuzzyPSReg: Strategies of Fuzzy Cluster-Based Point Set Registration

相机定位

1. A Deep Feature Aggregation Network for Accurate Indoor Camera Localization

路径规划导航

1. Learning to Ground Objects for Robot Task and Motion Planning

2. Autonomous and Adaptive Navigation for Terrestrial-Aerial Bimodal Vehicles

3. VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation

4. Multi-Modal Motion Prediction with Transformer-Based Neural Network for Autonomous Driving

5. Proactive Anomaly Detection for Robot Navigation with Multi-Sensor Fusion

6. Autonomous Exploration Development Environment and the Planning Algorithms

轨迹预测

1. DIRECT: A Differential Dynamic Programming Based Framework for Trajectory Generation

2. Trajectory Prediction for Autonomous Driving with Topometric Map

3. Domain Generalization for Vision-Based Driving Trajectory Generation

其它

1. Aerial-Ground Robots Collaborative 3D Mapping in GNSS-Denied Environments

往期回顾

史上最全综述 | 3D目标检测算法汇总！（单目/双目/LiDAR/多模态/时序/半弱自监督）

【自动驾驶之心】全栈技术交流群

自动驾驶之心是首个自动驾驶开发者社区，聚焦目标检测、语义分割、全景分割、实例分割、关键点检测、车道线、目标跟踪、3D目标检测、多传感器融合、SLAM、光流估计、轨迹预测、高精地图、规划控制、AI模型部署落地等方向；

加入我们：自动驾驶之心技术交流群汇总！

自动驾驶之心【知识星球】

想要了解更多自动驾驶感知（分类、检测、分割、关键点、车道线、3D目标检测、多传感器融合、目标跟踪、光流估计、轨迹预测）、自动驾驶定位建图（SLAM、高精地图）、自动驾驶规划控制、领域技术方案、AI模型部署落地实战、行业动态、岗位发布，欢迎扫描下方二维码，加入自动驾驶之心知识星球（三天内无条件退款），日常分享论文+代码，这里汇聚行业和学术界大佬，前沿技术方向尽在掌握中，期待交流！