ICRA 2023 | 移动机器人/SLAM相关论文

ICRA 2023 Mobile-Robot/SLAM Selection Paper

• 0006: Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras

• 0072: A Global Max-Flow-Based Multi-Resolution Next-Best-View Method for Reconstruction of 3D Unknown Objects

• 0077: Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping

• 0084: Multimodal Neural Radiance Field

• 0106: Autonomous Exploration in a Cluttered Environment for a Mobile Robot with 2D-Map Segmentation and Object Detection

• 0120: DynaVINS: A Visual-Inertial SLAM for Dynamic Environments

• 0121: ViViD++ : Vision for Visibility Dataset

• 0124: Rearrange Indoor Scenes for Human-Robot Co-Activity

• 0144: Stein Particle Filter for Nonlinear, Non-Gaussian State Estimation

• 0145: Stein ICP for Uncertainty Estimation in Point Cloud Matching

• 0146: Faster-LIO: Lightweight Tightly Coupled Lidar-inertial Odometry using Parallel Sparse Incremental Voxels

• 0176: Visual-Inertial Odometry with Online Calibration of Velocity-Control Based Kinematic Motion Models

• 0178: Reuse your features: unifying retrieval and feature-metric alignment

• 0181: Homography-based loss function for camera pose regression

• 0184: 360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation

• 0188: ORORA: Outlier-Robust Radar Odometry

• 0216: GNM: A General Navigation Model to Drive Any Robot

• 0220: NeRF-Loc: Visual Localization with Conditional Neural Radiance Field

• 0221: Light-Weight Pointcloud Representation with Sparse Gaussian Process

• 0222: Fusing Event-based Camera and Radar for SLAM Using Spiking Neural Networks with Continual STDP Learning

• 0258: Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs

• 0349: NIFT: Neural Interaction Field and Template for Object Manipulation

• 0367: Pose-graph SLAM Using Multi-order Ultrasonic Echoes and Beamforming for Long-range Inspection Robots

• 0387: DS-K3DOM: 3-D Dynamic Occupancy Mapping with Kernel Inference and Dempster-Shafer Evidential Theor

• 0394: Direct LiDAR-Inertial Odometry: Lightweight LIO with Continuous-Time Motion Correction

• 0425: Learning Augmented, Multi-Robot Long-Horizon Navigation in Partially Mapped Environments

• 0431: Multi-Object Navigation in real environments using hybrid policies

• 0434: Frontier Semantic Exploration for Visual Target Navigation

• 0437: CamMap: Extrinsic Calibration of Non-Overlapping Cameras Based on SLAM Map Alignment

• 0455: Hybrid Visual SLAM for Underwater Vehicle Manipulator Systems

• 0457: Data-driven Loop Closure Detection in Bathymetric Point Clouds for Underwater SLAM

• 0490: Conditional GANs for Sonar Image Filtering with Applications to Underwater Occupancy Mapping

• 0495: FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback

• 0503: Real-Time Dense 3D Mapping of Underwater Environments

• 0507: iMODE:Real-Time Incremental Monocular Dense Mapping Using Neural Field

• 0512: Lighthouses and Global Graph Stabilization: Active SLAM for Low-compute, Narrow-FoV Robots

• 0516: Convolutional Bayesian Kernel Inference for 3D Semantic Mapping

• 0542: Zero-Shot Object Goal Visual Navigation

• 0550: Learning to View: Decision Transformers for Active Object Detection

• 0551: ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation

• 0552：Informable Multi-Objective and Multi-Directional RRT∗ System for Robot Path Planning

• 0553：Online Visual SLAM Adaptation against Catastrophic Forgetting with Cycle-Consistent Contrastive Learning

• 0569：The SLAM Hive Benchmarking Suite

• 0587：EdgeVO: An Effcient and Accurate Edge-based Visual Odometry

• 0589：WOLF: A modular estimation framework for robotics based on factor graphs

• 0610：GMM Registration: a Probabilistic scan matching approach for sonar-based AUV navigation

• 0614：General, Single-shot, Target-less, and Automatic LiDAR-Camera Extrinsic Calibration Toolbox

• 0645：Swarm-LIO: Decentralized Swarm LiDAR-inertial Odometry

• 0649：RoboSC: a domain-specific language for supervisory controller synthesis of ROS applications

• 0673：Non-Minimal Solvers for Relative Pose Estimation with a Known Relative Rotation Angle

• 0685：Enforcing safety for vision-based controllers via Control Barrier Functions and Neural Radiance Fields

• 0697：WAVN: Wide Area Visual Navigation for Large-scale, GPS-denied Environments

• 0701：STD: Stable Triangle Descriptor for 3D place recognition

• 0702：ARiADNE: A Reinforcement learning approach using Attention-based Deep Networks for Exploration

• 0790：Factor Graph Fusion of Raw GNSS Sensing with IMU and Lidar for Precise Robot Localization without a Base Station

• 0820：Neural Implicit Surface Reconstruction using Imaging Sonar

• 0833：NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields

• 0884：SCORE: A Second-Order Conic Initialization for Range-Aided SLAM

• 0898：Scene-level Point Cloud Colorization with Semantics-and-geometry-aware Networks

• 0909：Stochastic Planning for ASV Navigation Using Satellite Images

• 0912：Efficient Visual-Inertial Navigation with Point-Plane Map

• 0918：PIEKF-VIWO: Visual-Inertial-Wheel Odometry using Partial Invariant Extended Kalman Filter

• 0921：Inverse Perspective Mapping-Based Neural Occupancy Grid Map for Visual Parking

• 0947：Continuous-Time LiDAR-Inertial-Vehicle Odometry Method with Lateral Acceleration Constraint

• 0952：Monocular Visual-Inertial Odometry with Planar Regularities

• 0963：Wild-Places: A Large-Scale Dataset for Lidar Place Recognition in Unstructured Natural Environments

• 0965：Multimodal Image Registration for GPS-denied UAV Navigation Based on Disentangled Representations

• 0981：SM/VIO: Robust Underwater State Estimation Switching Between Model-based and Visual Inertial Odometry

• 0982：Constraint Manifolds for Robotic Inference and Planning

• 1074：Descriptor Distillation for Efficient Multi-Robot SLAM

• 1107：Exploring Navigation Maps for Learning-Based Motion Prediction

• 1116：Global Localization in Repetitive and Ambiguous Environments

• 1197：Knowledge Distillation for Feature Extraction in Underwater VSLAM

• 1213：DAMS-LIO: A Degeneration-Aware and Modular Sensor-Fusion LiDAR-inertial Odometry

• 1267：Question Generation for Uncertainty Elimination in Referring Expressions in 3D Environments

• 1291：Robust Incremental Smoothing and Mapping (riSAM)

• 1309：Robust Map Fusion with Visual Attention Utilizing Multi-agent Rendezvous

• 1316：BAMF-SLAM: Bundle Adjusted Multi-Fisheye Visual-Inertial SLAM Using Recurrent Field Transforms

• 1331：Towards View-invariant and Accurate Loop Detection Based on Scene Graph

• 1343：DisCo: A Multiagent 3D Coordinate System for Lattice Based Modular Self-Reconfigurable Robots

• 1370：Detecting spatio-temporal Relations by Combining a Semantic Map with a Stream Processing Engine

• 1371：Monocular Simultaneous Localization and Mapping using Ground Textures

• 1380：Combining Motion and Appearance for Robust Probabilistic Object Segmentation in Real Time

• 1393：A Moving Target Tracking System of Quadrotors with Visual-Inertial Localization

• 1414：Efficient Planar Pose Estimation via UWB Measurements

• 1434：Online Consistent Video Depth with Gaussian Mixture Representation

• 1471：ASRO-DIO: Active Subspace Random Optimization based Depth Inertial Odometry

• 1524：Multi-Robot 3D Gas Distribution Mapping: Coordination, Information Sharing and Environmental Knowledge

• 1547：COVINS-G: A Generic Back-end for Collaborative Visual-Inertial SLAM

• 1550：kollagen: A Collaborative SLAM Pose Graph Generator

• 1638：Neural-Kalman GNSS/INS Navigation for Precision Agriculture

• 1664：FloorplanNet: Learning Topometric Floorplan Matching for Robot Localization

• 1671：A Probabilistic Framework for Visual Localization in Ambiguous Scenes

• 1679：Sensor Localization by Few Distance Measurements via the Intersection of Implicit Manifolds

• 1700：Portable Multi-Hypothesis Monte Carlo Localization for Mobile Robots

• 1704：Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation

• 1739：SRI-Graph: A Novel Scene-Robot Interaction Graph for Robust Scene Understanding

• 1767：Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding

• 1812：Active Metric-Semantic Mapping by Multiple Aerial Robots

• 1824：Loc-NeRF: Monte Carlo Localization using Neural Radiance Fields

• 1856：LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

• 1858：3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs

• 1861：CIOT: Constraint-Enhanced Inertial-Odometric Tracking for Articulated Dump Trucks in GNSS-Denied Mining Environments

• 1897：PredRecon: A Prediction-boosted Planning Framework for Fast and High-quality Autonomous Aerial Reconstruction

• 1906：Cross-Agent Relocalization for Decentralized Collaborative SLAM

• 1929：MOFT: Monocular odometry based on deep depth and careful feature selection and tracking

• 1949：Semantics-aware Exploration and Inspection Path Planning

• 1991：Autonomous Navigation in Unknown Environments With Sparse Bayesian Kernel-Based Occupancy Mapping

• 2013：FRAME: Fast and Robust Autonomous 3D point cloud Map-merging for Egocentric multi-robot exploration

• 2018：SEER: Safe Efficient Exploration for Aerial Robots using Learning to Predict Information Gain

• 2042：Adaptive Keyframe Generation based LiDAR Inertial Odometry for Complex Underground Environments

• 2090：Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference

• 2094：GUTS: Generalized Uncertainty-Aware Thompson Sampling for Multi-Agent Active Search

• 2149：Finding Things in the Unknown: Semantic Object-Centric Exploration with an MAV

• 2155：Efficient View Path Planning for Autonomous Implicit Reconstruction

• 2215：Multi-Agent Active Search using Detection and Location Uncertainty

• 2270：Robot Person Following Under Partial Occlusion

• 2280：From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds

• 2313：Sequence-Agnostic Multi-Object Navigation

• 2363：Learning to Explore Informative Trajectories and Samples for Embodied Perception

• 2369：Neural Grasp Distance Fields for Robot Manipulation

• 2375：Mono-STAR: Mono-camera Scene-level Tracking and Reconstruction

• 2398：Multi-Objective Ergodic Search for Dynamic Information Maps

• 2403：Large-Scale Radar Localization using Online Public Maps

• 2436：4DRadarSLAM: A 4D Imaging Radar SLAM System for Large-scale Environments based on Pose Graph Optimization

• 2437：Improving the Performance of Local Bundle Adjustment for Visual-Inertial SLAM with Efficient Use of GPU Resources

• 2512：The Reflectance Field Map: Mapping Glass and Specular Surfaces in Dynamic Environments

• 2526：SLAMER: Simultaneous Localization and Map-Assisted Environment Recognition

• 2627：Safe and Efficient Navigation in Extreme Environments using Semantic Belief Graphs

• 2635：Fast and Scalable Signal Inference for Active Robotic Source Seeking

• 2642：Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Field

• 2678：Visual Language Maps for Robot Navigation

• 2757：Efficient Bundle Adjustment for Coplanar Points and Lines

• 2767：GP-Frontier for Local Mapless Navigation

• 2822：Learning Continuous Control Policies for Information-Theoretic Active Perception

• 2910：SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations

• 2977：SLAMesh: Real-time LiDAR Simultaneous Localization and Meshing

• 3006：A System for Generalized 3D Multi-Object Search

• 3036：Probabilistic Plane Extraction and Modeling for Active Visual-Inertial Mapping

• 3039：GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF

• 3083：A real-time dynamic obstacle tracking and mapping system for UAV navigation and collision avoidance with an RGB-D camera

• 3088：DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments

• 3098：NOCaL: Calibration-Free Semi-Supervised Learning of Odometry and Camera Intrinsics

• 3123：Monocular Visual-Inertial Depth Estimation

• 3168：Effcient Implicit Neural Reconstruction Using LiDAR

• 3171：Real-Time Simultaneous Localization and Mapping with LiDAR Intensity

• 3185：Deep Unsupervised Visual Odometry Via Bundle Adjusted Pose Graph Optimization

• 3188：Data-Association-Free Landmark-based SLAM

• 3197：RoLM: Radar on LiDAR Map Localization

• 3206：Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types

• 3215：Memory-based Exploration-value Evaluation Model for Visual Navigation

• 3293：Mapping Waves with an Uncrewed Surface Vessel via Gaussian Process Regression

• 3320：RAMP: A Risk-Aware Mapping and Planning Pipeline for Fast Off-Road Ground Robot Navigation

• 3343：Object-aware Monocular Depth Prediction with Instance Convolutions

• 3507：Discrete-Continuous Smoothing and Mapping

• 3527：Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields

• 3560：UWB-VIO Fusion for Accurate and Robust Relative Localization of Round Robotic Teams

• 3595：Generalized LOAM: LiDAR Odometry Estimation with Trainable Local Geometric Features

• 3606: Point Cloud Change Detection With Stereo V-SLAM: Dataset, Metrics and Baseline

• 3615: BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM

• 3616: Deep IMU Bias Inference for Robust Visual-Inertial Odometry with Factor Graphs

• 3617: Sigma-FP: Robot Mapping of 3D Floor Plans with an RGB-D Camera under Uncertainty

• 3618: A Framework to Co-Optimize Robot Exploration and Task Planning in Unknown Environments

• 3640: Hilti-Oxford Dataset: A Millimeter-Accurate Benchmark for Simultaneous Localization and Mapping

• 3643: IC-GVINS: A Robust, Real-time, INS-Centric  GNSS-Visual-Inertial Navigation System

• 3652: Gaussian Mixture Midway-Merge for Object SLAM With Pose Ambiguity

• 3658: Improving Self-Consistency in Underwater Mapping through Laser-Based Loop Closure

• 3665: Picking Up Speed: Continuous-Time Lidar-Only Odometry using Doppler Velocity Measurements

• 3683: Wheel-SLAM: Simultaneous Localization and Terrain Mapping Using One Wheel-mounted IMU

• 3685: Long-Term Localization using Semantic Cues in Floor Plan Maps

• 3692: Fast and Versatile Feature-Based LiDAR Odometry via Efficient Local Quadratic Surface Approximation

• 3699: SOFT2: Stereo Visual Odometry for Road Vehicles based on a Point-to-Epipolar-Line Metric

• 3700: Self-Supervised Feature Learning for Long-Term Metric Visual Localization

• 3701: GraffMatch: Global Matching of 3D Lines and Planes for Wide Baseline LiDAR Registration

• 3702: maplab 2.0 – A Modular and Multi-Modal Mapping Framework

• 3709: Long-Term Visual SLAM With Bayesian Persistence Filter Based Global Map Prediction

—END—

---

高效学习3D视觉三部曲

第一步 加入行业交流群，保持技术的先进性

目前工坊已经建立了3D视觉方向多个社群，包括SLAM、工业3D视觉、自动驾驶方向，细分群包括：[工业方向]三维点云、结构光、机械臂、缺陷检测、三维测量、TOF、相机标定、综合群；[SLAM方向]多传感器融合、ORB-SLAM、激光SLAM、机器人导航、RTK|GPS|UWB等传感器交流群、SLAM综合讨论群；[自动驾驶方向]深度估计、Transformer、毫米波|激光雷达|视觉摄像头传感器讨论群、多传感器标定、自动驾驶综合群等。除了这些，还有求职、硬件选型、视觉产品落地等交流群。大家可以添加小助理微信: dddvisiona，备注：加群+方向+学校|公司, 小助理会拉你入群。

添加小助理微信：dddvisiona, 拉你入群

第二步 加入知识星球，问题及时得到解答

针对3D视觉领域的视频课程（三维重建、三维点云、结构光、手眼标定、相机标定、激光/视觉SLAM、自动驾驶等）、源码分享、知识点汇总、入门进阶学习路线、最新paper分享、疑问解答等进行深耕，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、项目对接为一体的铁杆粉丝聚集区，6000+星球成员为创造更好的AI世界共同进步，知识星球入口：「3D视觉从入门到精通」

学习3D视觉核心技术，扫描查看，3天内无条件退款

高质量教程资料、答疑解惑、助你高效解决问题

第三步 系统学习3D视觉，对模块知识体系，深刻理解并实践

如果大家对3D视觉某一个细分方向想系统学习[从理论、代码到实战],推荐3D视觉精品课程学习网址：www.3dcver.com

工业3D视觉方向课程：

[1]机械臂抓取从入门到实战课程（理论+源码）

[2]从零搭建一套结构光3D重建系统理论+源码+实践

[3]三维点云处理：算法与实战汇总

[4]彻底搞懂基于Open3D的点云处理教程！

[5]3D视觉缺陷检测教程：理论与实战！

[6]如何学习相机模型与标定？（代码+实战）

SLAM方向课程:

[1]彻底剖析激光-视觉-IMU-GPS融合SLAM算法：理论推导、代码讲解和实战

[2]（第二期）彻底搞懂基于LOAM框架的3D激光SLAM：源码剖析到算法优化

[3]彻底搞懂视觉-惯性SLAM：VINS-Fusion原理精讲与源码剖析

[4]彻底剖析室内、室外激光SLAM关键算法和实战(cartographer+LOAM+LIO-SAM)

[5]ORB-SLAM3理论讲解与代码精析（第2期）

[6]ROS2从入门到精通：理论与实战

视觉三维重建

[1]彻底搞透视觉三维重建：原理剖析、代码讲解、及优化改进)

自动驾驶方向课程：

[1]单目深度估计方法：算法梳理与代码实现

[2]面向自动驾驶领域的3D点云目标检测全栈学习路线！(单模态+多模态/数据+代码)

[3]如何将深度学习模型部署到实际工程中？（分类+检测+分割）