【泡泡前沿追踪】跟踪SLAM前沿动态系列之IROS2018

跟踪SLAM前沿动态系列之IROS2018

本文中提及的文章，均已上传至百度云盘中，点击 阅读原文 即可获取

VIO

1.A Tutorial on Quantitative Trajectory Evaluation for Visual(-Inertial) Odometry

(https://github.com/uzh-rpg/rpg_trajectory_evaluation)

2.Challenges in Monocular Visual Odometry Photometric Calibration, Motion Bias and Rolling Shutter Effect

3.CVI-SLAM – Collaborative Visual-Inertial SLAM

4.Embedding Temporally Consistent Depth Recovery for Real-time Dense Mapping in Visual-inertial Odometry

5.Hybrid Contact Preintegration for Visual-Inertial-Contact State Estimation Using Factor Graphs

(https://youtu.be/WDPhdl5g2MQ)

6.Information Sparsification in Visual-Inertial Odometry

7.Key-Frame Strategy During Fast Image-Scale Changes and Zero Motion in VIO Without Persistent Features

8.On the Comparison of Gauge Freedom Handling in Optimization-based Visual-Inertial State Estimation

9.Online Temporal Calibration for Monocular Visual-Inertial Systems

(https://github.com/HKUST-Aerial-Robotics/VINS-Mono)

10.Real-Time Fully Incremental Scene Understanding on Mobile Platforms

11.The TUM VI Benchmark for Evaluating Visual-Inertial Odometry

(https://vision.in.tum.de/data/datasets/visual-inertial-dataset)

12.Trifo-VIO Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines

13.π-SoC Heterogeneous SoC Architecture for Visual Inertial SLAM Applications

14.Robocentric Visual-Inertial Odometry

15.Robust Visual-Inertial State Estimation with Multiple Odometries and Efficient Mapping on an MAV with Ultra-Wide FOV Stereo Vision

16.Unscented Kalman Filter on Lie Groups for Visual_Inertial Odometry

RGBD

1.Perception Based Locomotion System for a Humanoid Robot with Adaptive Footstep Compensation under Task Constraints

2.Real-time 3D Reconstruction Using a Combination of Point-based and Volumetric Fusion

3.Edge-based Robust RGB-D Visual Odometry_Using 2-D Edge Divergence Minimization

Lidar

1.A Maximum Likelihood Approach to Extract Polylines from 2-D Laser Range Scans

(https://github.com/acschaefer/ple)

2.A robust pose graph approach for city scale LiDAR mapping

3.Dynamic Scaling Factors of Covariances for Accurate 3D Normal Distributions Transform Registration

4.Integrating Deep Semantic Segmentation into 3D Point Cloud Registration

5.LIMO Lidar-Monocular Visual Odometry 

(The code is released to the community.)

6.LIPS LiDAR-Inertial 3D Plane SLAM 

(https://github.com/rpng/lips)

7.PoseMap Lifelong, Multi-Environment 3D LiDAR Localization

(https://youtu.be/BWxDRWdIpY)

(https://youtu.be/KSxuxDnfiko)

8.Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition

9.Stereo Camera Localization in 3D LiDAR Maps

10.LeGO-LOAM_ Lightweight and Ground-Optimized_Lidar Odometry and Mapping on Variable Terrain

(https://github.com/RobustFieldAutonomyLab/LeGO-LOAM)

11.LiDAR and Camera Calibration using Motions Estimated by Sensor_Fusion Odometry

12.Scan Context_ Egocentric Spatial Descriptor_for Place Recognition within 3D Point Cloud Map

Eventcamera

1.AsynchronousCornerDetectionandTrackingforEventCamerasinReal-Time

(https://youtu.be/bKUAZ7IQcf0)

Map

1.A B-spline Mapping Framework for Long-Term Autonomous Operations

2.C-blox A Scalable and Consistent TSDF-based Dense Mapping Approach

(https://github.com/ethz-asl/c-blox)

3.Efficient Long-term Mapping in Dynamic Environments

(https://gitlab.com/srrg-software/srrg mapper2d)

4.HMAPs – Hybrid Height-Voxel Maps for Environment Representation

5.Human-in-the-loop Augmented Mapping

6.Structured Skip List A Compact Data Structure for 3D Reconstruction

Slamsystem

1.ArthroSLAM multi-sensor robust visual localization for minimally invasive orthopedic surgery

2.DynaSLAM Tracking, Mapping and Inpainting in Dynamic Scenes

(https://youtu.be/EabI goFmQs)

3.Improving Repeatability of Experiments by Automatic Evaluation of SLAM Algorithms

(https://github.com/AIRLab-POLIMI/predictivebenchmarking)

4.Indoor Mapping and Localization for Pedestrians using Opportunistic Sensing with Smartphones

5.MIS-SLAM Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing

6.Omnidirectional DSO Direct Sparse Odometry with Fisheye Cameras

7.OpenSeqSLAM2.0 An Open Source Toolbox for Visual Place Recognition Under Changing Conditions

(http://tiny.cc/openseqslam2)

8.Probabilistic Dense Reconstruction from a Moving Camera

(https://github.com/ygling2008/probabilistic_mapping)

9.Robust Long-Term Registration of UAV Images of Crop Fields for Precision Agriculture

10.Semi-Supervised SLAM Leveraging Low-Cost Sensors on Underground Autonomous Vehicles for Position Tracking

11.Towards Robust Visual Odometry with a Multi-Camera System

(https://cvg.ethz.ch/research/visual-odometry/)

12.Fast Cylinder and Plane Extraction from Depth Cameras for Visual_Odometry

13.Geometric-based Line Segment Tracking for HDR Stereo Sequences

(https://github.com/rubengooj/StVO-PL)

14.Multimotion Visual Odometry (MVO)__Simultaneous Estimation of Camera and Third-Party Motions

15.Reliable fusion of black-box estimates of underwater localization

16.Stereo Visual Odometry and Semantics based Localization of Aerial_Robots in Indoor Environments

(https://vimeo.com/259349563)

Backend

1.LDSO Direct Sparse Odometry with Loop Closure

(https://vision.in.tum.de/research/vslam/ldso)

2.Predicting Objective Function Change in Pose-Graph Optimization

3.Scan Similarity-based Pose Graph Construction Method for Graph SLAM

4.Submap-based Pose-graph Visual SLAM A Robust Visual Exploration and Localization System

5.Virtual Occupancy Grid Map for Submap-based Pose Graph SLAM and Planning in 3D Environments

Frontend

1.A Combined RGB and Depth Descriptor for SLAM with Humanoids

(https://www.hrl.uni-bonn.de/research/DLab)

2.Good Feature Selection for Least Squares Pose Optimization in VOVSLAM

3.HBST A Hamming Distance embedding Binary Search Tree for Feature-based Visual Place Recognition

4.Keyframe-based Photometric Online Calibration and Color Correction

(https://www.ais.uni-bonn.de/videos/IROS_2018_

photometric_calibration)

5.Optimized Contrast Enhancements to Improve Robustness of Visual Tracking in a SLAM Relocalisation Context

6.Robust Camera Pose Estimation via Consensus on Ray Bundle and Vector Field

7.Unit Quaternion-based Parameterization for Point Features in Visual Navigatio

8.Perspective Correcting Visual Odometry for Agile MAVs using a_Pixel Processor Array

Deepslam

1.A Variational Feature Encoding Method of 3D Object for Probabilistic Semantic SLAM

2.Bayesian Information Recovery from CNN for Probabilistic Inference

3.DS-SLAM A Semantic Visual SLAM towards Dynamic Environments

4.Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation

5.Integrating Deep Semantic Segmentation into 3D Point Cloud Registration

6.Learning monocular visual odometry with dense 3D mapping from dense 3D flow

(https://youtu.be/Ccj1O7yndIk)

7.Localization of Classified Objects in SLAM using Nonparametric Statistics and Clustering

8.Pose Estimation and Map Formation with Spiking Neural Networks towards Neuromorphic SLAM

9.Robust Exploration with Multiple Hypothesis Data Association

10.Semantic Monocular SLAM for Highly Dynamic Environments

11.Unsupervised Odometry and Depth Learning for Endoscopic Capsule_Robots

(https://github.com/mpi/deepunsupervised-endovo)