3.8 Proceedings Paper

PaGO-LOAM: Robust Ground-Optimized LiDAR Odometry

Related references

Note: Only part of the references are listed.
Article Computer Science, Information Systems

G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments

Seungwon Song et al.

Summary: This paper proposes a generalized grouping and pruning method for RGB-D SLAM in low-dynamic environments. The traditional methods have limitations in rejecting dynamic objects, but our proposed method selectively removes false constraints, improving the accuracy of PGO.

IEEE ACCESS (2022)

Article Robotics

Patchwork: Concentric Zone-Based Region-Wise Ground Segmentation With Ground Likelihood Estimation Using a 3D LiDAR Sensor

Hyungtae Lim et al.

Summary: The letter introduces a novel ground segmentation method called Patchwork, which efficiently addresses the issue of uneven ground and significantly reduces false positives, while demonstrating a faster processing speed compared to existing methods based on plane fitting.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Robotics

ERASOR: Egocentric Ratio of Pseudo Occupancy-Based Dynamic Object Removal for Static 3D Point Cloud Map Building

Hyungtae Lim et al.

Summary: The letter introduces a novel static map building method called ERASOR, which is fast and robust to motion ambiguity. The approach focuses on the nature of dynamic objects in urban environments being inevitably in contact with the ground. By proposing the concept of pseudo occupancy and adopting Region-wise Ground Plane Fitting, static points can be distinguished from dynamic points effectively.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Robotics

FAST-LIO: A Fast, Robust LiDAR-Inertial Odometry Package by Tightly-Coupled Iterated Kalman Filter

Wei Xu et al.

Summary: This study introduces a computationally efficient and robust LiDAR-inertial odometry framework for reliable navigation in fast-motion, noisy, or cluttered environments. By presenting a new formula for computing the Kalman gain, the computation load is reduced in the presence of a large number of measurements. The proposed method has been tested in various indoor and outdoor environments, showing reliable real-time navigation results.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Proceedings Paper Automation & Control Systems

Avoiding Degeneracy for Monocular Visual SLAM with Point and Line Features

Hyunjun Lim et al.

Summary: This paper proposes a degeneracy avoidance method for a point and line based visual SLAM algorithm, effectively addressing the shortcomings of point features in low-texture and illuminance variant environments. By using line features to compensate for the weaknesses of point features, and introducing a novel structural constraint to avoid degeneracy problems.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Proceedings Paper Automation & Control Systems

MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square

Yue Pan et al.

Summary: MULLS is an efficient, low-drift, and versatile 3D LiDAR SLAM system that uses feature point extraction and multi-metric linear least square algorithm for frame-to-submap registration to keep the map updated and reduce error from dead reckoning through hierarchical pose graph optimization.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Proceedings Paper Automation & Control Systems

REAL: Rapid Exploration with Active Loop-Closing toward Large-Scale 3D Mapping using UAVs

Eungchang Mason Lee et al.

Summary: The proposed method in this paper combines pre-calculated Peacock Trajectory with graph-based global exploration and active loop-closing to rapidly and accurately explore and map unknown large-scale environments. By considering kinodynamics of UAVs and utilizing both local and global exploration, the method ensures obstacle avoidance and minimizes unnecessary revisiting, improving pose estimation performance. The performance of the proposed method is verified in 3D simulation environments and validated in a real-world experiment.

2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2021)

Proceedings Paper Automation & Control Systems

Floorplan-based Localization and Map Update Using LiDAR Sensor

Seungwon Song et al.

Summary: This paper introduces a novel localization and map update method for indoor use, utilizing LIDAR sensor and floorplan. By extracting ceiling parts and lines from the border of these parts, and employing Monte Carlo Localization algorithm for estimation, the proposed method achieves accurate indoor localization and map update by comparing with floorplan lines.

2021 18TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS (UR) (2021)

Proceedings Paper Automation & Control Systems

MSDPN: Monocular Depth Prediction with Partial Laser Observation using Multi-stage Neural Networks

Hyungtae Lim et al.

2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2020)

Proceedings Paper Automation & Control Systems

Normal Distributions Transform is Enough: Real-time 3D Scan Matching for Pose correction of Mobile Robot Under Large Odometry Uncertainties

Hyungtae Lim et al.

2020 20TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS) (2020)

Article Computer Science, Information Systems

GP-ICP: Ground Plane ICP for Mobile Robots

Hyungjin Kim et al.

IEEE ACCESS (2019)

Proceedings Paper Robotics

Drivable Road Detection with 3D Point Clouds Based on the MRF for Intelligent Vehicle

Jaemin Byun et al.

FIELD AND SERVICE ROBOTICS (2015)

Proceedings Paper Computer Science, Artificial Intelligence

Ground Segmentation based on Loopy Belief Propagation for Sparse 3D Point Clouds

Mingfang Zhang et al.

2015 INTERNATIONAL CONFERENCE ON 3D VISION (2015)

Article Geography, Physical

Ground and building extraction from LiDAR data based on differential morphological profiles and locally fitted surfaces

Domen Mongus et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2014)

Article Computer Science, Artificial Intelligence

Comparing ICP variants on real-world data sets

Francois Pomerleau et al.

AUTONOMOUS ROBOTS (2013)

Article Robotics

Vision meets robotics: The KITTI dataset

A. Geiger et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2013)

Article Computer Science, Artificial Intelligence

1-Point-RANSAC Structure from Motion for Vehicle-Mounted Cameras by Exploiting Non-holonomic Constraints

Davide Scaramuzza

INTERNATIONAL JOURNAL OF COMPUTER VISION (2011)