Quadric Representations for LiDAR Odometry, Mapping and Localization

Article Robotics

MR-GMMapping: Communication Efficient Multi-Robot Mapping System via Gaussian Mixture Model

Haolin Dong et al.

Summary: Collaborative perception in unknown environments is critical for multi-robot systems. We propose MR-GMMapping, a mapping system that uses GMM submaps for relative localization to reduce data transmission and storage. Experimental results show improved precision in relative pose estimation and significant reduction in data transmission.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

添加到收藏夹

Article Robotics

Direct LiDAR Odometry: Fast Localization With Dense Point Clouds

Kenny Chen et al.

Summary: This letter presents a lightweight frontend LiDAR odometry solution for fast and accurate state estimation in perceptually-challenging environments. The solution prioritizes computational efficiency and utilizes dense point clouds and a novel keyframing system to provide accurate pose estimates.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

添加到收藏夹

Article Robotics

Efficient and Probabilistic Adaptive Voxel Mapping for Accurate Online LiDAR Odometry

Chongjian Yuan et al.

Summary: This study proposes an efficient and probabilistic adaptive voxel mapping method for LiDAR odometry. The method utilizes voxel maps to probabilistically represent the environment and accurately register new LiDAR scans, achieving high accuracy and efficiency compared to other state-of-the-art methods.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

添加到收藏夹

Article Automation & Control Systems

Onboard Sensors-Based Self-Localization for Autonomous Vehicle With Hierarchical Map

Chao Xia et al.

Summary: This article proposes a self-localization framework that does not rely on GPS or wireless signals, achieving centimeter-level localization accuracy. It is lightweight and suitable for embedded computing systems. Experimental results demonstrate its effectiveness and advantages compared to similar algorithms.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

添加到收藏夹

Proceedings Paper Automation & Control Systems

CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure

Pierre Dellenbach et al.

Summary: In this study, we propose a new real-time LiDAR-only odometry method called CT-ICP, which introduces combined continuity and discontinuity for improved scan matching accuracy and robustness. A complete SLAM system is built on top of this odometry, utilizing a fast pure LiDAR loop detection method for precise localization. Testing on multiple datasets demonstrates the stable and reliable performance of the proposed method.

2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022) (2022)

添加到收藏夹

Article Robotics

Efficient LiDAR Odometry for Autonomous Driving

Xin Zheng et al.

Summary: To address the challenges of traditional tree-based neighbor search and the inefficiency in dealing with ground points parallel to LiDAR beams, a novel efficient LiDAR odometry approach is proposed, utilizing both non-ground spherical range images and bird's-eye-view maps. Additionally, a range adaptive method is introduced to estimate the local surface normal robustly, and a fast and memory-efficient model update scheme is proposed to fuse points and their corresponding normals at different time-stamps. Extensive experiments on the KITTI odometry benchmark and UrbanLoco dataset show promising results, demonstrating the effectiveness of the approach.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Article Robotics

Globally Consistent 3D LiDAR Mapping With GPU-Accelerated GICP Matching Cost Factors

Kenji Koide et al.

Summary: The letter introduces a real-time 3D LiDAR mapping framework based on global matching cost minimization, which leverages GPU parallel processing to improve estimation accuracy of long trajectories by directly minimizing matching costs between frames over the entire map.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Article Robotics

BALM: Bundle Adjustment for Lidar Mapping

Zheng Liu et al.

Summary: The letter introduces a local Bundle Adjustment (BA) method for lidar SLAM, which effectively reduces drift and allows large-scale dense plane and edge features to be used. To speed up the optimization process, the method also introduces a novel adaptive voxelization method.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Proceedings Paper Automation & Control Systems

Range Image-based LiDAR Localization for Autonomous Vehicles

Xieyuanli Chen et al.

Summary: In this paper, range images from 3D LiDAR scans are utilized for accurate localization in large-scale outdoor environments. The proposed observation model integrated into a Monte Carlo localization framework achieves better performance and generalization ability in tracking vehicle pose online at the LiDAR sensor frame rate across different environments.

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

添加到收藏夹

Proceedings Paper Automation & Control Systems