Miguel A. Vega Torres's Projects
Advanced implementation of LOAM
AdpInEKF for 3D point cloud localization, in which the points of a 3D point cloud set are directly used to measurements to update the predicted state, and any registration algorithms can be employed to data association process.
The ultimate list of open data semantic city models
Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.
Direct LiDAR Odometry: Fast Localization with Dense Point Clouds
DLL: Direct Lidar Localization
Python package for the evaluation of odometry and SLAM
The tight integration of FAST-LIO with Radius-Search-based loop closure module.
LiDAR SLAM = FAST-LIO + Scan Context
ROS package for frontier exploration based on wavefront frontier detection
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
Save LiDAR scan data from a bag file at a specific rate or timestamp.
A framework of lidar mapping and localization with strong extensibility
The official repository for paper "LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition" To appear in 2022 IEEE International Conference on Robotics and Automation (ICRA) https://arxiv.org/abs/2109.08336
A Modular Framework for LiDAR-based Lifelong Mapping
Generate session data to enable rapid place recognition using a 3D point cloud or BIM model.
An open visual-inertial mapping framework.
Config files for my GitHub profile.
Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)
learning and feeling SLAM together with hands-on-experiments
A Modular Optimization framework for Localization and mApping (MOLA)
Multi-threaded and SSE friendly NDT algorithm
Robust BIM-based 2D-LiDAR Localization for Lifelong Indoor Navigation in Changing and Dynamic Environments
[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465