A collection of GICP-based fast point cloud registration algorithms

Efficient and parallel algorithms for point cloud registration [C++, Python]

Point cloud registration pipeline for robot localization and 3D perception

Multi-threaded and SSE friendly NDT algorithm

K-Closest Points and Maximum Clique Pruning for Efficient and Effective 3-D Laser Scan Matching (RA-L 2022)

Laser scan matcher ported to ROS2

ROS package for NDT-PSO, a 2D Laser scan matching algorithm for SLAM

Globally localise your 2D LIDAR in a 2D map in no time [IROS'24]

Obtain robust odometry from your noisy panoramic 2D LIDAR [IROS'22]

The Fourier Scan Matcher: a correspondenceless and closed-form matching algorithm for range scans of 2D panoramic LIDAR sensors

This repository contains solution for SLAM lectures taught by Claus Brenner on YouTube.

Simple 2D point-to-point scan matcher implemented in Python. Works with ROS1.

[ROS package] Lidar odometry from panoramic 2D range scans. Method: scan-matching without using correspondences, based on properties of the Discrete Fourier Transform

LiDAR Odometry with Scan Matching

Simple scan matcher based on the paper Real-Time Correlative Scan Matching by Olson 2009

Self-Driving Car Engineer Nanodegree program, Course 4 - Localization Project

Implementation of Fast Spectral Scan Matching (F-SSM) and SVM-based place recognition for coarse-to-fine global localization of a mobile robot, based on Park & Roh (2016). Built and tested in the NEU Racing Gymnasium environment using 2D lidar scan data.

Implemented the Iterative Closest Point (ICP) algorithm, and used it to estimate the rigid transformation that optimally aligns two 3D point clouds