Inside lidar_localization_ros2: NDT map matching plus RKO-LIO odometry, BSD-licensed on GitHub
rsasaki0109 · x · 2026-11-18
The author shared the GitHub repo behind his 600-star project lidarlocalizationros2 with fuller technical detail.
It does map-based 3D LiDAR localization for ROS 2 and Nav2 (not SLAM): per-scan NDT matching against a prior point-cloud map, with RKO-LIO odometry predicting inter-scan motion, staying robust even when scans mismatch the map or leave it entirely. Tested handheld with a Livox MID-360 over 390 m outdoors. The repo has 577 commits, Docker setup, CI workflows, a BSD-2-Clause license, and includes an AGENTS.md.
Related event: Open-source ROS 2 3D LiDAR Localization Project Hits 600 Stars(2 posts)→
More from Embodied
- NVIDIA-backed Agile ONE SN humanoid robot for researchers ships early 2027 — xmercury_one · 2026-11-18
- Peking University Open-Sources PanDWM, a 360° 4D Driving World Model Beating DiST-4D — PekingUniversity · 2026-11-18
- Humanoids serve ice cream and spar in Shenzhen while APEC leaders visit — TansuYegen · 2026-11-18
- Otto by Rockwell explains using Gazebo digital twins for AMR deployments — ___Mufasaa · 2026-11-18
- Tokkey debuts thumb-sized AI hardware to run local models on your Mac — TejasKumar_ · 2026-11-18
- 'Nothing more physical AI than moving tons of rock': live demo at Web Summit shows real-world difficulty — MarvinTBaumann · 2026-11-18