koide3/hdl_localization

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1019 stars · 333 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A ROS package for real-time 3D localization using 3D LIDARs such as Velodyne HDL32e and VLP16. It performs UKF-based pose estimation with IMU prediction and multi-threaded NDT scan matching against a global map point cloud.

Use cases

• localize a robot in real time using a 3D lidar
• estimate sensor pose from velodyne point clouds and IMU
• perform NDT scan matching against a prebuilt 3D map
• get odometry for a ROS-based mobile robot
• relocalize a robot on a known map
• align live point clouds with a global map

When to choose

• you need map-based real-time lidar localization in a ROS1 pipeline
• you have a Velodyne-style 3D lidar with built-in IMU
• you want UKF pose estimation corrected by scan matching
• you need CUDA-accelerated NDT on GPU hardware

When to avoid

• you need a ROS2 package (this targets ROS1/catkin)
• you want full SLAM/mapping rather than localization against an existing map
• you have no 3D lidar or point cloud map
• you need a maintained actively developed solution - the author recommends GLIM/GLIL instead

Facets

library · maturity maintenance

robotics computer-vision monitoring robotics autonomous-vehicles computer-vision cpp lidar localization ros kalman-filter ndt-scan-matching velodyne point-cloud slam linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="koide3/hdl_localization")