# koide3/hdl_graph_slam

3D LIDAR-based Graph SLAM

Repository: https://github.com/koide3/hdl_graph_slam
Canonical: https://ross.abutalabs.com/products/hdl_graph_slam
Language: C++
License: BSD-2-Clause
License Family: permissive
Topics: ros, slam, lidar, velodyne, hdl-graph-slam, point-cloud, rslidar
Last push: 2024-07-16T01:39:14+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3166, "days_push": 779, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2332, forks 747 (observed 2026-08-28T04:06:37.794160+00:00)

## What it is
hdl_graph_slam is an open-source ROS package for real-time 6DOF SLAM using 3D LIDAR, based on graph SLAM with NDT scan matching odometry and loop detection. It supports GPS, IMU, and floor plane constraints and has been tested with Velodyne and RoboSense sensors.

## Use cases
- build 3D maps from lidar data in real time
- estimate robot trajectory with 3D lidar odometry
- perform loop closure detection and pose graph optimization
- fuse GPS and IMU constraints with lidar SLAM
- map indoor and outdoor environments with a Velodyne or RoboSense sensor
- detect floor planes from point clouds to constrain SLAM

## When to choose
- you need real-time 6DOF SLAM from a 3D lidar in a ROS1 (melodic/noetic) pipeline
- you want to combine lidar scan matching with GPS, IMU, or floor plane constraints
- you are working with Velodyne HDL32e/VLP16 or RoboSense 16-channel sensors

## When to avoid
- you are starting a new project - the successor package glim is recommended
- you need ROS2 support out of the box
- you only have a camera or 2D lidar instead of a 3D lidar

## Facets
- artifact type: library
- maturity: maintenance
- function: simulation, computer-vision, robotics
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp
- tags: slam, lidar, point-cloud, ros, graph-slam, ndt-scan-matching, loop-closure, velodyne, mapping, linux

## Member repositories
- koide3/hdl_graph_slam (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.794160+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:37:56.987142+00:00, confidence not recorded.
  - readme: https://github.com/koide3/hdl_graph_slam (fetched 2026-08-28T04:06:37.794160+00:00, sha 4bfd685af8d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.