# HViktorTsoi/FAST_LIO_LOCALIZATION

A simple localization framework that can re-localize in built maps based on FAST-LIO.

Repository: https://github.com/HViktorTsoi/FAST_LIO_LOCALIZATION
Canonical: https://ross.abutalabs.com/products/fast_lio_localization
Language: C++
License: GPL-2.0
License Family: copyleft
Topics: localization, lidar-odometry, livox-lidar
Last push: 2023-05-20T19:10:48+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": 1851, "days_push": 1201, "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 1048, forks 213 (observed 2026-08-28T04:03:22.335092+00:00)

## What it is
A ROS-based localization framework that re-localizes a robot in a pre-built 3D point cloud map by fusing FAST-LIO lidar odometry with low-frequency global localization. It eliminates odometry drift and supports initial pose estimation via RVIZ or external sensors.

## Use cases
- localize a robot in a pre-built lidar point cloud map
- eliminate accumulated odometry drift from FAST-LIO
- run realtime 3D global localization with Livox lidar
- re-localize in maps built with LIO-SAM or FAST-LIO-SLAM
- fuse low-frequency global localization with high-frequency lidar odometry
- provide initial pose manually in RVIZ or from another sensor

## When to choose
- you already use FAST-LIO and need map-based localization
- you have a pre-built point cloud map from LIO-SAM or FAST-LIO-SLAM
- you need computationally efficient realtime localization with Livox lidar
- your robot runs ROS on Linux

## When to avoid
- you need a full SLAM system to build maps from scratch
- you don't use ROS or Livox-style lidar
- you need visual (camera-based) localization
- you need active maintenance or recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: robotics, computer-vision, simulation
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp, python
- tags: lidar-localization, fast-lio, ros, point-cloud-map, slam, livox-lidar, odometry, linux

## Member repositories
- HViktorTsoi/FAST_LIO_LOCALIZATION (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.335092+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 2026-08-30T07:00:34.861365+00:00, confidence not recorded.
  - readme: https://github.com/HViktorTsoi/FAST_LIO_LOCALIZATION (fetched 2026-08-28T04:03:22.335092+00:00, sha 326e80c1521e)
- Data as of 2026-08-30T08:39:29.467469+00:00.