# HKUST-Aerial-Robotics/GVINS

Tightly coupled GNSS-Visual-Inertial system for locally smooth and globally consistent state estimation in complex environment.

Repository: https://github.com/HKUST-Aerial-Robotics/GVINS
Canonical: https://ross.abutalabs.com/products/gvins
Language: C++
License: GPL-3.0
License Family: copyleft
Topics: sensor-fusion, estimation-algorithm, slam, gnss, localization
Last push: 2021-09-11T10:55:25+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1987, "days_push": 1817, "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 1155, forks 274 (observed 2026-08-28T04:03:47.823268+00:00)

## What it is
GVINS is a C++/ROS nonlinear optimization system that tightly fuses GNSS raw measurements (pseudorange and Doppler) with visual and inertial data for real-time, drift-free 6-DoF global localization. It extends VINS-Mono with multi-constellation GNSS support and works even in GNSS-denied areas.

## Use cases
- fuse GNSS with camera and IMU for global localization
- drift-free 6-DoF state estimation for drones
- localize robots in GNSS-denied environments
- multi-constellation GNSS-visual-inertial odometry
- smooth and globally consistent SLAM in complex environments
- estimate poses in ECEF frame from raw GNSS measurements

## When to choose
- you need globally consistent localization combining GNSS raw data with VIO
- you work with ROS and have raw GNSS receiver measurements (e.g., u-blox F9P)
- you need localization that survives GNSS-denied areas
- you want multi-constellation GNSS support (GPS, GLONASS, Galileo, BeiDou)

## When to avoid
- you only need GPS coordinates without visual-inertial fusion
- you need a maintained project with recent releases
- you cannot use ROS or Linux
- you need a permissive license (GPL-3.0)

## Facets
- artifact type: library
- maturity: maintenance
- function: robotics, simulation, nlp
- domain: robotics, autonomous-vehicles
- platform: cpp
- tags: slam, gnss, sensor-fusion, visual-inertial-odometry, state-estimation, localization, ros, ceres-solver, algorithms, linux

## Member repositories
- HKUST-Aerial-Robotics/GVINS (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:47.823268+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 2026-08-30T06:32:10.763212+00:00, confidence not recorded.
  - readme: https://github.com/HKUST-Aerial-Robotics/GVINS (fetched 2026-08-28T04:03:47.823268+00:00, sha 5fd2d57c63b0)
- Data as of 2026-08-30T08:39:29.467469+00:00.