# HKUST-Aerial-Robotics/VINS-Fusion

An optimization-based multi-sensor state estimator

Repository: https://github.com/HKUST-Aerial-Robotics/VINS-Fusion
Canonical: https://ross.abutalabs.com/products/vins-fusion
Language: C++
License: GPL-3.0
License Family: copyleft
Last push: 2024-05-23T09:17:03+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": 2792, "days_push": 832, "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 4684, forks 1621 (observed 2026-08-28T04:08:56.950305+00:00)

## What it is
VINS-Fusion is an optimization-based multi-sensor state estimator for accurate self-localization in autonomous applications such as drones, cars, and AR/VR. It extends VINS-Mono to support mono camera + IMU, stereo cameras + IMU, stereo-only setups, and GPS fusion, with online spatial/temporal calibration and visual loop closure.

## Use cases
- estimate drone pose from camera and IMU data
- run visual-inertial odometry on stereo camera feeds
- fuse GPS with visual-inertial localization
- perform visual loop closure detection for SLAM
- calibrate camera-IMU extrinsics and time offset online
- benchmark odometry on the KITTI dataset
- localize an autonomous car without GPS

## When to choose
- you need a proven, well-cited visual-inertial odometry/SLAM estimator in C++ with ROS support
- you want flexible sensor configurations including stereo-only or GPS fusion
- you need online camera-IMU spatial and temporal calibration
- you are doing academic research on aerial robotics or autonomous driving localization

## When to avoid
- you need a maintained project with frequent updates and modern ROS 2 support
- you want a plug-and-play solution without building against ROS and Ceres Solver
- your platform is not Linux/ROS-based
- you need licensing more permissive than GPL-3.0

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, simulation, robotics
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp
- tags: visual-inertial-odometry, slam, sensor-fusion, state-estimation, ros, gps-fusion, loop-closure, drones, algorithms, linux

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:56.950305+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 2026-08-29T18:19:17.988504+00:00, confidence not recorded.
  - readme: https://github.com/HKUST-Aerial-Robotics/VINS-Fusion (fetched 2026-08-28T04:08:56.950305+00:00, sha c6b042d1e384)
- Data as of 2026-08-30T08:39:29.467469+00:00.