VINS-Fusion
- Software
- Navigation and mapping
- Library
VINS-Fusion is an optimization-based multi-sensor state estimator for self-localization of drones, cars, and AR/VR devices. It extends VINS-Mono to several camera and IMU setups.
- Stale
Made by HKUST Aerial Robotics Group, Hong Kong SAR China (checked on github.com/HKUST-Aerial-Robotics (opens in a new tab)).
Source on GitHub: github.com/HKUST-Aerial-Robotics/VINS-Fusion (opens in a new tab). Facts read at commit be55a93 (opens in a new tab).
Licenses
- Code
- GPL-3.0-only (opens in a new tab)
Read by Robotheca from LICENCE (opens in a new tab) (GPL-3.0-only) at commit be55a93 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
Copyleft: Modified source must be published.
Labels
- StaleNo commit in 12 months: the newest is from 26 Jul 2021.
What it does
- Supports stereo cameras, mono camera plus IMU, and stereo cameras plus IMU.
- Performs online spatial calibration between the camera and the IMU.
- Performs online temporal calibration of the time offset between camera and IMU.
- Includes visual loop closure to correct drift over long trajectories.
- Can fuse visual-inertial odometry with GPS as a toy example.
- Ships example configurations and runs for EuRoC, KITTI odometry, KITTI GPS fusion, and a car bag file.
Written by Robotheca from the project's README (opens in a new tab) at commit be55a93.
Getting started
- Difficulty
- Advanced
- Hardware it needs, as the project states it
- Ubuntu 64-bit 16.04 or 18.04 with ROS Kinetic or Melodic, plus Ceres Solver.
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 26 Jul 2021 on master
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.