# rpng/open_vins

An open source platform for visual-inertial navigation research.

Repository: https://github.com/rpng/open_vins
Canonical: https://ross.abutalabs.com/products/open_vins
Homepage: https://docs.openvins.com
Language: C++
License: GPL-3.0
License Family: copyleft
Topics: visual-inertial-odometry, slam, msckf, sensor-calibration, ekf-localization, research-platform, open-vins, vio, robotics
Last push: 2025-11-30T08:23:17+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 54, release rhythm 8, longevity 100
- inputs: {"age_days": 2785, "days_push": 276, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_readme
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3057, forks 917 (observed 2026-08-28T04:07:39.795686+00:00)

## What it is
OpenVINS is an open-source C++ platform for visual-inertial navigation research, centered on a filter-based (MSCKF/EKF) estimator that fuses inertial measurements with sparse visual feature tracks. It includes a core computer vision library, a multi-sensor simulator, evaluation tooling, and runs with ROS1/ROS2, ROS-free, or in Docker.

## Use cases
- run visual-inertial odometry on a camera and IMU dataset
- estimate camera and IMU trajectory with an EKF-based VIO system
- calibrate a visual-inertial sensor rig
- simulate synthetic IMU and camera measurements for research
- evaluate and plot VIO estimation results for a paper
- build a SLAM or state-estimation prototype on top of a modular filter framework

## When to choose
- you need a state-of-the-art filter-based (MSCKF) visual-inertial odometry estimator
- you are doing robotics or navigation research and want modular, well-documented code
- you want ROS1/ROS2, ROS-free, or Docker deployment options
- you need sensor calibration, simulation, and evaluation tooling in one platform

## When to avoid
- you need a full SLAM system with loop closure and persistent mapping
- you require a permissively licensed library (it is GPL-3.0)
- you want an optimization-based (graph) VIO backend rather than a filter
- you need a plug-and-play production solution with no C++ or robotics background

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, simulation, testing, math
- domain: robotics, computer-vision, autonomous-vehicles
- platform: cpp, cross-platform
- tags: visual-inertial-odometry, slam, msckf, ekf, sensor-fusion, state-estimation, ros, research-platform, sensor-calibration, algorithms, linux, docker

## Member repositories
- rpng/open_vins (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:39.795686+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 2026-08-30T07:28:49.141379+00:00, confidence not recorded.
  - homepage: https://docs.openvins.com (fetched 2026-08-29T09:43:46.759353+00:00, sha 6ac90c6b9df1)
  - site_page: https://docs.openvins.com/getting-started.html (fetched 2026-08-29T09:43:46.762285+00:00, sha fd1b5d196399)
- Data as of 2026-08-30T08:39:29.467469+00:00.