# KumarRobotics/msckf_vio

Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight

Repository: https://github.com/KumarRobotics/msckf_vio
Canonical: https://ross.abutalabs.com/products/msckf_vio
Language: C++
License: NOASSERTION
License Family: other
Topics: visual-inertial-odometry, stereo-vision, ros
Last push: 2023-11-22T09:11:28+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": 3198, "days_push": 1015, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1969, forks 612 (observed 2026-08-28T04:06:00.732803+00:00)

## What it is
A stereo visual-inertial odometry package implementing the Multi-State Constraint Kalman Filter (MSCKF) in C++ on ROS. It fuses synchronized stereo images and IMU data to produce real-time 6DOF pose estimation, designed for fast autonomous drone flight.

## Use cases
- estimate 6DOF camera/IMU pose from stereo video and IMU data
- visual odometry for drone autonomous flight
- run VIO on the EuRoC dataset
- real-time state estimation for a quadrotor without GPS
- fuse stereo cameras and IMU with a Kalman filter
- benchmark VIO algorithms on fast-flight datasets

## When to choose
- you need proven, real-time stereo VIO on ROS with a well-cited MSCKF implementation
- your robot has hardware-synchronized stereo cameras and an IMU
- you want GPS-denied pose estimation for fast-moving aerial vehicles
- you have Kalibr calibration files for your camera-IMU rig

## When to avoid
- you need monocular-only VIO or visual SLAM with loop closure and mapping
- you are not using ROS or cannot build a catkin package
- you need support for modern ROS 2 or recent Ubuntu versions out of the box
- your cameras and IMU are not hardware synchronized and you cannot calibrate them

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, robotics, simulation
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp
- tags: visual-inertial-odometry, stereo-vision, msckf, ros, slam, state-estimation, drones, kalman-filter, linux

## Member repositories
- KumarRobotics/msckf_vio (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:00.732803+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 2026-08-30T03:05:08.921286+00:00, confidence not recorded.
  - readme: https://github.com/KumarRobotics/msckf_vio (fetched 2026-08-28T04:06:00.732803+00:00, sha 2eacc0816a54)
- Data as of 2026-08-30T08:39:29.467469+00:00.