Skip to content
RobothecaBeta
Log in

Kimera-VIO

  • Software
  • Navigation and mapping
  • Library

Kimera-VIO is a visual-inertial odometry pipeline that estimates a robot's state from stereo camera and IMU data, with an optional monocular mode. It is built for accurate real-time localization.

  • Stale

Made by MIT-SPARK, United States (checked on github.com/MIT-SPARK/Kimera-VIO/blob/HEAD/LICENSE.BSD (opens in a new tab)).

Source on GitHub: github.com/MIT-SPARK/Kimera-VIO (opens in a new tab). Facts read at commit ce8c59b (opens in a new tab).

Licenses

Code
BSD-2-Clause (opens in a new tab)

Read by Robotheca from LICENSE.BSD (opens in a new tab) (BSD-2-Clause) at commit ce8c59b (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

Labels

  • StaleNo commit in 12 months: the newest is from 10 Feb 2025.

What it does

  • Estimates state from stereo cameras plus an IMU; can optionally use a single camera plus IMU instead.
  • Includes an optional loop-closure detection module (LoopClosureDetector and PGO), disabled by default.
  • Can be run on the Euroc dataset via a bash script, or through a ROS wrapper called Kimera-VIO-ROS.
  • Supports pinhole and omni camera models, configured through YAML parameter files and gflags.
  • Offers an optional VIO mode that uses structural regularities, described in the authors' ICRA 2019 paper.
  • Includes a gtest unit test suite and produces per-module timing and queue statistics when run.

Written by Robotheca from the project's README (opens in a new tab) at commit ce8c59b.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
Tested on Ubuntu 20.04. Requires GTSAM >= 4.1, OpenCV >= 3.4, OpenGV, Glog, Gflags, DBoW2, Kimera-RPGO and ANMS.

Maintenance

Status
Stale: no commit in 12 months
Newest commit
10 Feb 2025 on master
Latest release
Modular Pipelining (28 Dec 2019)

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.