Skip to content


Folders and files

Last commit message
Last commit date

Latest commit



8 Commits

Repository files navigation


Simple But Effective Redundant Odometry for Autonomous Vehicles

Authors: Andrzej Reinke, Xieyuanli Chen, Cyrill Stachniss

Related Papers

  • Simple But Effective Redundant Odometry for Autonomous Vehicles, Andrzej Reinke, Xieyuanli Chen, Lei Tai,Cyrill Stachniss, IEEE International Conference on Robotics and Automation (ICRA) 2021. pdf
title={{Simple But Effective Redundant Odometry for Autonomous Vehicles}},
author={A. Reinke and X. Chen and C. Stachniss},
booktitle={Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
url = {}

1. Prerequisites

1.1 Ubuntu

The code was tested under Ubuntu 64-bit 18.04.

1.2. Open3D

Installation processhere

1.3. OpenCV 4.3

Installation process here

1.4. catkin_tools

Installation process here

2. How to run

2.1. Clone the repo

mkdir MutiverseOdometry_ws
cd MutiverseOdometry
git clone
catkin build 

2.1. Setup config file

Before running setup paths in demos_standalone/config/config.yaml With the new release the parameters are read from txt kitti file

2.1.1 Odometries Here are available odometries that you can setup (in a default mode all odometries are available)

  colorbased_vlo: null
  gicp_lo: null
      contrastThreshold: 0.04
      edgeThreshold: 10.0
      nOctaveLayers: 3
      nfeatures: 0
      sigma: 1.6
  ndt_lo: null
  point2plane_lo: null

null are necessary in order to yaml work In the future relase there will be more things to play with since there will be a chance to pick matcher and feature descriptor for the image-based odometry for Huang's method (also with deep learning methods and semantic/panoptic information)

2.2. Run

Go to build/standalone/

Run (as you can see the initial name was a bit different)


3 Notes/TODO:

  • New release with more clean code is coming soon since this release is a cherry pick from semester master project.
  • The plan is also to make it real time and ROS-based.
  • Of course other research will be added on-top of this work.

4. Licence

The source code is released under GPLv3 license.

For any technical issues, please contact Andrzej Reinke with tag [MutiverseOdometry].


Code for Simple But Effective Redundant Odometry for Autonomous Vehicles






No releases published


No packages published