Ubuntu 14.04+ROS indigo and Ubuntu 16.04+ROS kinetic:
News
- May 2018: maplab was presented at ICRA in Brisbane. (paper)
- March 2018: Check out our release candidate with improved localization and lots of new features! PR
Description
This repository contains maplab, an open, research-oriented visual-inertial mapping framework, written in C++, for creating, processing and manipulating multi-session maps.
On the one hand, maplab can be considered as a ready-to-use visual-inertial mapping and localization system.
On the other hand, maplab provides the research community with a collection of multi-session mapping tools that include map merging, visual-inertial batch optimization, and loop closure.
Furthermore, it includes an online frontend, ROVIOLI, that can create visual-inertial maps and also track a global drift-free pose within a localization map.
For documentation, tutorials and datasets, please visit the wiki.
Please also check out our video:
Features
Robust visual-inertial odometry with localization
Large-scale multisession mapping and optimization
Dense reconstruction
A research platform extensively tested on real robots
Installation and getting started
The following articles help you with getting started with maplab and ROVIOLI:
- Installation on Ubuntu 14.04 or 16.04
- Introduction to the maplab framework
- Structure of the framework
- Running ROVIOLI in VIO mode
- Basic console usage
- Console map management
More detailed information can be found in the wiki pages.
Research Results
The maplab framework has been used as an experimental platform for numerous scientific publications. For a complete list of publications please refer to Research based on maplab.
Citing
Please cite the following paper when using maplab or ROVIOLI for your research:
@article{schneider2018maplab,
title={maplab: An Open Framework for Research in Visual-inertial Mapping and Localization},
author={T. Schneider and M. T. Dymczyk and M. Fehr and K. Egger and S. Lynen and I. Gilitschenski and R. Siegwart},
journal={IEEE Robotics and Automation Letters},
year={2018},
doi={10.1109/LRA.2018.2800113}
}
Additional Citations
Certain components of maplab are directly using the code of the following publications:
- Localization:
@inproceedings{lynen2015get, title={Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization.}, author={Lynen, Simon and Sattler, Torsten and Bosse, Michael and Hesch, Joel A and Pollefeys, Marc and Siegwart, Roland}, booktitle={Robotics: Science and Systems}, year={2015} }
- ROVIOLI which is composed of ROVIO + maplab for map building and localization:
@article{bloesch2017iterated, title={Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback}, author={Bloesch, Michael and Burri, Michael and Omari, Sammy and Hutter, Marco and Siegwart, Roland}, journal={The International Journal of Robotics Research}, volume={36}, number={10}, pages={1053--1072}, year={2017}, publisher={SAGE Publications Sage UK: London, England} }
Credits
- Thomas Schneider
- Marcin Dymczyk
- Marius Fehr
- Kevin Egger
- Simon Lynen
- Mathias Bürki
- Titus Cieslewski
- Timo Hinzmann
- Mathias Gehrig
For a complete list of contributors, have a look at CONTRIBUTORS.md