EllipseLIO

Video   •   Install   •   Paper   •   Report Issues

EllipseLIO is an Adaptive LiDAR Inertial Odometry Approach with an Ellipsoid Representation

ROS2 Humble and Jazzy

Build

mkdir -p ~/colcon_ws/src
cd ~/colcon_ws/src
git clone git@github.com:v4rl-ucy/ellipselio.git
cd ..
colcon build --packages-select ellipselio --cmake-args -DCMAKE_BUILD_TYPE=Release --symlink-install
source ~/colcon_ws/install/setup.bash

Run standalone with a bag file

ros2 launch ellipselio ellipselio_standalone.launch.py config_file:=<config_file_name>
ros2 bag play --clock <imu_rate> <bag_folder> --topics <lidar_topic> <imu_topic>

Included dataset configs

Config file	Dataset
config/os128_ncd.yaml	Newer College Multi-Cam
config/os64_ncd.yaml	Newer College Stereo-Cam
config/qt64_spires.yaml	Oxford Spires
config/vlp16_bot.yaml	BotanicGarden
config/vlp16_geode.yaml	GEODE Alpha
config/os64_geode.yaml	GEODE Beta
config/vlp16_graco.yaml	GRACO

Run standalone with live data

ros2 launch ellipselio ellipselio_standalone.launch.py config_file:=<config_file_name> use_sim_time:=false

📝 Citation

If you use EllipseLIO please cite our preprint on arXiv

@article{border2026ellipselio,
   author = {Border, Rowan and Chli, Margarita},
   journal = {arXiv},
   title = {{EllipseLIO}: Adaptive {LiDAR} Inertial Odometry with an Ellipsoid Representation},
   url = {http://arxiv.org/abs/2605.21150},
   year = {2026}
}

🙏 Acknowledgements

Many thanks to the authors of FAST-LIO2, IKFoM, and i-Octree for open-sourcing their work, which made the development of EllipseLIO possible.

📫 Contact information

If you have any questions, please do not hesitate to contact

• Rowan Border ✉️ rborder dot robots at gmail dot com