GIRA: Gaussian Mixture Models for Inference and Robot Autonomy
Paper • Contact Us
GIRA3D is an open-source framework for compact, high-resolution point cloud modeling using Gaussian mixture models that provides fundamental robotics capabilities, including reconstruction, pose estimation, and occupancy modeling.
Reconstruction¶
The reconstruction repository is available here: gira3d-reconstruction.
Please cite the following works if you use gira3d-reconstruction
:
@ARTICLE{goel_proabilistic_2023,
title = {Probabilistic {{Point Cloud Modeling}} via {{Self-Organizing Gaussian Mixture Models}}},
author = {Goel, Kshitij and Michael, Nathan and Tabib, Wennie},
year = {2023},
month = may,
journal={IEEE Robotics and Automation Letters},
volume = {8},
number = {5},
pages = {2526--2533},
issn = {2377-3766},
doi = {10.1109/LRA.2023.3256923},
keywords = {Adaptation models,Complexity theory,Computational modeling,Data models,field robots,Mapping,Point cloud compression,Probabilistic logic,RGB-D perception,Three-dimensional displays}
}
Registration¶
The registration repository is available here: gira3d-registration.
Please cite the following works if you use gira3d-registration
:
@article{tabib2018manifold,
title={On-manifold gmm registration},
author={Tabib, Wennie and O’Meadhra, Cormac and Michael, Nathan},
journal={IEEE Robotics and Automation Letters},
volume={3},
number={4},
pages={3805--3812},
year={2018},
doi={https://doi.org/10.1109/LRA.2018.2856279},
publisher={IEEE}
}
@InProceedings{tabib2019fsr,
author="Tabib, Wennie
and Michael, Nathan",
editor="Ishigami, Genya
and Yoshida, Kazuya",
title="Simultaneous Localization and Mapping of Subterranean Voids with Gaussian Mixture Models",
booktitle="Field and Service Robotics",
year="2021",
publisher="Springer Singapore",
address="Singapore",
pages="173--187",
isbn="978-981-15-9460-1"
}
Occupancy Modeling¶
The occupancy modeling repository is available here: gira3d-occupancy-modeling.
Please cite the following works if you use gira3d-occupancy-modeling
:
@ARTICLE{omeadhra2019ral,
author={O’Meadhra, Cormac and Tabib, Wennie and Michael, Nathan},
journal={IEEE Robotics and Automation Letters},
title={Variable Resolution Occupancy Mapping Using Gaussian Mixture Models},
year={2019},
volume={4},
number={2},
pages={2015-2022},
doi={10.1109/LRA.2018.2889348}
}