hc_lio

Repository for 3D localization and mapping of multi-agricultural scenes via a hierarchically-coupled LiDAR-Inertial Odometry

Dependencies:

PCL == 1.10.0; GTSAM == 4.0.3; Eigen == 3.3.7

Build:

cd ~catkin_ws/ && catkin_make -j$(nproc) or ./build.sh

Our datasets: https://drive.google.com/drive/folders/1-SLxUejiFGY_PzGn1oLpMKWUoBMMOyx5?usp=drive_link M2DGR: https://github.com/SJTU-ViSYS/M2DGR.

Experiments in open and dense agriculture:

walk_dataset (lio_sam) dlio:

ours:

cotton_1: fast_lio2:

ours:

hku_main_building:

TODO: add gravity factor; add submap management based point-based or voxel-based; ...

Acknowledgments:

@article{chen2022dlio, title={Direct LiDAR-Inertial Odometry: Lightweight LIO with Continuous-Time Motion Correction}, author={Chen, Kenny and Nemiroff, Ryan and Lopez, Brett T}, journal={2023 IEEE International Conference on Robotics and Automation (ICRA)}, year={2023}, pages={3983-3989}, doi={10.1109/ICRA48891.2023.10160508} }

@Booklet{EasyChair:2703, author = {Kenji Koide and Masashi Yokozuka and Shuji Oishi and Atsuhiko Banno}, title = {Voxelized GICP for Fast and Accurate 3D Point Cloud Registration}, howpublished = {EasyChair Preprint no. 2703},

year = {EasyChair, 2020}}

@book{factor_graphs_for_robot_perception, author={Frank Dellaert and Michael Kaess}, year={2017}, title={Factor Graphs for Robot Perception}, publisher={Foundations and Trends in Robotics, Vol. 6}, url={http://www.cs.cmu.edu/~kaess/pub/Dellaert17fnt.pdf} }