DynaLO

This repo will contain the implementation for our paper: Dynamic Object-aware LiDAR Odometry Aided by Joint Weightings Estimation in Urban Areas. The proposed method is released, and the vehicle simulator will be released once it is ready!

Evaluation

Prerequisites

We tested on Ubuntu 64-bit 18.04, ROS Melodic. ROS Installation. The package is tested on Ubuntu 18.04 with ROS Melodic.

1. Ceres Solver

Ceres Solver

Build

Clone repository:

    cd ~/catkin_ws/src
    git clone https://github.com/DarrenWong/code_for_dynaLO.git
    cd ..
    catkin_make
    source ~/catkin_ws/devel/setup.bash

Download test rosbag

Download dynamic vehicle data, this data is modified based on nuScenes Sequence 0171 using our proposed vehicle simulator (will release soon)

Launch

    roslaunch dynaLO reweight.launch

Acknowledgements

This work is based on F-LOAM and LIO-Mapping. Thanks for their great work!

Citation

If you use this work for your research, you may want to cite

F. Huang, W. Wen, J. Zhang, C. Wang and L. -T. Hsu, "Dynamic Object-aware LiDAR Odometry Aided by Joint Weightings Estimation in Urban Areas," in IEEE Transactions on Intelligent Vehicles, doi: 10.1109/TIV.2023.3338141.

@article{dynaLO2023huang,
  author={Huang, Feng and Wen, Weisong and Zhang, Jiachen and Wang, Chaoqun and Hsu, Li-Ta},
  journal={IEEE Transactions on Intelligent Vehicles},
  title={Dynamic Object-aware LiDAR Odometry Aided by Joint Weightings Estimation in Urban Areas}, 
  year={2023}
}