tops666 / DLIOM

[WIP] DLIOM - Direct Lidar-Intertial Odometry: Perceptive and Connective SLAM

This repo implements DLIOM, based on DLIO [repo] | [paper]

Current Status

Frontend

• 2-step deskew
• Jaccard-based keyframing
• Slip-resistant keyframing

Backend

• Factors
  • Sequential Factor
  • Connective Factor
    • min/max threshold
  • Gravity factor
  • Loop factor
  • GPS factor (unaligned, GTSAM)
    • matched with keyframes in case of new
    • matched with any keyframe at any time
• Architecture
  • separate thread
  • tightly coupled with Frontend

Acknowledgments

Thank you to the original Authors of DLIO; Kenny Chen, Ryan Nemiroff and Brett T. Lopez

Citations

@misc{chen2023direct,
      title={Direct LiDAR-Inertial Odometry and Mapping: Perceptive and Connective SLAM}, 
      author={Kenny Chen and Ryan Nemiroff and Brett T. Lopez},
      year={2023},
      eprint={2305.01843},
      archivePrefix={arXiv},
      primaryClass={cs.RO}
}

@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}
}

Please see the original instructions as well.