iESKF-lio
This repository is a modified LiDAR-inertial odometry system. The system is developed based on the open-source odometry framework FAST-LIO to get the odometry information. And the feature extract moudle is implemented based on LIO-SAM .
Modification
- Feature extract moudle is implemented based on lio-sam, this moudle support multiple lidar types(such as velodyne,ouster,robosense, livox etc.);
- laser mapping moudle is implemented base on fast-lio 1.0, Use Eigen matrix instead of IKFom;
- use ikdtree manage the map;
- the new laser mapping moudle support multiple lidar types: both traditional spinning lidar (velodyne, ouster, robsense etc.) and solid-state lidar(livox);
- add online extrinsic calib as fast-lio2
- add new lidar process moudle, this moudle support process multi-lidar (as one Lidar);
- add greedy based feature select(reference to M-LOAM);(code upload in a new branck(gfs) 2022-11-23)
DEMO
[update 2022-11-08]
VIDEO: IESKF-LIO+Greedy based Feature Select
[update 2022-08-05]
UrbanNav-HK-TST-20210517 test video
Dependency
Follow the fast_lio
Build
Use the following commands to download and compile the package.
cd ~/${yourdir}/src
git clone https://github.com/chengwei0427/ESKF_LIO.git
cd ..
source devel/setup.bash
catkin_make
How to run
- change the params in config/feat.yaml;
- test direct/feature based eskf-lio use run.launch;
- test multi-lidar slam use run_multi.launch;
other notes
- you cloud test the multi-lidar with the UrbanNavDataset;
- the auxiliary lidar only support velodyne current, the primary lidar support multi-type lidars(such as velodyne,ouster,robosense, livox etc.);
TODO
- add ivox
- add extrinsic parameter calibration
- compare with FAST-LIO2
- add test video
- support multi-lidar
- add greedy base feature select
Contributing
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Contact
Author: chengwei zhao
Maintainer: chengwei zhao([email protected])
Project Link: ESKF_LIO
Acknowledgments
Thanks for LOAM, FAST_LIO ,LIO_SAM, M-LOAM and UrbanNavDataset.