Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[IEEE ICRA'23] A new lightweight LiDAR-inertial odometry algorithm with a novel coarse-to-fine approach in constructing continuous-time trajectories for precise motion correction.
| Date | Stars |
|---|---|
| 2026-07-24 | 1022 |
| 2026-07-25 | 1022 |
| 2026-07-28 | 1022 |
| 2026-07-30 | 1022 |
| 2026-08-06 | 1022 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Direct LiDAR-Inertial Odometry: Lightweight LIO with Continuous-Time Motion Correction
#### [[ IEEE ICRA ](https://ieeexplore.ieee.org/document/10160508)] [[ arXiv ](https://arxiv.org/abs/2203.03749)] [[ Video ](https://www.youtube.com/watch?v=4-oXjG8ow10)] [[ Presentation ](https://www.youtube.com/watch?v=Hmiw66KZ1tU)]
DLIO is a new lightweight LiDAR-inertial odometry algorithm with a novel coarse-to-fine approach in constructing continuous-time trajectories for precise motion correction. It features several algorithmic improvements over its predecessor, [DLO](https://github.com/vectr-ucla/direct_lidar_odometry), and was presented at the IEEE International Conference on Robotics and Automation (ICRA) in London, UK in 2023.
<br>
<p align='center'>
<img src="./doc/img/dlio.png" alt="drawing" width="720"/>
</p>
## Instructions
### Sensor Setup & Compatibility
DLIO has been extensively tested using a variety of sensor configurations and currently supports Ouster, Velodyne, Hesai, and Livox LiDARs. The point cloud should be of input type `sensor_msgs::PointCloud2` and the 6-axis IMU input type of `sensor_msgs::Imu`.
For Livox sensors specifically, you can use the `master` branch directly if it is of type `sensor_msgs::PointCloud2` (`xfer_format: 0`), or the `feature/livox-support` branch and the latest [`livox_ros_driver2`](https://github.com/Livox-SDK/livox_ros_driver2) package if it is of type `livox_ros_driver2::CustomMsg` (`xfer_format: 1`) (see [here](https://github.com/vectr-ucla/direct_lidar_inertial_odometry/issues/5) for more information).
For best performance, extrinsic calibration between the LiDAR/IMU sensors and the robot's center-of-gravity should be inputted into `cfg/dlio.yaml`. If the exact values of these are unavailable, a rough LiDAR-to-IMU extrinsics can also be used (note however that performance will be degraded).
IMU intrinsics are also necessary for best performance, and there are several open-source calibration tools to get these values. These values should also go into `cfg/dlio.yaml`. In practice however, if you are just testing this work, using the default ideal values and performing the initial calibration procedure should be fine.
Also note that the LiDAR and IMU sensors _need_ to be properly time-synchronized, otherwise DLIO will not work. We recommend using a LiDAR with an integrated IMU (such as an Ouster) for simplicity of extrinsics and synchronization.
### Dependencies
The following has been verified to be compatible, although other configurations may work too:
- Ubuntu 20.04
- ROS Noetic (`roscpp`, `std_msgs`, `sensor_msgs`, `geometry_msgs`, `nav_msgs`, `pcl_ros`)
- C++ 14
- CMake >= `3.12.4`
- OpenMP >= `4.5`
- Point Cloud Library >= `1.10.0`
- Eigen >= `3.3.7`
```sh
sudo apt install libomp-dev libpcl-dev libeigen3-dev
```
DLIO supports ROS1 by default, and ROS2 using the `feature/ros2` branch.
### Compiling
Compile using the [`catkin_tools`](https://catkin-tools.readthedocs.io/en/latest/) package via:
```sh
mkdir ws && cd ws && mkdir src && catkin init && cd src
git clone https://github.com/vectr-ucla/direct_lidar_inertial_odometry.git
catkin build
```
### Execution
After compiling, source the workspace and execute via:
```sh
roslaunch direct_lidar_inertial_odometry dlio.launch \
rviz:={true, false} \
pointcloud_topic:=/robot/lidar \
imu_topic:=/robot/imu
```
for Ouster, Velodyne, Hesai, or Livox (`xfer_format: 0`) sensors, or
```sh
roslaunch direct_lidar_inertial_odometry dlio.launch \
rviz:={true, false} \
livox_topic:=/livox/lidar \
imu_topic:=/robot/imu
```
for Livox sensors (`xfer_format: 1`).
Be sure to change the topic names to your corresponding topics. Alternatively, edit the launch file directly if desired. If successful, you should see the following output in your terminal:
<br>
<p align='center'>
<img src="./doc/img/terminal.png" alt="drawing" width="480"/>
</p>
### Services
To save DLIO's generated map into `.pcd` format, call the foExcerpt of 6,143 characters
Read on GitHub
20
3
Vincent Richard · Macnica
2
2
Julian Gaal
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2c2eb6bb5bcb3567, topic:robotics, topic:ros, topic:slam