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.
A real-time, direct and tightly-coupled LiDAR-Inertial SLAM for high velocities with spinning LiDARs
| Date | Stars |
|---|---|
| 2026-07-24 | 318 |
| 2026-07-25 | 318 |
| 2026-07-28 | 318 |
| 2026-07-30 | 318 |
| 2026-08-06 | 318 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# LIMO-Velo Contact me at ``[email protected]`` for questions or ideas. ## News! 🎉 - [Carlos](https://github.com/CPerezRuiz335) is working on [LIMOncello](https://github.com/CPerezRuiz335/LIMOncello) that improves the Lie Algebra of the Kalman Filter, is written in functional code and has thread safety just like [Fast-LIMO](https://github.com/fetty31/fast_LIMO). Better, safer and simpler! - [Oriol](https://github.com/fetty31) just released [Fast-LIMO](https://github.com/fetty31/fast_LIMO) - a thread-safe and fast implementation of LIMO-Velo! - Now with a ROS2 branch, `ros2` - thanks to [bertaveira](https://github.com/bertaveira). Broader LiDARs support is needed. - [bertaveira](https://github.com/bertaveira) is also working on a [LIMO-Velo++](https://github.com/bertaveira/LIMO_Velo) with python bindings. Check out his work in progress! ## A real-time LiDAR-Inertial SLAM for high velocities in spinning LiDARs. <p align="center"> <img src="./config/docs/img/Localization.gif" alt="Perfomance of the algorithm" /><br /> Visualization of the algorithm with <code>delta = 0.01</code> (100Hz) </p> Designed for easy modifying via modular and easy to understand code. Relying upon [HKU-Mars](https://github.com/hku-mars)'s [IKFoM](https://github.com/hku-mars/IKFoM) and [ikd-Tree](https://github.com/hku-mars/ikd-Tree) open-source libraries. Based also on their [FAST_LIO2](https://github.com/hku-mars/FAST_LIO). ### Tested and made for racing at Formula Student Driverless Common working speeds are 20m/s in straights and 100deg/s in the turns. <p align="center"> <img src="./config/docs/img/xaloc.gif" alt="Perfomance of the algorithm" /><br /> Tested on and made for Barcelona's own "<a href="https://www.youtube.com/watch?v=ly_ax8w-T7E&feature=emb_logo">Xaloc</a>". </p> ### Centimeter-level accuracy is kept under racing speeds Only algorithm that can deliver centimeter-level resolution on real-time. See the part of my thesis where I explain the algorithm and its results: [LIMOVelo + Results](https://github.com/Huguet57/LIMO-Velo/blob/main/config/docs/Thesis%20-%20LIMOVelo%20%2B%20Results.pdf). <p align="center"> <img src="./config/docs/img/cones-comparison.png" alt="Map comparison - Cones" /><br /> Comparison of cones under racing speeds running all algorithms in real-time, except for LIO-SAM (-r 0.5). It failed otherwise. </p> ### Designed to be easily understood even by beginners Developing an algorithm for a team requires the algorithm to be easy enough to understand being passed through generations. <p align="center"> <img src="./config/docs/img/pipeline.png" alt="Map comparison - Cones" /><br /> LIMO-Velo's pipeline. Here are seen the different modules (blue), data (orange) and libraries (dark green). </p> # LiDARs supported - Velodyne - Hesai - Ouster - Livox (check ``livox`` git branch) # Dependencies - [Ubuntu](https://ubuntu.com) (tested on 18.04, 20.04) - [ROS](http://wiki.ros.org/ROS/Installation) (tested on Melodic, Noetic) - [Eigen](http://eigen.tuxfamily.org/index.php?title=Main_Page) - [PCL](http://www.pointclouds.org/downloads/linux.html) (tested on 1.8) # Newest additions ## High Quality Maps Sometimes a higher map quality is needed, now a new ``high_quality_publish`` parameter has been added to yield results like this below. <p align="center"> <img src="./config/docs/img/high-quality-cones.png" alt="High quality cones" /><br /> Sometimes Xaloc needs more definition to see if a cluster of points is actually a cone. </p> ## Work in progress (branch ``hdmaps``) <p align="center"> <img src="./config/docs/img/prelocalization-hdmaps.gif" alt="Prelocalizing with a given HD map" /><br /> Prelocalization with a previoulsy saved HD map. Still work in progress on the <code>hdmaps</code> branch. Official release will be in a couple of days. </p> # Sample datasets <p align="center"> <img src="./config/docs/img/rosbag-xaloc.gif" alt="Xaloc's fast dataset" /><br /> Xaloc's "fast" dataset. High
Excerpt of 7,239 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9799168aee552792, topic:slam, desc:slam, readme:slam