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.
ROS 2 LiDAR SLAM for pointcloud-map authoring, benchmarking, and Autoware-compatible map workflows.
| Date | Stars |
|---|---|
| 2026-07-24 | 833 |
| 2026-07-25 | 833 |
| 2026-07-28 | 832 |
| 2026-07-30 | 832 |
| 2026-08-06 | 832 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
15.0
growth rate 0.00%/day
# lidarslam_ros2
[](https://github.com/rsasaki0109/lidar_slam_ros2/actions/workflows/main.yml)
[](https://opensource.org/licenses/BSD-2-Clause)
[](#support-and-license)
[](https://github.com/rsasaki0109/lidar_slam_ros2/stargazers)
**Turn a rosbag into a map you can actually drive on.**
ROS 2 LiDAR SLAM that outputs an Autoware-compatible map bundle — `pointcloud_map/`,
`map_projector_info.yaml`, and auto-generated lanelet2. Frontend is `RKO-LIO` (MIT), backend is
`graph_based_slam` (BSD-2). No GPL components on the default workflow.
*Shinjuku point cloud map built from a demo rosbag with this stack — start at the
[Quickstart](#quickstart). `develop` is the default branch; latest release notes:
[v0.6.0](docs/releases/v0.6.0.md).*
## Why lidarslam_ros2
Most LiDAR SLAM stacks stop at a trajectory and a point cloud. This one ships the
artifacts you need downstream:
- **Autoware-compatible output** — `pointcloud_map/` + `map_projector_info.yaml` open
directly in Autoware map loaders; `verify_autoware_map.py` prints
`map_verify: PASS` on every saved bundle.
- **lanelet2 auto-generation** — drivable lanelets from the SLAM trajectory,
validated for multi-segment Autoware routing.
- **Surveyed ground truth** — releases are gated in CI by per-dataset APE
thresholds, including total-station checkpoints on a Livox MID-360
([accuracy](#accuracy)).
- **Loop closure, GPL-free** — opt-in built-in Scan Context, BEV / SOLiD /
STD/BTC-style Triangle descriptors, and 3D-BBS verification.
- **Tunnel / fog degeneracy presets** — opt-in radar fusion and gravity
alignment map a ~500 m self-similar tunnel end-to-end
([result](#tunnel-and-fog-mapping-without-degeneracy-collapse), [guide](docs/degeneracy-guide.md)).
- **Deterministic offline mapping** — `graph_slam_offline_runner` (backend,
recorded odometry bag) and `scan_matcher_offline_runner` (frontend, raw bag)
produce *byte-identical* trajectories, loop edges and submaps; the release
gate enforces both.
- **Globally refined, quality-gated maps** — clean-room plane bundle adjustment
refines submap poses under holdout-validated quality thresholds
([evidence](docs/research/map-quality-baseline.md)).
- **GNSS georeferencing** — optional GNSS constraints and projector metadata for
real-world coordinates.
- **Camera-coloured point-cloud maps** — synchronized images are projected onto
registered LiDAR scans with calibration-aware, occlusion-resistant colouring.
```mermaid
flowchart LR
bag(["rosbag2"]) --> rko["RKO-LIO<br/>LiDAR-inertial odometry"]
rko --> gbs["graph_based_slam<br/>loop closure + graph optimization"]
gbs --> bundle["Autoware map bundle<br/>pointcloud_map · lanelet2 · projector info"]
```
## Quickstart
Start with [Getting Started](docs/getting-started.md). The [Product Contract](docs/product-contract.md)
defines the maintained surface; see [Distribution](docs/distribution.md) for installed names and binary-release limits.
### Try it with Docker (one command, no build)
```bash
mkdir -p "$PWD/lidarslam_output"
docker run --rm -e LIDARSLAM_HOST_UID="$(id -u)" -e LIDARSLAM_HOST_GID="$(id -g)" \
-v "$PWD/lidarslam_output:/lidarslam_ws/output" \
ghcr.io/rsasaki0109/lidar_slam_ros2:humble
```
This runs the 517 MB MID-360 demo with periodic progress and writes `lidarslam_output/mid360_demo/`.
UID/GID returns it to the Linux user; see [Getting Started](docs/getting-started.md) for other platforms.
### Build from source
```bash
cd ~/ros2_ws/src
git cloneExcerpt of 11,610 characters
Read on GitHub
Ryohei Sasaki · MAP IV · Japan
807
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1bc2f17ae0a09e1c, topic:robotics, topic:ros2, name:slam