AirSLAM
- Software
- Navigation and mapping
- Framework
A visual SLAM system for point-line mapping and relocalization that stays robust to lighting changes, supporting visual-only and visual-inertial modes.
Made by sair-lab.
Source on GitHub: github.com/sair-lab/AirSLAM (opens in a new tab). Facts read at commit d126577 (opens in a new tab).
Licenses
- Code
- GPL-3.0-only (opens in a new tab)
Read by Robotheca from LICENSE.md (opens in a new tab) (GPL-3.0-only) at commit d126577 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
Copyleft: Modified source must be published.
What it does
- Uses a single CNN to extract keypoints and structural lines, which are matched, triangulated and optimized together.
- Includes a lightweight relocalization pipeline that reuses a built map, matching keypoints, lines and a structure graph.
- Feature detection and matching networks are deployed with C++ and NVIDIA TensorRT for acceleration.
- Runs mapping, map optimization and relocalization through ROS launch files, using ASL-format or EuRoC datasets.
- Relocalization needs only monocular query images once a map has been built.
Written by Robotheca from the project's README (opens in a new tab) at commit d126577.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 19 Nov 2025 on master
- Latest release
- AirVO (IROS 2023) (5 Aug 2024)
Checked on GitHub on 22 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.