Wild Visual Navigation
- Software
- Navigation and mapping
- Framework
A visual, self-supervised traversability estimation system for mobile robots, trained online from a few minutes of human demonstrations in the field.
Made by leggedrobotics.
Source on GitHub: github.com/leggedrobotics/wild_visual_navigation (opens in a new tab). Facts read at commit 3d6d9d9 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 3d6d9d9 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
What it does
- Implements the full Wild Visual Navigation system in pure Python.
- Provides a Docker-based quick-start demo using a simulated Jackal robot.
- Includes scripts to run inference on images with pre-trained model checkpoints.
- Offers robot integration packages for ANYmal and Jackal robots using ROS 1.
- Integrates with elevation_mapping_cupy.
- Adapts to other robots through configuration files and a custom ROS package.
Written by Robotheca from the project's README (opens in a new tab) at commit 3d6d9d9.
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
- 27 May 2026 on main
- Latest release
- None published on GitHub
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.