rayguan97/GANav-offroad

This is the code base for GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments.

41
/ 100
Emerging

This helps outdoor robots, such as autonomous vehicles or drones, understand the terrain around them. It takes standard camera images and identifies regions that are safe to navigate, like paths or stable ground, versus unsafe areas such as deep mud or steep slopes. Roboticists and field operations engineers who deploy robots in complex, off-road environments would use this to improve robot autonomy and safety.

145 stars. No commits in the last 6 months.

Use this if you need your autonomous robot to reliably identify navigable and non-navigable terrain in unstructured outdoor settings from visual data.

Not ideal if your robot operates exclusively in highly structured, indoor environments or if you require precise obstacle avoidance based on 3D lidar data rather than visual segmentation.

robot-navigation terrain-segmentation autonomous-offroading field-robotics unstructured-environments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

145

Forks

18

Language

Python

License

Apache-2.0

Last pushed

Jan 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rayguan97/GANav-offroad"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.