rayguan97/GANav-offroad
This is the code base for GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments.
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.
Stars
145
Forks
18
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
patrick-llgc/Learning-Deep-Learning
Paper reading notes on Deep Learning and Machine Learning
eric-yyjau/pytorch-superpoint
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
magicleap/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
changhao-chen/deep-learning-localization-mapping
A collection of deep learning based localization models
lucasb-eyer/pydensecrf
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.