eugeneteoh/greenaug
GreenAug: Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation
This project helps robotics engineers train robotic arms to perform manipulation tasks more reliably across different real-world environments. By taking images or videos of robots in a green screen setup, it intelligently replaces the background with diverse, realistic, or even imagined scenes. The result is a more robust robotic policy that can handle unexpected variations in its operational setting, making deployment easier and more effective.
No commits in the last 6 months.
Use this if you are a robotics engineer developing manipulation policies and want your robots to generalize better to various environments beyond their training setup.
Not ideal if you are looking for a general-purpose image augmentation tool unrelated to robotic manipulation, or if you don't use a green screen for your robot's visual data.
Stars
12
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/eugeneteoh/greenaug"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.