kyegomez/RT-2

Democratization of RT-2 "RT-2: New model translates vision and language into action"

45
/ 100
Emerging

This project helps roboticists and automation engineers by providing a model that translates visual information and natural language commands directly into robot actions. You input images from a robot's camera and a natural language instruction, and the model outputs the necessary control actions for the robot to execute the task. It's designed for anyone working with robots that need to understand and act upon visual and verbal cues in dynamic environments.

554 stars. No commits in the last 6 months.

Use this if you need your robots to interpret complex visual scenes and human language commands to perform physical tasks, such as in automated factories or for assisted care.

Not ideal if your application requires extremely precise, real-time control based solely on sensor data without any language interpretation.

robotics automation manufacturing healthcare-robotics smart-home-automation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

554

Forks

68

Language

Python

License

MIT

Last pushed

Jul 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/RT-2"

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