declare-lab/Emma-X

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

29
/ 100
Experimental

This helps robots perform complex manipulation tasks by understanding high-level instructions and visual information from a camera. It takes a task description like "put carrot in pot" and an image of the scene, then outputs a series of robot actions. Operations engineers or automation specialists working with robotic arms would use this to program robots more intuitively.

No commits in the last 6 months.

Use this if you need a robot to execute specific, multi-step tasks based on natural language commands and real-time visual input.

Not ideal if you are looking for a simple pick-and-place robot or if your tasks do not require complex visual understanding and decision-making.

robotics industrial-automation human-robot-interaction robotic-manipulation
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

79

Forks

7

Language

Python

License

Last pushed

May 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/declare-lab/Emma-X"

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