mees/hulc2

[ICRA2023] Grounding Language with Visual Affordances over Unstructured Data

33
/ 100
Emerging

This project helps robotics engineers train robots to understand and perform complex tasks using natural language instructions. It takes in large datasets of robot interaction, including visual data and some language annotations, and outputs a trained robot policy capable of executing multi-step commands in real-world scenarios. Robotics researchers and developers who are building intelligent robotic systems would find this useful.

No commits in the last 6 months.

Use this if you need to efficiently train a robotic arm to follow abstract, multi-step natural language commands, especially with limited language-annotated data.

Not ideal if your robot tasks are simple, repetitive, or don't require high-level language understanding and generalization.

robot-learning robot-control natural-language-processing robot-manipulation human-robot-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

45

Forks

4

Language

Python

License

MIT

Last pushed

Oct 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mees/hulc2"

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