lukashermann/hulc

Hierarchical Universal Language Conditioned Policies

38
/ 100
Emerging

This project helps robotics researchers teach robots complex, multi-step tasks using plain language commands. You input videos of a robot performing actions and corresponding language descriptions, and it outputs a trained robot policy that can execute new instructions in a 3D environment. This is designed for robotics researchers and engineers working on general-purpose robot manipulation.

No commits in the last 6 months.

Use this if you are developing robot control policies and want to train a single model to perform a wide variety of long-horizon manipulation tasks using natural language instructions.

Not ideal if you are looking for a ready-to-deploy solution for a specific industrial automation task without further research and development.

robotics research robot manipulation language understanding imitation learning autonomous systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

77

Forks

10

Language

Python

License

MIT

Last pushed

Mar 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lukashermann/hulc"

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