KhaledSharif/robot-transformers

Train and evaluate an Action Chunking Transformer (ACT) to perform cooperative robot manipulation tasks

31
/ 100
Emerging

This project helps robotics engineers and researchers train robots to perform complex, fine-grained manipulation tasks, like picking up and inserting objects, by learning from human demonstrations. You provide videos of a human teleoperating a robot, and the system outputs a trained model that enables another robot to replicate those actions smoothly and precisely.

No commits in the last 6 months.

Use this if you need to teach a robot precise object manipulation skills from human-led examples and want to improve task success by reducing compounding errors.

Not ideal if your robot tasks are simple, repetitive, or don't require high precision, or if you don't have human teleoperation data for training.

robot-manipulation imitation-learning robot-training automation robotics-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

17

Forks

2

Language

Python

License

MIT

Last pushed

May 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/KhaledSharif/robot-transformers"

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