KhaledSharif/robot-transformers
Train and evaluate an Action Chunking Transformer (ACT) to perform cooperative robot manipulation tasks
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.
Stars
17
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action