ankile/imitation-juicer

Enabling robots to perform long-horizon dexterous tasks with imitation learning

34
/ 100
Emerging

This project helps roboticists teach robots to perform complex, multi-step assembly tasks more efficiently. By providing demonstrations of a task (like assembling furniture) using a 3D SpaceMouse, the system learns from these examples. The output is a trained robotic agent capable of performing these dexterous tasks autonomously, which is ideal for researchers and engineers working with robotic automation.

No commits in the last 6 months.

Use this if you are a roboticist or automation engineer looking to rapidly train robots for precise, long-horizon assembly tasks by demonstrating the actions yourself.

Not ideal if you need a plug-and-play solution for immediate deployment, as it requires significant setup and expertise in robotics simulation environments.

robotic-assembly automation robot-training imitation-learning dexterous-manipulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

41

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ankile/imitation-juicer"

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