robot-learning-freiburg/TAPAS

PyTorch code for TAPAS-GMM.

37
/ 100
Emerging

This project helps robotics engineers teach robots complex manipulation tasks more efficiently. By taking a few demonstrations of a task — for example, a human moving an object — it generates a policy that allows the robot to imitate and perform similar long-horizon tasks. This is ideal for researchers and developers working with robotic arms like the Franka Emika or in simulation environments like ManiSkill2 and RLBench, who need to quickly transfer skills from human examples to robot execution.

No commits in the last 6 months.

Use this if you need to program robots to perform intricate, multi-step manipulation tasks using only a small number of human demonstrations, aiming for robust and adaptable robot behavior.

Not ideal if you are looking for a plug-and-play solution for basic, pre-defined robotic tasks or if you do not have the expertise to set up and configure robotic simulation or hardware environments.

robot-manipulation robot-learning robot-imitation robotic-automation robot-programming
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

15

Forks

4

Language

Jupyter Notebook

License

Last pushed

Nov 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/robot-learning-freiburg/TAPAS"

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