robot-learning-freiburg/TAPAS
PyTorch code for TAPAS-GMM.
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.
Stars
15
Forks
4
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
oscarknagg/few-shot
Repository for few-shot learning machine learning projects
google-research/meta-dataset
A dataset of datasets for learning to learn from few examples
Sha-Lab/FEAT
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"