1,2Mengda Xu, 1,Zhenjia Xu, 1Cheng Chi, 2,3Manuela Veloso, 1Shuran Song
1Columbia University, 2JP Morgan AI Research,3CMU
CoRL 2023
This repository contains code for training and evaluating XSkill in both simulation and real-world settings.
Follow these steps to install XSkill
:
cd xskill
conda env create -f environment.yml
conda activate xskill
pip install -e .
To set up the simulation dataset:
mkdir datasets
cd datasets
wget https://xskill.cs.columbia.edu/data/kitchen.zip
unzip kitchen.zip
base_dev_dir
config/simulation/create_kitchen_datase.yaml to your working directory. Run the following command to generate the cross-embodiment kitchen data and the training mask:
cd scripts
python create_all_kitchen_dataset.py
python extract_kitchen_info.py
To Download the real world kitchen dataset:
mkdir datasets
cd datasets
wget https://xskill.cs.columbia.edu/data/real_kitchen_data.zip
Run the skill discovery script:
python scripts/skill_discovery.py
Label the dataset using the learned prototype by the trained model.
python scripts/label_sim_kitchen_dataset.py
Execute the skill transfer and composing script. Replace the pretrain_path and pretrain_ckpt in cfg/simulation/skill_transfer_composing.yaml
python scripts/skill_transfer_composing.py
Execute the real-world skill discovery script:
python scripts/realworld/skill_discovery.py
Label the real-world dataset:
python scripts/realworld/label_real_kitchen_dataset.py
📊 Visualization
Open the provided Jupyter notebook viz_real.ipynb
to visualize the learned prototypes:
@inproceedings{
xu2023xskill,
title={{XS}kill: Cross Embodiment Skill Discovery},
author={Mengda Xu and Zhenjia Xu and Cheng Chi and Manuela Veloso and Shuran Song},
booktitle={7th Annual Conference on Robot Learning},
year={2023},
url={https://openreview.net/forum?id=8L6pHd9aS6w}
}
This repository is released under the MIT license.