- One million+ trajectories from 100 robots.
- 100+ real-world scenarios across 5 target domains.
- Cutting-edge hardware: visual tactile sensors / 6-DoF Dexterous hand / mobile dual-arm robots
- Tasks involving:
- Contact-rich manipulation
- Long-horizon planning
- Multi-robot collaboration
[2024/12/30]
🤖 Agibot World demo released.
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
# When prompted for a password, use an access token with write permissions.
# Generate one from your settings: https://huggingface.co/settings/tokens
git clone https://huggingface.co/datasets/agibot-world/AgiBotWorld-Alpha
# If you want to clone without large files - just their pointers
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/agibot-world/AgiBotWorld-Alpha
Our project relies solely on the lerobot library (dataset v2.0
), please follow their installation instructions.
Here, we provide scripts for converting it to the lerobot format.
python scripts/convert_to_lerobot.py --src_path /path/to/agibotworld/alpha --task_id 352 --tgt_path /path/to/save/lerobot
We would like to express our gratitude to the developers of lerobot for their outstanding contributions to the open-source community.
To train a simple Diffusion Policy, please refer to this Jupyter.
- AgiBot World Alpha
- AgiBot World Beta: ~1,000,000 trajectories of high-quality robot data coming by the end of Q1 2025.
- Complete language annotation
- AgiBot World Colosseum:Comprehensive platform launching in 2025.
- 2025 AgiBot World Challenge
All the data and code within this repo are under CC BY-NC-SA 4.0. Please consider citing our project if it helps your research.
@misc{contributors2024agibotworldrepo,
title={AgiBot World Colosseum},
author={AgiBot World Colosseum contributors},
howpublished={\url{https://github.com/OpenDriveLab/AgiBot-World}},
year={2024}
}