Skip to content

World's First Large-scale High-quality Robotic Manipulation Benchmark

License

Notifications You must be signed in to change notification settings

liyonggang-mi/AgiBot-World

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

agibot_world

Static Badge Static Badge Static Badge

Key Features 🔑

  • 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

News

  • [2024/12/30] 🤖 Agibot World demo released.

Table of Contents

  1. Key Features
  2. Getting Started
  3. TODO List
  4. License and Citation

Getting started 🔥

Prepare the AgiBot World data

# 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

Dataset Preprocessing

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.

Training

To train a simple Diffusion Policy, please refer to this Jupyter.

(back to top)

TODO List 📅

  • 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

(back to top)

License and Citation

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}
}

About

World's First Large-scale High-quality Robotic Manipulation Benchmark

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%