A Python framework for robotics research and development.

Lightweight, flexible, and designed for researchers and developers in robotics.

⭐ Star us on GitHub — your support motivates us a lot! 🙏😊

Join us on Discord!

What is this about?

Ark is a Python-first playground for robot learning. Instead of wrestling with C++ and fragmented tools, you can collect data, train policies, and switch between simulation and real robots with just a few lines of code. Think of it as the PyTorch + Gym for robotics — simple, modular, and built for rapid prototyping of intelligent robots.

📚 Learn more:

• 📖 Tutorials
• ⚙️ Documentation
• 📄 Research Paper

Installation

The framework depends on Ark Types and requires a Python environment managed with Conda. The steps below describe how to set up the repositories on Ubuntu and macOS.

Ubuntu

# create a workspace and enter it
mkdir Ark
cd Ark

# create and activate the environment
conda create -n ark_env python=3.10
conda activate ark_env

# clone and install the framework
git clone https://github.com/Robotics-Ark/ark_framework.git
cd ark_framework
pip install -e .
cd ..

# clone and install ark_types
git clone https://github.com/Robotics-Ark/ark_types.git
cd ark_types
pip install -e .

macOS

# create a workspace and enter it
mkdir Ark
cd Ark

# create and activate the environment
conda create -n ark_env python=3.11
conda activate ark_env

# clone and install the framework
git clone https://github.com/Robotics-Ark/ark_framework.git
cd ark_framework
pip install -e .

# pybullet must be installed via conda on macOS
conda install -c conda-forge pybullet
cd ..

# clone and install ark_types
git clone https://github.com/Robotics-Ark/ark_types.git
cd ark_types
pip install -e .

After installation, verify the command-line tool is available:

ark --help

Cite

If you find Ark useful for your work please cite:

 @misc{robotark2025,
      title        = {Ark: An Open-source Python-based Framework for Robot Learning},
      author       = {Magnus Dierking, Christopher E. Mower, Sarthak Das, Huang Helong, Jiacheng Qiu, Cody Reading, 
                      Wei Chen, Huidong Liang, Huang Guowei, Jan Peters, Quan Xingyue, Jun Wang, Haitham Bou-Ammar},
      year         = {2025},
      howpublished = {\url{https://ark_robotics.github.io/}},
      note         = {Technical report}
    }