robopianist 1.0.3

A benchmark for high-dimensional robot control

RoboPianist: A Benchmark for High-Dimensional Robot Control

RoboPianist is a new benchmarking suite for high-dimensional control, targeted at testing high spatial and temporal precision, coordination, and planning, all with an underactuated system frequently making-and-breaking contacts. The proposed challenge is mastering the piano through bi-manual dexterity, using a pair of simulated anthropomorphic robot hands.

This codebase contains software and tasks for the benchmark, and is powered by MuJoCo.

• Getting Started
• Installation
  • Install from source
    • Optional: Download additional soundfonts
  • Install from PyPI
• MIDI Dataset
• Contributing
• FAQ
• Citing RoboPianist
• Acknowledgements
• License and Disclaimer

Getting Started

We've created an introductory Colab notebook that demonstrates how to use RoboPianist. It includes code for loading and customizing a piano playing task, and a demonstration of a pretrained policy playing a short snippet of Twinkle Twinkle Little Star. Click the button below to get started!

Installation

RoboPianist is supported on both Linux and macOS and can be installed with Python 3.8 up to 3.10. We recommend using Miniconda to manage your Python environment.

3.11 will be supported once the numba team resolves #8304.

Install from source

The recommended way to install this package is from source. Start by cloning the repository:

git clone https://github.com/google-research/robopianist.git

Next, install the prerequisite dependencies:

cd robopianist

bash scripts/install_deps.sh

git submodule init && git submodule update

Finally, create a new conda environment and install RoboPianist in editable mode:

conda create -n pianist python=3.10
conda activate pianist

pip install -e ".[dev]"

To test your installation, run make test and verify that all tests pass.

Optional: Download additional soundfonts

We recommend you install additional soundfonts to improve the quality of the synthesized audio. To do so, run:

bash scripts/get_soundfonts.sh

Install from PyPI

First, install the prerequisite dependencies:

bash <(curl -s https://raw.githubusercontent.com/google-research/robopianist/main/scripts/install_deps.sh)

Next, create a new conda environment and install RoboPianist:

conda create -n pianist python=3.10
conda activate pianist

pip install --upgrade robopianist

MIDI Dataset

Unfortunately, the PIG dataset cannot be redistributed on GitHub due to licensing restrictions. You will need to download it from the website and preprocess it with our script. See docs/dataset for more information.

Contributing

We welcome contributions to RoboPianist. Please see docs/contributing.md for more information.

FAQ

See docs/faq.md for a list of frequently asked questions.

Citing RoboPianist

If you use RoboPianist in your work, please use the following citation:

@software{zakka2023robopianist,
  author = {Zakka, Kevin and Smith, Laura and Gileadi, Nimrod and Howell, Taylor and Peng, Xue Bin and Singh, Sumeet and Tassa, Yuval and Florence, Pete and Zeng, Andy and Abbeel, Pieter},
  title = {{RoboPianist: A Benchmark for High-Dimensional Robot Control}},
  url = {https://github.com/google-research/robopianist},
  year = {2023},
}

Acknowledgements

We would like to thank the following people for making this project possible:

• Philipp Wu and Mohit Shridhar for being a constant source of inspiration and support.
• Ilya Kostrikov for RL debugging support.
• The Magenta team for helpful pointers and feedback.
• The MuJoCo team for the development of the MuJoCo physics engine and their support throughout the project.

License and Disclaimer

MuJoco Menagerie's license can be found here. Soundfont licensing information can be found here. MIDI licensing information can be found here. All other code is licensed under an Apache-2.0 License.

This is not an officially supported Google product.