https://github.com/qgallouedec/panda-gym

Set of robotic environments based on PyBullet physics engine and gymnasium.
https://github.com/qgallouedec/panda-gym

artificial-intelligence deep-learning franka-emika machine-learning python reinforcement-learning robotics

Last synced: about 1 month ago
JSON representation

Set of robotic environments based on PyBullet physics engine and gymnasium.

• Host: GitHub
• URL: https://github.com/qgallouedec/panda-gym
• Owner: qgallouedec
• License: mit
• Created: 2020-09-13T18:13:39.000Z (almost 4 years ago)
• Default Branch: master
• Last Pushed: 2023-12-18T20:45:52.000Z (6 months ago)
• Last Synced: 2024-05-09T10:23:13.905Z (about 2 months ago)
• Topics: artificial-intelligence, deep-learning, franka-emika, machine-learning, python, reinforcement-learning, robotics
• Language: Python
• Homepage:
• Size: 32.4 MB
• Stars: 453
• Watchers: 7
• Forks: 97
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-deep-reinforcement-learning - qgallouedec/panda-gym
• awesome-multi-step-manipulation - qgallouedec/panda-gym - > pre-trained model on [rl-baselines3-zoo](https://github.com/DLR-RM/rl-baselines3-zoo) (Core Area / Good Environment to Start)
• awesome-simulation - panda-gym - OpenaAI Gym Franka Emika Panda robot environment based on PyBullet. ([PyBullet](https://github.com/bulletphysics/bullet3))

README

        
# panda-gym

Set of robotic environments based on PyBullet physics engine and gymnasium.

[![PyPI version](https://img.shields.io/pypi/v/panda-gym.svg?logo=pypi&logoColor=FFE873)](https://pypi.org/project/panda-gym/)

[![Downloads](https://static.pepy.tech/badge/panda-gym)](https://pepy.tech/project/panda-gym)

[![GitHub](https://img.shields.io/github/license/qgallouedec/panda-gym.svg)](LICENSE.txt)

[![build](https://github.com/qgallouedec/panda-gym/actions/workflows/build.yml/badge.svg?branch=master)](https://github.com/qgallouedec/panda-gym/actions/workflows/build.yml)

[![codecov](https://codecov.io/gh/qgallouedec/panda-gym/branch/master/graph/badge.svg?token=pv0VdsXByP)](https://codecov.io/gh/qgallouedec/panda-gym)

[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

[![arXiv](https://img.shields.io/badge/cs.LG-arXiv%3A2106.13687-B31B1B.svg)](https://arxiv.org/abs/2106.13687)

## Documentation

Check out the [documentation](https://panda-gym.readthedocs.io/en/latest/).

## Installation

### Using PyPI

```bash

pip install panda-gym

```

### From source

```bash

git clone https://github.com/qgallouedec/panda-gym.git

pip install -e panda-gym

```

## Usage

```python

import gymnasium as gym

import panda_gym

env = gym.make('PandaReach-v3', render_mode="human")

observation, info = env.reset()

for _ in range(1000):

    action = env.action_space.sample() # random action

    observation, reward, terminated, truncated, info = env.step(action)

    if terminated or truncated:

        observation, info = env.reset()

env.close()

```

You can also [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/qgallouedec/panda-gym/blob/master/examples/PickAndPlace.ipynb)

## Environments

|                                  |                                                |

| :------------------------------: | :--------------------------------------------: |

|         `PandaReach-v3`          |                 `PandaPush-v3`                 |

| ![PandaReach-v3](docs/_static/img/reach.png) |         ![PandaPush-v3](docs/_static/img/push.png)         |

|         `PandaSlide-v3`          |             `PandaPickAndPlace-v3`             |

| ![PandaSlide-v3](docs/_static/img/slide.png) | ![PandaPickAndPlace-v3](docs/_static/img/pickandplace.png) |

|         `PandaStack-v3`          |              `PandaFlip-v3`                    |

| ![PandaStack-v3](docs/_static/img/stack.png) | ![PandaFlip-v3](docs/_static/img/flip.png) |

## Baselines results

Baselines results are available in [rl-baselines3-zoo](https://github.com/DLR-RM/rl-baselines3-zoo) and the pre-trained agents in the [Hugging Face Hub](https://huggingface.co/sb3).

## Citation

Cite as

```bib

@article{gallouedec2021pandagym,

  title        = {{panda-gym: Open-Source Goal-Conditioned Environments for Robotic Learning}},

  author       = {Gallou{\'e}dec, Quentin and Cazin, Nicolas and Dellandr{\'e}a, Emmanuel and Chen, Liming},

  year         = 2021,

  journal      = {4th Robot Learning Workshop: Self-Supervised and Lifelong Learning at NeurIPS},

}

```

Environments are widely inspired from [OpenAI Fetch environments](https://openai.com/blog/ingredients-for-robotics-research/).