polymetis

KO | EN

gitlite — search

#javascript #python #hacktoberfest #go #android #machine-learning #deep-learning #windows #cli #awesome-list #pytorch #ios #mcp #openai

(★ 94)

Write PyTorch controllers, test them in simulation, and seamlessly transfer to real-time hardware.

polymetis 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## **Note:** As part of FAIR Robotic's unified platform effort, the source of truth is now at our [monorepo](https://github.com/facebookresearch/droidlet/tree/main/polymetis) containing Polymetis, Droidlet, and PyRobot.

# [Polymetis](https://polymetis-docs.github.io/): a real-time PyTorch controller manager

[![CircleCI](https://circleci.com/gh/facebookresearch/polymetis/tree/main.svg?style=svg&circle-token=862dc8467344f7ac54f9a706e99c6e2ab57f067f)](https://circleci.com/gh/facebookresearch/polymetis/tree/main)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

> **Polymetis**: adj., Ancient Greek. _Clever in many ways._ Applied to Odysseus by Homer in the _Odyssey_.

**Write [PyTorch](http://pytorch.org/) controllers for robots, test them in simulation, and seamlessly transfer to real-time hardware.**

**Polymetis** powers robotics research at [Facebook AI Research](https://ai.facebook.com/). If you want to write your robot policies in PyTorch for simulation and immediately transfer them to high-frequency (1kHz) policies on real-time hardware (e.g. Franka Panda), read on!

## Features

- **Unified simulation & hardware interface**: Write all your robot controllers just once -- immediately transfer them to real-time hardware. You can even train neural network policies using reinforcement learning in simulation and transfer them to hardware, with just a single configuration toggle.
- **Write your own robot controllers:** Use the building blocks in our [TorchControl](https://polymetis-docs.github.io/torchcontrol-doc.html) library to write complex robot controllers, including operational space control. Take advantage of our wrapping of the [Pinocchio](https://github.com/stack-of-tasks/pinocchio) dynamics library for your robot dynamics.
- **Drop-in replacement for [PyRobot](https://pyrobot.org/)**: If you're already using PyRobot, you can use the exact same interface, but immediately gain access to arbitrary, custom high-frequency robot controllers.

## Get started

To get started, you only need one line:

```
conda install -c fair-robotics -c conda-forge polymetis
```

You can immediately start running the [example scripts](https://github.com/facebookresearch/polymetis/tree/main/examples) in both simulation and hardware. See [installation](https://polymetis-docs.github.io/installation.html) and [usage](https://polymetis-docs.github.io/usage.html) documentation for details.

## Documentation

All documentation on the [website](https://polymetis-docs.github.io/). Includes:

- Guides on setting up your [Franka Panda](https://frankaemika.github.io/docs/libfranka.html) hardware for real-time control
- How to quickly get started in [PyBullet](https://github.com/bulletphysics/bullet30) simulation
- Writing developing your own custom controllers in PyTorch
- Full [autogenerated documentation](https://polymetis-docs.github.io/modules.html)

## Contributing

See the [CONTRIBUTING](CONTRIBUTING.md) file for how to help out. [Make an issue](https://github.com/facebookresearch/polymetis/issues/new/choose) for bugs and feature requests, or contribute a new robot controller by making a [pull request](https://github.com/facebookresearch/polymetis/pulls)!

## License
Polymetis is MIT licensed, as found in the [LICENSE](LICENSE) file.

polymetis

polymetis 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

polymetis

polymetis 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README