https://github.com/google-deepmind/dm_robotics
Libraries, tools and tasks created and used at DeepMind Robotics.
https://github.com/google-deepmind/dm_robotics
Last synced: 12 days ago
JSON representation
Libraries, tools and tasks created and used at DeepMind Robotics.
- Host: GitHub
- URL: https://github.com/google-deepmind/dm_robotics
- Owner: google-deepmind
- License: apache-2.0
- Created: 2021-05-28T13:57:55.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2024-12-09T14:43:04.000Z (7 months ago)
- Last Synced: 2025-05-23T07:48:11.281Z (about 1 month ago)
- Language: Python
- Homepage:
- Size: 91.7 MB
- Stars: 371
- Watchers: 21
- Forks: 42
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
README
# `dm_robotics`: Libraries, tools, and tasks created and used for Robotics research at DeepMind.
## Package overview
| Package | Summary |
| ---- | ---- |
| [Transformations](py/transformations/README.md) | Rigid body transformations |
| [Geometry](py/geometry/README.md) | Scene and Robot geometry primitives |
| [Vision](py/vision/README.md) | Visual blob detection and tracking |
| [AgentFlow](py/agentflow/README.md) | Reinforcement Learning agent composition library |
| [Manipulation](py/manipulation/README.md) | "RGB" object meshes for manipulation tasks |
| [MoMa](py/moma/README.md) | Manipulation environment definition library, for simulated and real robots |
| [Controllers](cpp/controllers/README.md) | QP-optimization based cartesian controller |
| [Controller Bindings](cpp/controllers_py/README.md) | Python bindings for the controller |
| [Least Squares QP](cpp/least_squares_qp/README.md) | QP task definition and solver |
## Installation
These libraries are distributed on PyPI, the packages are:
* `dm_robotics-transformations`
* `dm_robotics-geometry`
* `dm_robotics-vision`
* `dm_robotics-agentflow`
* `dm_robotics-manipulation`
* `dm_robotics-moma`
* `dm_robotics-controllers`
Python versions 3.8, 3.9 and 3.10 are supported.
## Dependencies
`MoMa`, `Manipulation` and `Controllers` depend on MuJoCo, the other packages do not.
See the individual packages for more information on their dependencies.
## Building
To build and test the libraries, run `build.sh`. This script assumes:
* [`dm_control`](https://github.com/deepmind/dm_control) is installed.
* cmake version >= 3.20.2 is installed.
* Python 3.8, 3.9 or 3.10 and system headers are installed.
* GCC version 9 or later is installed.
* numpy is installed.
The Python libraries are tested with `tox`, the C++ code is built and tested
with `cmake`.
Tox's `distshare` mechanism is used to share the built source distribution
packages between the packages.