Rigid Body Dynamics Library using Tensorflow.
Project description
tf_rbdl
tf_rbdl is a python library that contains some essential rigid body dynamics algorithms such as forward dynamics and inverse dynamics using Tensorflow. It uses Lie Group representation and provides kinematic and dynamics quatities of rigid body systems.
Examples
General Usages
Kinematics
- Function usages
- Inverse kinematics control
Dynamics
- Function usages
- Inverse dynamics control
Computation Efficiency
Running examples/computation_time.py evaluates inverse dynamics for 5 batches and 500 epochs.
Single Input w/ Autograph | Single Input w/o Autograph | Batch Input w/ Autograph | Batch Input w/o Autograph | |
---|---|---|---|---|
CPU | 3.82 (s) | 71.68 (s) | 0.95 (s) | 13.02 (s) |
GPU | 8.53 (s) | 89.75 (s) | 2.46 (s) | 18.27 (s) |
Installation
You can install tf_rbd
from PyPI:
$ pip install tf_rbdl
or, you can also install from source:
$ git clone https://github.com/junhyeokahn/tf_rbdl
$ cd tf_rbdl
$ pip install -e .
Todo
- Write examples
- Parse urdf
Acknowledgement
This library is based on the book Modern Robotics and the code.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tf_rbdl-0.1.0.tar.gz
(12.1 kB
view hashes)
Built Distribution
Close
Hashes for tf_rbdl-0.1.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 414b6701a94b6c5ead8e2d543078608473be556d9db5a8aaf08de42e99b71c00 |
|
MD5 | a9c21da2f7b9ba2b2c99e86227ab2844 |
|
BLAKE2b-256 | f78b1579d3c4f7dfe5189a04630971fb4592036a3a344007bee569e768ee022c |