# TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
[![License: MIT](https://img.shields.io/github/license/facebookresearch/tacto)](LICENSE)
[![PyPI](https://img.shields.io/pypi/v/tacto)](https://pypi.org/project/tacto/)
[![CircleCI](https://circleci.com/gh/facebookresearch/tacto.svg?style=shield)](https://circleci.com/gh/facebookresearch/tacto)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
<a href="https://digit.ml/">
<img height="20" src="/website/static/img/digit-logo.svg" alt="DIGIT-logo" />
</a>
<img src="/website/static/img/teaser.jpg?raw=true" alt="TACTO Simulator" />
This package provides a simulator for vision-based tactile sensors, such as [DIGIT](https://digit.ml).
It provides models for the integration with PyBullet, as well as a renderer of touch readings.
For more information refer to the corresponding paper [TACTO: A Fast, Flexible, and Open-source Simulator for High-resolution Vision-based Tactile Sensors](https://arxiv.org/abs/2012.08456).
NOTE: the simulator is not meant to provide a physically accurate dynamics of the contacts (e.g., deformation, friction), but rather relies on existing physics engines.
**For updates and discussions please join the #TACTO channel at the [www.touch-sensing.org](https://www.touch-sensing.org/) community.**
## Installation
The preferred way of installation is through PyPi:
```bash
pip install tacto
```
Alternatively, you can manually clone the repository and install the package using:
```bash
git clone https://github.com/facebookresearch/tacto.git
cd tacto
pip install -e .
```
## Content
This package contain several components:
1) A renderer to simulate readings from vision-based tactile sensors.
2) An API to simulate vision-based tactile sensors in PyBullet.
3) Mesh models and configuration files for the [DIGIT](https://digit.ml) and Omnitact sensors.
## Usage
Additional packages ([torch](https://github.com/pytorch/pytorch), [gym](https://github.com/openai/gym), [pybulletX](https://github.com/facebookresearch/pybulletX)) are required to run the following examples.
You can install them by `pip install -r requirements/examples.txt`.
For a basic example on how to use TACTO in conjunction with PyBullet look at [TBD],
For an example of how to use just the renderer engine look at [examples/demo_render.py](examples/demo_render.py).
For advanced examples of how to use the simulator with PyBullet look at the [examples folder](examples).
* [examples/demo_pybullet_digit.py](examples/demo_pybullet_digit.py): rendering RGB and Depth readings with a [DIGIT](https://digit.ml) sensor.
<img src="/website/static/img/demo_digit.gif?raw=true" alt="Demo DIGIT" />
* [examples/demo_pybullet_allegro_hand.py](examples/demo_pybullet_omnitact.py): rendering 4 DIGIT sensors on an Allegro Hand.
<img src="/website/static/img/demo_allegro.gif?raw=true" alt="Demo Allegro" />
* [examples/demo_pybullet_omnitact.py](examples/demo_pybullet_omnitact.py): rendering RGB and Depth readings with a [OmniTact](https://arxiv.org/pdf/2003.06965.pdf) sensor.
<img src="/website/static/img/demo_omnitact.gif?raw=true" alt="Demo OmniTact" />
* [examples/demo_pybullet_grasp.py](examples/demo_grasp.py): mounted on parallel-jaw grippers and grasping objects with different configurations.
<img src="/website/static/img/demo_grasp.gif?raw=true" alt="Demo Grasp" />
* [examples/demo_pybullet_rolling.py](examples/demo_rolling.py): rolling a marble with two DIGIT sensors.
<img src="/website/static/img/demo_rolling.gif?raw=true" alt="Demo Rolling" />
* [examples/demo_pybullet_digit_shadow.py](examples/demo_pybullet_digit_shadow.py): enable shadow rendering.
<img src="/website/static/img/demo_shadow.gif?raw=true" alt="Demo Shadow" />
### Headless Rendering
NOTE: the renderer requires a screen. For rendering headless, use the "EGL" mode with GPU and CUDA driver or "OSMESA" with CPU.
See [PyRender](https://pyrender.readthedocs.io/en/latest/install/index.html) for more details.
Additionally, install the patched version of PyOpenGL via,
```
pip install git+https://github.com/mmatl/pyopengl.git@76d1261adee2d3fd99b418e75b0416bb7d2865e6
```
You may then specify which engine to use for headless rendering, for example,
```
import os
os.environ["PYOPENGL_PLATFORM"] = "osmesa" # osmesa cpu rendering
```
## Operating System
We recommend to conduct experiments on **Ubuntu**.
For **macOS**, there exists some visualization problem between pybullet.GUI and pyrender as we know of. Please let us know if it can be resolved, and we will share the information at the repo!
## License
This project is licensed under MIT license, as found in the [LICENSE](LICENSE) file.
## Citing
If you use this project in your research, please cite:
```BibTeX
@Article{Wang2022TACTO,
author = {Wang, Shaoxiong and Lambeta, Mike and Chou, Po-Wei and Calandra, Roberto},
title = {{TACTO}: A Fast, Flexible, and Open-source Simulator for High-resolution Vision-based Tactile Sensors},
journal = {IEEE Robotics and Automation Letters (RA-L)},
year = {2022},
volume = {7},
number = {2},
pages = {3930--3937},
issn = {2377-3766},
doi = {10.1109/LRA.2022.3146945},
url = {https://arxiv.org/abs/2012.08456},
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
基于视觉的触觉传感器模拟器_python_代码_相关文件_下载
共187个文件
stl:55个
py:30个
dae:26个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 14 浏览量
2022-07-13
18:40:27
上传
评论
收藏 35.37MB ZIP 举报
温馨提示
TACTO:用于高分辨率视觉触觉传感器的快速、灵活和开源模拟器 执照:麻省理工学院 派皮 圈子CI 代码风格:黑色 数字标志 战术模拟器 该软件包为基于视觉的触觉传感器(例如DIGIT )提供模拟器。它提供了与 PyBullet 集成的模型,以及触摸读数的渲染器。有关更多信息,请参阅相应的论文TACTO: A Fast, Flexible, and Open-source Simulator for High-resolution Vision-based Tactile Sensors。 注意:模拟器并不意味着提供物理上精确的接触动力学(例如,变形、摩擦),而是依赖于现有的物理引擎。 更多详情、使用方法,请下载后细读README.md文件
资源推荐
资源详情
资源评论
收起资源包目录
基于视觉的触觉传感器模拟器_python_代码_相关文件_下载
(187个子文件)
l4.DAE 4.69MB
l4.DAE 4.69MB
l0.DAE 3.59MB
l0.DAE 3.59MB
pedestal.DAE 2.53MB
pedestal.DAE 2.53MB
l5.DAE 2.02MB
l5.DAE 2.02MB
l6.DAE 1.9MB
l6.DAE 1.9MB
head.DAE 1.32MB
head.DAE 1.32MB
base.DAE 977KB
base.DAE 977KB
l2.DAE 639KB
l2.DAE 639KB
l3.DAE 604KB
l3.DAE 604KB
l1.DAE 462KB
l1.DAE 462KB
l6.DAE 271KB
l6.DAE 271KB
l1.DAE 227KB
l1.DAE 227KB
l0.DAE 216KB
l0.DAE 216KB
.flake8 201B
demo_grasp.gif 4.98MB
demo_shadow.gif 4.35MB
demo_allegro.gif 3.07MB
demo_digit.gif 2.52MB
demo_rolling.gif 2.18MB
demo_omnitact.gif 1.18MB
checker_huge.gif 2KB
checker_huge.gif 2KB
.gitignore 1KB
.gitignore 5B
teaser.jpg 66KB
bg_digit_240_320.jpg 13KB
LICENSE 1KB
LICENSE 1KB
LICENSE 1KB
LICENSE 1KB
LICENSE 1KB
LICENSE 1KB
CODE_OF_CONDUCT.md 3KB
CONTRIBUTING.md 1KB
README.md 1KB
README.md 1KB
CHANGELOG.md 45B
README.md 5KB
textured_sphere_smooth.mtl 161B
textured_sphere_smooth.mtl 161B
depthmap.npy 19KB
color-osmesa-ground-truth.npy 14KB
textured_sphere_smooth.obj 109KB
textured_sphere_smooth.obj 109KB
cube.obj 836B
cube.obj 836B
allegro_hand_left.pdf 12KB
allegro_hand_right.pdf 12KB
renderer.py 19KB
train.py 13KB
RollingEnv.py 10KB
grasp_data_collection.py 9KB
sensor.py 9KB
sawyer_gripper_env.py 7KB
robot.py 6KB
sawyer_gripper.py 5KB
draw.py 3KB
demo_sawyer_gripper_env.py 2KB
draw_rolling.py 2KB
Rolling.py 2KB
BO_rolling_collect.py 2KB
demo_pybullet_rolling.py 2KB
demo_pybullet_digit_shadow.py 2KB
setup.py 2KB
benchmark.py 2KB
demo_pybullet_allegro_hand.py 1KB
demo_pybullet_omnitact.py 1KB
demo_pybullet_digit.py 1KB
test_render_from_depth_osmesa.py 1KB
demo_pybullet_grasp.py 1KB
demo_render.py 1KB
camera.py 1KB
timeit.py 846B
__init__.py 812B
test_random_normal_generator.py 800B
random_normal_generator.py 701B
test_timeit.py 465B
noxfile.py 304B
allegro_hand_config.rviz 7KB
build_desc.sh 2KB
pedestal.STL 1.57MB
pedestal.STL 1.57MB
digit.STL 1.39MB
digit.STL 1.39MB
digit.STL 1.39MB
digit.STL 1.39MB
digit.STL 1.39MB
共 187 条
- 1
- 2
资源评论
快撑死的鱼
- 粉丝: 1w+
- 资源: 9156
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功