dora-rs
/
dora
Not watched
1
0
Fork 0
Code
Releases 124 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branch: main
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'main'
${ noResults }
dora/examples/aloha/INSTALLATION.md

3.5 kB
Raw Permalink Blame History

Dora pipeline Robots

Aloha is a bi manual robot that can be teleoperated using a similar arm. This repository contains
the Dora pipeline to manipulate arms, cameras, and record/replay episodes with LeRobot.

Installation

Dataflow-oriented robotic application (Dora) is a framework that makes creation of robotic applications fast and simple.
See Dora repository.

Please read the instructions carefully before installing the required software and environment to run the robot.

You must install Dora before attempting to run theAloha Robot pipeline. Here are the steps to install Dora:

  • Install Rust by following the instructions at Rustup. (You may need to install Visual Studio C++
    build tools on Windows.)
  • Install Dora by running the following command:
cargo install dora-cli

Now you're ready to run Rust dataflow applications! We decided to only make Python dataflow for Aloha Robot, so
you may need to setup your Python environment:

  • Install Python 3.12 or later by following the instructions at Python.
  • Clone this repository by running the following command:
git clone https://github.com/dora-rs/dora
  • Open a bash terminal and navigate to the repository by running the following command:
cd dora
  • Create a virtual environment by running the following command (you can find where is all your pythons executable with
    the command whereis python3 on Linux, on default for Windows it's located
    in C:\Users\<User>\AppData\Local\Programs\Python\Python3.12\python.exe)):
path_to_your_python3_executable -m venv venv
  • Activate the virtual environment and install the required Python packages by running the following command:
# If you are using a custom environment, you will have to activate it before running the command
source [your_custom_env_bin]/activate

# If you followed the installation instructions, you can run the following command
source venv/bin/activate # On Linux
source venv/Scripts/activate # On Windows bash
venv\Scripts\activate.bat # On Windows cmd
venv\Scripts\activate.ps1 # On Windows PowerShell

pip install -r examples/so100/requirements.txt

If you want to install the required Python packages in development mode, you can run the following command, but you will
have to avoid using dora build during execution procedure:

pip install -r examples/aloha/development.txt # You **MUST** be inside dora to run this command

Note: You're totally free to use your own Python environment, a Conda environment, or whatever you prefer, you will
have to activate
your custom python environment before running dora up && dora start [graph].yml.

In order to record episodes, you need ffmpeg installed on your system. You can download it from
the official website. If you're on Windows, you can download the latest build
from here. You can
extract the zip file and add the bin folder to your PATH.
If you're on Linux, you can install ffmpeg using the package manager of your distribution. (
e.g sudo apt install ffmpeg on Ubuntu, brew install ffmpeg on macOS)

Acknowledgement

This work is inspired from tonyzhaozh/aloha and we're trying to bring perfornance
improvement.

License

This library is licensed under the Apache License 2.0.