LeRobot Robot Arm Tutorial

This tutorial has been updated to December 15th, and you can choose to follow the latest version of the official documentation for operation . For the specific tutorial in the official documentation, please refer to this link . If you need files such as URDF, please refer to this link . For the old version of September 15th, please refer to this link . The running codes of SO-ARM101 and SO-ARM100 are mutually compatible.

A. Tutorial Instructions

The Pro version's black active arm uses a 5V6A power adapter, while the white passive arm uses a 12V5A power adapter! ​

Servo installation and servo angle calibration should be completed in advance, and you can refer to the official assembly tutorial , which is not covered in this tutorial!

Refer to the assembly tutorial for details Lerobot SO-ARM101 Assembly Tutorial

If the servo is not configured or the robotic arm is not assembled, please first follow the instructions in this README . It includes a bill of materials, links to obtain parts, instructions for 3D printing parts, and suggestions if you are printing for the first time or do not have a 3D printer.

Let's first start from installing the LeRobot environment.

B. Environment Preparation

For Ubuntu X86:

•
Ubuntu 22.04​

•
CUDA 12+​

•
Python 3.10​

•
Torch 2.6+​

For Jetson Orin:

•
Jetson Jetpack 6.0+​

•
Python 3.10​

•
Torch 2.5.0a0+872d972e41​

Installation and Construction Guide for RealSense Depth Camera D400 Series

RealSense Depth Camera D400 Series Data Sheet

Install LeRobot Environment

1. Install the Miniconda environment:

You need to install environments such as pytorch and torchvision according to your CUDA version. ​

1.
For Jetson: ​

代码块

wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh​
chmod +x Miniconda3-latest-Linux-aarch64.sh​
bash ~/Miniconda3-latest-Linux-aarch64.sh​
source ~/.bashrc​

Alternatively, for X86 Ubuntu 22.04:

代码块

mkdir -p ~/miniconda3​
cd miniconda3​
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh​
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3​
rm ~/miniconda3/miniconda.sh​
source ~/miniconda3/bin/activate​
conda init --all​

2. Under the directory where you want to deploy (create, for example: lerobot), create and activate a new conda environment for lerobot: ​

Please do not create or import the lerobot project under the ~/miniconda3 directory​

代码块

conda create -y -n lerobot python=3.10

3. Then activate your conda environment (you need to do this every time you open the terminal to use lerobot!):​

代码块

conda activate lerobot

4. Clone LeRobot:

代码块

git clone https://github.com/Juxi-Technology/lerobot.git

💡

You can choose to follow the latest version: https://github.com/huggingface/lerobot.git

LeRobot Robot Arm Tutorial​

LeRobot Robot Arm Tutorial