Environment Setup (Ubuntu)
The black leader arm uses a 5V6A power adapter
The white follower arm uses a 12V5A power adapter
Install Miniconda
https://www.anaconda.com/download
Change the pip Source
Shell
pip config set global.index-url https://mirrors.aliyun.com/pypi/simpleChange the conda Source
Shell
# Clear the existing .condarc configuration (optional, to avoid conflicts)
echo "" > ~/.condarc
# Write the Tsinghua mirror configuration
cat << EOF > ~/.condarc
channels:
- defaults
show_channel_urls: true
default_channels:
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
custom_channels:
conda-forge: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
msys2: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
bioconda: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
menpo: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
pytorch: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
pytorch-lts: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
simpleitk: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
EOF
# Clear the cache to apply the configuration
conda clean -iCreate a Virtual Environment
Shell
conda create -y -n lerobot python=3.12 -yEnter the Virtual Environment
Shell
conda activate lerobotInstall ffmpeg
Shell
conda install *ffmpeg*=7.1.1 *-c* conda-forge -yVerify the installation was successful
Shell
ffmpeg

Download the Official LeRobot Code Repository
Shell
git clone https://github.com/huggingface/lerobot.gitInstall the Code Repository
Shell
#cd lerobot-main
cd lerobot
pip install -e ".[feetech]"

Verify Successful Installation
Shell
lerobot-info
python
import lerobot
lerobot.__version__
import torch
torch.cuda.is_available()
import scservo_sdkResults of Running on the 4090 Host


Results of Running on an NVIDIA DGX Spark


