MotionBricks 安装教程：克隆、权重、第一个演示

环境要求

• Python 3.10+
• CUDA 可用 GPU
• Git LFS —— 权重、网格与展示 GIF 均由 LFS 跟踪

MotionBricks 是 GR00T-WholeBodyControl 的子项目：克隆父仓库后在 motionbricks/ 目录内工作。

1 · 克隆仓库

git lfs install

父仓库默认跳过 MotionBricks 预训练权重，所以普通单仓库克隆不会自动下载额外的约 2.2 GB 权重文件。仅需源码（例如要在自己的数据上训练）时这样克隆：

git clone https://github.com/NVlabs/GR00T-WholeBodyControl.git
cd GR00T-WholeBodyControl/motionbricks

2 · 显式拉取权重

运行交互式演示需要权重以及 G1 网格。在仓库根目录：

git clone https://github.com/NVlabs/GR00T-WholeBodyControl.git
cd GR00T-WholeBodyControl
git lfs pull --include="motionbricks/out/**" --exclude=""
git lfs pull --include="motionbricks/assets/skeletons/g1/meshes/**" --exclude=""  # needed for interactive demo
cd motionbricks

3 · 核对文件确实下载完成

这一步很多人跳过，然后花一小时排错。权重文件必须是真实大小：

ls -lh out/G1-clip.ckpt                                     # ~7.5 MB
ls -lh out/motionbricks_vqvae/version_1/checkpoints/*.ckpt  # ~273 MB
ls -lh out/motionbricks_pose/version_1/checkpoints/*.ckpt   # ~1.6 GB
ls -lh out/motionbricks_root/version_1/checkpoints/*.ckpt   # ~391 MB

git lfs pull --include="motionbricks/out/**" --exclude=""

4 · 安装依赖

# Create environment
conda create -n motionbricks python=3.10 -y
conda activate motionbricks

# Install dependencies
pip install -e .

# Linux only: needed for keyboard input and MuJoCo key-grab workaround
pip install pynput python-xlib

5 · 运行交互式 G1 演示

DISPLAY=:1 python scripts/interactive_demo_g1.py

这会打开 MuJoCo 查看器并加载 G1 机器人；用键盘实时驱动它，按住鼠标左键拖动可旋转观察方向。前缀 DISPLAY=:1 假设 X11 会话在 GPU 1 的显示上——请按你的环境调整或去掉。完整键位表与相机操作见G1 演示指南。

已知问题（README 原文）

• Linux/X11 only: The keyboard key-grab workaround requires X11 (python-xlib). On Wayland, macOS, or Windows, some MuJoCo keyboard shortcuts may conflict with the controller keys. Keep the terminal focused (not the MuJoCo window) as a workaround.
• PYTORCH_JIT=0 disables key grabs: Running with PYTORCH_JIT=0 interferes with the X11 key-grab workaround. If you need PYTORCH_JIT=0, keep the terminal focused instead.
• Keyboard package differs by OS: The pynput package is required for keyboard input on Linux/macOS. On Windows, the keyboard package is used instead.