> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/NVIDIA/Isaac-GR00T/llms.txt
> Use this file to discover all available pages before exploring further.

# Unitree G1 locomanipulation

> Whole-body control tasks for Unitree G1 humanoid robot

This benchmark tests loco-manipulation capabilities on the Unitree G1 humanoid robot using whole-body control in MuJoCo. Tasks require navigation, object manipulation, and maintaining balance across the entire body.

## Benchmark results

Checkpoint: [nvidia/GR00T-N1.6-G1-PnPAppleToPlate](https://huggingface.co/nvidia/GR00T-N1.6-G1-PnPAppleToPlate)

| Task            | Success rate |
| --------------- | ------------ |
| PnPAppleToPlate | 58%          |

<Warning>
  This task exhibits high evaluation variance. Fluctuations of ±15% are expected across different evaluation runs.
</Warning>

## Fine-tuning

You can skip this section and directly evaluate with the provided checkpoint above.

<Steps>
  <Step title="Clone dataset repository">
    Clone without downloading all files:

    ```bash theme={null}
    cd examples/GR00T-WholeBodyControl

    git clone --filter=blob:none --no-checkout \
        https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-GR00T-X-Embodiment-Sim

    cd PhysicalAI-Robotics-GR00T-X-Embodiment-Sim
    ```
  </Step>

  <Step title="Setup sparse checkout">
    Download only the G1 dataset:

    ```bash theme={null}
    # Initialize sparse-checkout
    git sparse-checkout init --cone

    # Select folder to download
    git sparse-checkout set unitree_g1.LMPnPAppleToPlateDC

    # Checkout files
    git checkout

    # Pull LFS files
    git lfs pull
    ```
  </Step>

  <Step title="Run fine-tuning">
    ```bash theme={null}
    cd ../../../
    uv run bash examples/GR00T-WholeBodyControl/finetune_g1.sh
    ```
  </Step>
</Steps>

## Evaluation

### Setup environment

Install the required dependencies (only needs to be done once):

```bash theme={null}
apt-get update
apt-get install libegl1-mesa-dev libglu1-mesa
bash gr00t/eval/sim/GR00T-WholeBodyControl/setup_GR00T_WholeBodyControl.sh
```

### Run evaluation

<Steps>
  <Step title="Start policy server">
    In Terminal 1, choose one of the following options:

    **Option 1: Local fine-tuned checkpoint**

    ```bash theme={null}
    uv run python gr00t/eval/run_gr00t_server.py \
        --model-path /tmp/g1_finetune/checkpoint-10000/ \
        --embodiment-tag UNITREE_G1 \
        --use-sim-policy-wrapper
    ```

    **Option 2: Remote fine-tuned checkpoint**

    ```bash theme={null}
    uv run python gr00t/eval/run_gr00t_server.py \
        --model-path nvidia/GR00T-N1.6-G1-PnPAppleToPlate \
        --embodiment-tag UNITREE_G1 \
        --use-sim-policy-wrapper
    ```
  </Step>

  <Step title="Start evaluation client">
    In Terminal 2:

    ```bash theme={null}
    gr00t/eval/sim/GR00T-WholeBodyControl/GR00T-WholeBodyControl_uv/.venv/bin/python \
        gr00t/eval/rollout_policy.py \
        --n_episodes 10 \
        --max_episode_steps=1440 \
        --env_name gr00tlocomanip_g1_sim/LMPnPAppleToPlateDC_G1_gear_wbc \
        --n_action_steps 20 \
        --n_envs 5
    ```
  </Step>
</Steps>

## Available tasks

* `gr00tlocomanip_g1_sim/LMPnPAppleToPlateDC_G1_gear_wbc` - Pick apple and place on plate with dynamic constraints

## Real robot deployment

When working with real Unitree G1 robot data, you have two options:

### Option 1: Using GR00T-WholeBodyControl

If you collected data using [GR00T-WholeBodyControl](https://github.com/NVlabs/GR00T-WholeBodyControl), leverage the `UNITREE_G1` embodiment tag. This is a pre-trained embodiment with models already trained on in-the-wild Unitree G1 datasets.

### Option 2: Custom whole-body controller

If your data was collected using a different whole-body controller, create and fine-tune with a `NEW_EMBODIMENT` tag. This allows you to define a custom embodiment tailored to your specific controller setup.

See the [fine-tune new embodiment guide](/getting-started/finetune-new-embodiment) for detailed instructions.