> ## 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.

# DROID benchmark

> Real-world manipulation with the DROID dataset

GR00T N1.6-DROID is fine-tuned on the [DROID dataset](https://droid-dataset.github.io/), a large-scale dataset for real-world robotic manipulation. This checkpoint can be deployed on DROID-compatible robot hardware.

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

## Deployment

### Setup inference server

<Steps>
  <Step title="Start policy server">
    On a machine with a sufficiently powerful GPU, start the policy server from the root folder of the repository:

    ```bash theme={null}
    uv run python gr00t/eval/run_gr00t_server.py \
        --embodiment-tag OXE_DROID \
        --use_sim_policy_wrapper \
        --model-path=nvidia/GR00T-N1.6-DROID
    ```
  </Step>
</Steps>

### Setup robot control

<Steps>
  <Step title="Install DROID package">
    Install the DROID package on the robot control laptop/workstation following the [official instructions](https://droid-dataset.github.io/droid/software-setup/host-installation.html#configuring-the-laptopworkstation).
  </Step>

  <Step title="Install GR00T dependencies">
    Install additional dependencies for the GR00T control script in the DROID environment:

    ```bash theme={null}
    pip install tyro moviepy==1.0.3 pydantic numpy==1.26.4
    ```
  </Step>

  <Step title="Configure cameras">
    Enter the camera IDs for your ZED cameras in `examples/DROID/main_gr00t.py`.
  </Step>

  <Step title="Start control script">
    Run the control script with your chosen external camera:

    ```bash theme={null}
    python examples/DROID/main_gr00t.py --external_camera="left"  # or "right"
    ```
  </Step>
</Steps>

## Hardware requirements

For the DROID setup, you'll need:

* GPU machine for running the policy server (RTX 4090, H100, or similar)
* DROID-compatible robot hardware
* ZED cameras configured as per DROID specifications
* Network connection between control laptop and GPU server

## Dataset information

The [DROID dataset](https://droid-dataset.github.io/) provides:

* Large-scale real-world manipulation demonstrations
* Multi-camera observations
* Diverse manipulation tasks
* Standardized data format compatible with GR00T's LeRobot schema