> ## 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.

# Embodiment tags

> Explanation of embodiment tags and supported robots

Embodiment tags are used to identify the robot embodiment in your data. They enable GR00T to apply embodiment-specific configurations and handle cross-embodiment training.

## Naming convention

Embodiment tags follow the pattern:

```
<dataset>_<robot_name>
```

When using multiple datasets for the same robot (e.g., sim GR1 and real GR1), you can drop the dataset name and use only the robot name.

## Pretrain embodiment tags

These embodiments were included in the base model pretraining:

<ParamField path="ROBOCASA_PANDA_OMRON" type="string" default="robocasa_panda_omron">
  The RoboCasa Panda robot with omron mobile base.
</ParamField>

<ParamField path="GR1" type="string" default="gr1">
  The Fourier GR1 robot.
</ParamField>

## Pre-registered posttrain embodiment tags

These embodiments have ready-to-use configurations for fine-tuning:

<ParamField path="UNITREE_G1" type="string" default="unitree_g1">
  The Unitree G1 robot.
</ParamField>

<ParamField path="LIBERO_PANDA" type="string" default="libero_panda">
  The Libero panda robot.
</ParamField>

<ParamField path="OXE_GOOGLE" type="string" default="oxe_google">
  The Open-X-Embodiment Google robot.
</ParamField>

<ParamField path="OXE_WIDOWX" type="string" default="oxe_widowx">
  The Open-X-Embodiment WidowX robot.
</ParamField>

<ParamField path="OXE_DROID" type="string" default="oxe_droid">
  The Open-X-Embodiment DROID robot with relative joint position actions.
</ParamField>

<ParamField path="BEHAVIOR_R1_PRO" type="string" default="behavior_r1_pro">
  The Behavior R1 Pro robot.
</ParamField>

## Custom embodiments

<ParamField path="NEW_EMBODIMENT" type="string" default="new_embodiment">
  Any new embodiment not included in the pre-registered tags.
</ParamField>

<Info>
  Use `NEW_EMBODIMENT` when fine-tuning on your own robot. You'll need to provide a custom modality configuration.
</Info>

## Using embodiment tags

Embodiment tags are specified in your dataset and during training/inference:

### In your dataset

Specify the embodiment tag when creating `VLAStepData`:

```python theme={null}
from gr00t.data.embodiment_tags import EmbodimentTag
from gr00t.data.types import VLAStepData

step_data = VLAStepData(
    images={"front": [image_array]},
    states={"joint_pos": state_array},
    actions={"joint_pos": action_array},
    text="pick up the cube",
    embodiment=EmbodimentTag.GR1,  # Specify your robot
    is_demonstration=False,
)
```

### During training

Specify the embodiment tag in your training command:

```bash theme={null}
uv run python gr00t/experiment/launch_finetune.py \
    --base-model-path nvidia/GR00T-N1.6-3B \
    --dataset-path <DATASET_PATH> \
    --embodiment-tag UNITREE_G1 \
    --num-gpus 1
```

### During inference

Specify the embodiment tag when loading the policy:

```bash theme={null}
uv run python gr00t/eval/run_gr00t_server.py \
    --embodiment-tag GR1 \
    --model-path nvidia/GR00T-N1.6-3B
```

## Implementation details

Embodiment tags are implemented as an enum in `gr00t/data/embodiment_tags.py:14-61`:

```python theme={null}
from enum import Enum

class EmbodimentTag(Enum):
    ##### Pretrain embodiment tags #####
    ROBOCASA_PANDA_OMRON = "robocasa_panda_omron"
    """
    The RoboCasa Panda robot with omron mobile base.
    """

    GR1 = "gr1"
    """
    The Fourier GR1 robot.
    """

    ##### Pre-registered posttrain embodiment tags #####
    UNITREE_G1 = "unitree_g1"
    """
    The Unitree G1 robot.
    """

    # ... additional embodiments

    # New embodiment during post-training
    NEW_EMBODIMENT = "new_embodiment"
    """
    Any new embodiment.
    """
```

## Cross-embodiment training

GR00T's cross-embodiment architecture allows the model to learn from multiple robot types simultaneously. The embodiment tag is used to:

1. Apply embodiment-specific normalization statistics
2. Load embodiment-specific modality configurations
3. Enable the model to distinguish between different robot morphologies

<Tip>
  When fine-tuning on a new embodiment, the model leverages knowledge from all pretrained embodiments, enabling faster adaptation with less data.
</Tip>

## Next steps

<CardGroup cols={2}>
  <Card title="Modality configs" icon="sliders" href="/concepts/modality-configs">
    Configure data processing for your embodiment
  </Card>

  <Card title="Data format" icon="database" href="/concepts/data-format">
    Prepare your data in the correct format
  </Card>

  <Card title="Fine-tuning guide" icon="graduation-cap" href="/guides/finetuning">
    Fine-tune on your custom embodiment
  </Card>
</CardGroup>