Skip to content

vllm_omni.diffusion.models.dreamzero.transform.droid

DROID dataset transform.

DROID uses 1-indexed exterior cameras, 3 views total (OXE_DROID embodiment). Stitching layout (same as RoboArena — both are OXE_DROID): ┌─────────────────────────┐ │ wrist (2x width) │ ← pixel-repeat along width ├────────────┬────────────┤ │ left ext │ right ext │ └────────────┴────────────┘

DroidTransform

Bases: RobotPolicyTransform

Transform for DROID dataset (OXE_DROID embodiment).

DROID observation keys (1-indexed exterior cameras): observation/exterior_image_1_left → left exterior observation/exterior_image_2_left → right exterior observation/wrist_image_left → wrist

ACTION_DIM class-attribute instance-attribute

ACTION_DIM = 8

EMBODIMENT_NAME class-attribute instance-attribute

EMBODIMENT_NAME = 'oxe_droid'

IMAGE_KEY_MAP class-attribute instance-attribute

IMAGE_KEY_MAP = {
    "observation/exterior_image_1_left": "images/exterior_0",
    "observation/exterior_image_2_left": "images/exterior_1",
    "observation/wrist_image_left": "images/wrist",
}