Parameters
ImageInput
required
Current camera frame as file path, URL, PIL Image, or numpy array.
Union[np.ndarray, list]
required
Robot joint state as numpy array or list (7 arm joints + gripper).
str
required
Natural-language task instruction string.
Optional[ImageInput]
Previous camera frame, or None on the first call of an episode.
float | None
Optional timeout in seconds for the HTTP request.
Returns
Action dictionary containing:- “actions”: numpy array of shape (64, 8) with predicted actions