X-VLA：首个适用于任意机器人、任意任务的软提示机器人基础模型

pip install -e .[xvla]

pip install lerobot[xvla]

policy.type=xvla

lerobot-eval \
  --policy.path="lerobot/xvla-libero" \
  --env.type=libero \
  --env.task=libero_spatial,libero_goal,libero_10 \
  --env.control_mode=absolute \
  --eval.batch_size=1 \
  --eval.n_episodes=1 \
  --env.episode_length=800 \
  --seed=142

lerobot-train \
  --dataset.repo_id=YOUR_DATASET \
  --output_dir=./outputs/xvla_training \
  --job_name=xvla_training \
  --policy.path="lerobot/xvla-base" \
  --policy.repo_id="HF_USER/xvla-your-robot" \
  --policy.dtype=bfloat16 \
  --policy.action_mode=auto \
  --steps=20000 \
  --policy.device=cuda \
  --policy.freeze_vision_encoder=false \
  --policy.freeze_language_encoder=false \
  --policy.train_policy_transformer=true \
  --policy.train_soft_prompts=true \

lerobot-train \
  --dataset.repo_id=<USER>/bimanual-so100-handover-cube \
  --output_dir=./outputs/xvla_bimanual \
  --job_name=xvla_so101_training \
  --policy.path="lerobot/xvla-base" \
  --policy.dtype=bfloat16 \
  --policy.repo_id="YOUR_USERNAME/xvla-biso101" \
  --steps=3000 \
  --policy.device=cuda \
  --policy.action_mode=so101_bimanual \
  --policy.freeze_vision_encoder=false \
  --policy.freeze_language_encoder=false \
  --policy.train_policy_transformer=true \
  --policy.train_soft_prompts=true

# Model outputs 20 dimensions for compatibility
dim_action = 20

# Real robot only needs 12 dimensions
# [left_arm (6), right_arm (6)] = [joints (5) + gripper (1)] × 2
REAL_DIM = 12

# Preprocessing: Pad 12D actions to 20D for training
# Postprocessing: Trim 20D predictions to 12D for deployment

lerobot-train \
  --policy.path="lerobot/xvla-base" \
  --policy.action_mode=auto \
  --policy.max_action_dim=20 \
  ...

# Example: LIBERO checkpoint uses domain_id=3
domain_id = 3

from lerobot.policies.xvla.processor_xvla import LiberoProcessorStep

processor = LiberoProcessorStep()
# Handles robot_state dictionary, converts rotation matrices to 6D representation
# Applies 180° image rotation for camera convention

# Observation and action
n_obs_steps: int = 1          # Number of observation timesteps
chunk_size: int = 32           # Action sequence length
n_action_steps: int = 32       # Number of action steps to execute

# Model architecture
hidden_size: int = 1024        # Transformer hidden dimension
depth: int = 24                # Number of transformer layers
num_heads: int = 16            # Number of attention heads
num_domains: int = 30          # Maximum number of domain IDs
len_soft_prompts: int = 32     # Length of soft prompt embeddings

# Action space
action_mode: str = "ee6d"      # Action space type (use "auto" for auto-detection)
use_proprio: bool = True       # Use proprioceptive state
max_state_dim: int = 32        # Maximum state dimension
max_action_dim: int = 20       # Max action dim for padding (used by "auto" mode)

# Vision
num_image_views: int | None    # Number of camera views
resize_imgs_with_padding: tuple[int, int] | None  # Target image size with padding

# Training
num_denoising_steps: int = 10  # Flow matching denoising steps

from lerobot.policies.xvla.action_hub import BaseActionSpace, register_action
import torch.nn as nn

@register_action("my_custom_robot")
class MyCustomActionSpace(BaseActionSpace):
    """Custom action space for my robot."""

    dim_action = 15  # Your robot's action dimension
    gripper_idx = (7, 14)  # Gripper channel indices

    def __init__(self):
        super().__init__()
        self.mse = nn.MSELoss()
        self.bce = nn.BCEWithLogitsLoss()

    def compute_loss(self, pred, target):
        """Define your loss computation."""
        # Example: MSE for joints, BCE for grippers
        joints_loss = self.mse(pred[:, :, :7], target[:, :, :7])
        gripper_loss = self.bce(pred[:, :, self.gripper_idx],
                                target[:, :, self.gripper_idx])

        return {
            "joints_loss": joints_loss,
            "gripper_loss": gripper_loss,
        }

    def preprocess(self, proprio, action, mode="train"):
        """Preprocess actions before training."""
        # Example: Zero out grippers in proprioception
        proprio_m = proprio.clone()
        action_m = action.clone() if action is not None else None
        proprio_m[..., self.gripper_idx] = 0.0
        if action_m is not None:
            action_m[..., self.gripper_idx] = 0.0
        return proprio_m, action_m

    def postprocess(self, action):
        """Post-process predictions for deployment."""
        # Example: Apply sigmoid to gripper logits
        action[..., self.gripper_idx] = torch.sigmoid(action[..., self.gripper_idx])
        return action

lerobot-train \
  --policy.action_mode=my_custom_robot \
  --dataset.repo_id=YOUR_DATASET \
  --policy.path="lerobot/xvla-base" \
  ...

# Configure for 3 camera views
policy.num_image_views=3

# Add empty cameras if you have fewer physical cameras
policy.empty_cameras=1  # Adds 1 zero-padded camera view

from lerobot.processor import PolicyProcessorPipeline
from lerobot.policies.xvla import (
    XVLAImageToFloatProcessorStep,
    XVLAImageNetNormalizeProcessorStep,
    XVLAAddDomainIdProcessorStep,
)

# Build custom pipeline
preprocessor = PolicyProcessorPipeline(
    steps=[
        YourCustomProcessorStep(),  # Your custom processing
        XVLAImageToFloatProcessorStep(),  # Required: convert to float
        XVLAImageNetNormalizeProcessorStep(),  # Required: ImageNet norm
        XVLAAddDomainIdProcessorStep(domain_id=5),  # Your domain ID
    ]
)

# Automatically detects your dataset's action dimension
# Works with any robot without custom code
policy.action_mode=auto
policy.max_action_dim=20  # Match pretrained model

# Model expects 20D, dataset has 12D
# Action mode handles padding internally
action_mode = "so101_bimanual"  # Pads 12 → 20

@register_action("my_mapped_action")
class MappedActionSpace(BaseActionSpace):
    dim_action = 20
    REAL_DIM = 12

    def _pad_to_model_dim(self, x):
        # Custom padding logic
        ...

@article{zheng2025x,
  title   = {X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model},
  author  = {Zheng, Jinliang and Li, Jianxiong and Wang, Zhihao and Liu, Dongxiu and Kang, Xirui
             and Feng, Yuchun and Zheng, Yinan and Zou, Jiayin and Chen, Yilun and Zeng, Jia and others},
  journal = {arXiv preprint arXiv:2510.10274},
  year    = {2025}
}