xvla-google-robot

import torch
from lerobot.datasets.lerobot_dataset import LeRobotDataset
from lerobot.policies.factory import make_pre_post_processors

# Swap this import per-policy
from lerobot.policies.xvla.modeling_xvla import XVLAPolicy

# load a policy
model_id = "lerobot/xvla-google-robot"  # <- swap checkpoint
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

policy = XVLAPolicy.from_pretrained(model_id).to(device).eval()

preprocess, postprocess = make_pre_post_processors(
    policy.config,
    model_id,
    preprocessor_overrides={"device_processor": {"device": str(device)}},
)
# load a lerobotdataset (we will replace with a simpler dataset)
dataset = LeRobotDataset("lerobot/libero")

# pick an episode
episode_index = 0

# each episode corresponds to a contiguous range of frame indices
from_idx = dataset.meta.episodes["dataset_from_index"][episode_index]
to_idx   = dataset.meta.episodes["dataset_to_index"][episode_index]

# get a single frame from that episode (e.g. the first frame)
frame_index = from_idx
frame = dict(dataset[frame_index])

batch = preprocess(frame)
with torch.inference_mode():
    pred_action = policy.select_action(batch)
    # use your policy postprocess, this post process the action
    # for instance unnormalize the actions, detokenize it etc..
    pred_action = postprocess(pred_action)

lerobot-record  \
  --robot.type=so100_follower \
  --robot.port=/dev/ttyACM1 \
  --robot.cameras="{ up: {type: opencv, index_or_path: /dev/video10, width: 640, height: 480, fps: 30}, side: {type: intelrealsense, serial_number_or_name: 233522074606, width: 640, height: 480, fps: 30}}" \
  --robot.id=my_awesome_follower_arm \
  --display_data=false \
  --dataset.repo_id=${HF_USER}/eval_so100 \
  --dataset.single_task="Put lego brick into the transparent box" \
  # <- Teleop optional if you want to teleoperate in between episodes \
  # --teleop.type=so100_leader \
  # --teleop.port=/dev/ttyACM0 \
  # --teleop.id=my_awesome_leader_arm \
  --policy.path=${HF_USER}/my_policy