LeRobotDataset

my_dataset/
├── data/                    # Robot observations and actions
│   ├── chunk-000/
│   │   ├── file-000.parquet
│   │   └── file-001.parquet
│   └── chunk-001/
│       └── ...
├── meta/                    # Dataset metadata
│   ├── episodes/
│   │   └── chunk-000/
│   │       └── file-000.parquet
│   ├── info.json           # Dataset configuration
│   ├── stats.json          # Normalization statistics
│   └── tasks.parquet       # Task descriptions
└── videos/                  # Camera recordings
    ├── observation.images.laptop/
    │   └── chunk-000/
    │       ├── file-000.mp4
    │       └── file-001.mp4
    └── observation.images.phone/
        └── ...

from lerobot.datasets import LeRobotDataset

dataset = LeRobotDataset.create(
    repo_id="username/my_robot_data",
    fps=30,
    robot_type="so_follower",
    features={
        "observation.state": {
            "dtype": "float32",
            "shape": (6,),
            "names": ["shoulder_pan", "shoulder_lift", "elbow_flex",
                     "wrist_flex", "wrist_roll", "gripper"],
        },
        "observation.images.top": {
            "dtype": "video",
            "shape": (480, 640, 3),
            "names": ["height", "width", "channel"],
        },
        "action": {
            "dtype": "float32",
            "shape": (6,),
            "names": ["shoulder_pan", "shoulder_lift", "elbow_flex",
                     "wrist_flex", "wrist_roll", "gripper"],
        },
    },
    use_videos=True,
)

for timestep in range(episode_length):
    frame = {
        "observation.state": robot.get_observation()["state"],
        "observation.images.top": robot.get_observation()["camera_top"],
        "action": action,
        "task": "pick_and_place",
    }
    dataset.add_frame(frame)

dataset.save_episode(
    episode_index=0,
    task="pick_and_place",
)

dataset.finalize()

dataset = LeRobotDataset(
    repo_id="username/my_robot_data",
    root="/path/to/dataset",
)

dataset = LeRobotDataset(
    repo_id="lerobot/pusht",
    download_videos=True,
)

dataset = LeRobotDataset(
    repo_id="lerobot/pusht",
    episodes=[0, 1, 2, 5, 10],  # Only load these episodes
)

from torch.utils.data import DataLoader

dataloader = DataLoader(
    dataset,
    batch_size=32,
    shuffle=True,
    num_workers=4,
)

for batch in dataloader:
    observations = batch["observation.state"]
    actions = batch["action"]
    # Train your policy...

frame = dataset[0]
print(frame.keys())
# dict_keys(['observation.state', 'observation.images.top', 'action',
#            'episode_index', 'frame_index', 'timestamp', 'task', ...])

print(dataset.fps)              # Frames per second (e.g., 30)
print(dataset.num_episodes)     # Total number of episodes
print(dataset.num_frames)       # Total number of frames
print(dataset.features)         # Feature definitions
print(dataset.meta.robot_type)  # Robot type used for recording

stats = dataset.meta.stats
print(stats["action"]["mean"])  # Mean action values
print(stats["action"]["std"])   # Standard deviation
print(stats["action"]["min"])   # Minimum values
print(stats["action"]["max"])   # Maximum values

print(dataset.meta.tasks)
#        task_index
# task               
# pick    0
# place   1

dataset = LeRobotDataset(
    repo_id="lerobot/pusht",
    delta_timestamps={
        "observation.state": [-0.1, 0.0],     # 100ms ago and now
        "action": [0.0, 0.033, 0.066, 0.1],  # Next 4 actions
    },
)

frame = dataset[100]
print(frame["observation.state"].shape)  # (2, 6) - 2 timesteps
print(frame["action"].shape)             # (4, 6) - 4 future actions

from torchvision.transforms import v2 as transforms

transform = transforms.Compose([
    transforms.RandomCrop(224),
    transforms.ColorJitter(brightness=0.2),
])

dataset = LeRobotDataset(
    repo_id="lerobot/pusht",
    image_transforms=transform,
)

dataset.push_to_hub(
    branch="main",
    tags=["robotics", "manipulation"],
    license="apache-2.0",
    push_videos=True,
)

dataset = LeRobotDataset.create(
    repo_id="username/my_data",
    fps=30,
    features=features,
    vcodec="libsvtav1",  # Options: 'h264', 'hevc', 'libsvtav1', 'auto'
)

dataset = LeRobotDataset.create(
    repo_id="username/my_data",
    fps=30,
    features=features,
    streaming_encoding=True,  # Encode frames as they arrive
    encoder_queue_maxsize=30,  # Buffer size per camera
)

{
  "codebase_version": "v3.0",
  "fps": 30,
  "robot_type": "so_follower",
  "total_episodes": 100,
  "total_frames": 50000,
  "total_tasks": 3,
  "features": {...},
  "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
  "video_path": "videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4"
}