cell1_20260506_laundry_folding_organising
收藏Hugging Face2026-05-21 更新2026-05-21 收录
下载链接:
https://huggingface.co/datasets/nodogoro/cell1_20260506_laundry_folding_organising
下载链接
链接失效反馈官方服务:
资源简介:
该数据集由LeRobot创建,专注于机器人学领域的洗衣折叠整理任务。数据集包含一个完整的任务执行过程,共1个episode和52,590帧数据,使用starpilot_yam_gripper型机器人。数据以parquet格式存储,视频以mp4格式存储,帧率为30fps。特征包括:动作数据(14维浮点数组,控制两个机械臂的x、y、z位置、rx、ry、rz旋转和夹爪宽度)、观测状态(32维浮点数组,包括机械臂的编码器角度、IMU加速度和角速度、位姿(位置和四元数)、夹爪开合状态和距离),以及多个图像观测视频(来自realsense和scene相机的RGB和RGB深度图像,分辨率分别为480x848和1024x1024,用于提供视觉信息)。此外,还包含时间戳、帧索引、episode索引等元数据。该数据集适用于机器人控制、模仿学习或强化学习任务,旨在促进洗衣折叠整理等家庭自动化场景的研究。
This dataset is created by LeRobot and focuses on the laundry folding and tidying task in the field of robotics. It contains a complete task execution process with 1 episode and 52,590 frames of data, using a starpilot_yam_gripper robot. The data is stored in parquet format, and videos are stored in mp4 format with a frame rate of 30fps. Features include: action data (a 14-dimensional floating-point array controlling the x, y, z positions, rx, ry, rz rotations, and gripper width of two robotic arms), observation states (a 32-dimensional floating-point array including encoder angles, IMU acceleration and angular velocity, pose (position and quaternion), gripper open/close status and distance of the robotic arms), and multiple image observation videos (from realsense and scene cameras, providing RGB and RGB-D images with resolutions of 480x848 and 1024x1024, respectively, for visual information). Additionally, it includes metadata such as timestamps, frame indices, and episode indices. This dataset is suitable for robot control, imitation learning, or reinforcement learning tasks, aiming to promote research in home automation scenarios like laundry folding and tidying.
提供机构:
nodogoro创建时间:
2026-05-21
原始信息汇总
数据集概述
- 数据集名称:
cell1_20260506_laundry_folding_organising - 许可证: Apache-2.0
- 任务类别: 机器人学(robotics)
- 标签: LeRobot
- 创建工具: 使用 LeRobot 创建
数据集结构
基本信息
| 属性 | 值 |
|---|---|
| 代码库版本 | v3.0 |
| 机器人类型 | starpilot_yam_gripper |
| 总片段数(episodes) | 1 |
| 总帧数 | 52,590 |
| 总任务数 | 1 |
| 数据块大小(chunks_size) | 1,000 |
| 数据文件大小 | 100 MB |
| 视频文件大小 | 200 MB |
| 帧率(fps) | 30 |
| 数据路径格式 | data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet |
| 视频路径格式 | videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4 |
| 训练集划分 | 0:1(全部数据用于训练) |
特征(Features)
动作(action)
- 数据类型: float32
- 形状: [14]
- 包含字段:
arm1_x,arm1_y,arm1_z,arm1_rx,arm1_ry,arm1_rz,arm1_grip_widtharm2_x,arm2_y,arm2_z,arm2_rx,arm2_ry,arm2_rz,arm2_grip_width
观测状态(observation.state)
- 数据类型: float32
- 形状: [32]
- 包含字段: 包含双臂的编码器角度、IMU数据、位姿(位置+四元数)、夹爪状态等共32维
观测图像(observation.images)
| 图像键名 | 分辨率(高×宽×通道) | 编码格式 | 是否深度图 |
|---|---|---|---|
realsense_rgb |
480×848×3 | h264, yuv420p | 否 |
realsense_rgb_depth |
480×848×3 | h264, yuv420p | 否 |
arm2_realsense_rgb |
480×848×3 | h264, yuv420p | 否 |
arm2_realsense_rgb_depth |
480×848×3 | h264, yuv420p | 否 |
scene_rgb |
1024×1024×3 | h264, yuv420p | 否 |
scene_rgb_2 |
1024×1024×3 | h264, yuv420p | 否 |
其他特征
timestamp: float32,形状 [1]frame_index: int64,形状 [1]episode_index: int64,形状 [1]index: int64,形状 [1]task_index: int64,形状 [1]



