G1_MountCamera_Dataset
收藏魔搭社区2025-11-01 更新2025-01-11 收录
下载链接:
https://modelscope.cn/datasets/unitreerobotics/G1_MountCamera_Dataset
下载链接
链接失效反馈官方服务:
资源简介:
This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).
## Dataset Description
- **Homepage:** [More Information Needed]
- **Paper:** [More Information Needed]
- **License:** apache-2.0
- **Task Objective:** Place the OAK-D-LITE camera into the mounting case and secure the lid.
- **Operational Objects:** An OAK-D-LITE camera along with its original complete packaging (Purchase link: [【淘宝】7天无理由退货 https://e.tb.cn/h.606wnDDmrTMhcch?tk=Dr7feJHVOyp CZ009 「OpenCV AI视觉套件 OAK-D-Lite智能开发 深度摄像头RGB高清相机」点击链接直接打开 或者 淘宝搜索直接打开])
- **Operation Duration:** Each operation takes approximately 40 seconds.
- **Recording Frequency:** 30 Hz.
- **Robot Type:** 7-DOF dual-arm G1 robot.
- **End Effector:** Three-fingered dexterous hands.
- **Dual-Arm Operation:** Yes.
- **Image Resolution:** 640x480.
- **Camera Positions:** Wrist-mounted (monocular camera) + head-mounted (binocular cameras).
- **Data Content:**
• Robot's current state.
• Robot's next action.
• Current camera view images.
- **Robot Initial Posture:** The first robot state in each dataset entry.
- **Object Placement:** PPosition the camera case at the midpoint between the robot's arms in their initial state (arms vertical), 20cm away from the inner edge of the table's wall (robot-facing side). Place the camera on the right side of the case, and position the lid on the left side of the case.
- **Camera View:** Follow the guidelines in **Part 5** of [AVP Teleoperation Documentation](https://github.com/unitreerobotics/avp_teleoperate).
- **Important Notes:**
1. Due to the inability to precisely describe spatial positions, adjust the scene to closely match the first frame of the dataset after installing the hardware as specified in **Part 5** of [AVP Teleoperation Documentation](https://github.com/unitreerobotics/avp_teleoperate).
2. Data collection is not completed in a single session, and variations between data entries exist. Ensure these variations are accounted for during model training.
## Dataset Structure
[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v2.0",
"robot_type": "Unitree_G1",
"total_episodes": 351,
"total_frames": 389708,
"total_tasks": 1,
"total_videos": 1404,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:351"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4",
"features": {
"observation.state": {
"dtype": "float32",
"shape": [
16
],
"names": [
[
"kLeftShoulderPitch",
"kLeftShoulderRoll",
"kLeftShoulderYaw",
"kLeftElbow",
"kLeftWristRoll",
"kLeftWristPitch",
"kLeftWristyaw",
"kRightShoulderPitch",
"kRightShoulderRoll",
"kRightShoulderYaw",
"kRightElbow",
"kRightWristRoll",
"kRightWristPitch",
"kRightWristYaw",
"kLeftGripper",
"kRightGripper"
]
]
},
"action": {
"dtype": "float32",
"shape": [
16
],
"names": [
[
"kLeftShoulderPitch",
"kLeftShoulderRoll",
"kLeftShoulderYaw",
"kLeftElbow",
"kLeftWristRoll",
"kLeftWristPitch",
"kLeftWristyaw",
"kRightShoulderPitch",
"kRightShoulderRoll",
"kRightShoulderYaw",
"kRightElbow",
"kRightWristRoll",
"kRightWristPitch",
"kRightWristYaw",
"kLeftGripper",
"kRightGripper"
]
]
},
"observation.images.cam_left_high": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"observation.images.cam_right_high": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"observation.images.cam_left_wrist": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"observation.images.cam_right_wrist": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"timestamp": {
"dtype": "float32",
"shape": [
1
],
"names": null
},
"frame_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"episode_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"task_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
}
}
}
```
## Citation
**BibTeX:**
```bibtex
[More Information Needed]
```
本数据集基于[LeRobot](https://github.com/huggingface/lerobot)构建。
## 数据集说明
- **主页:** [更多信息待补充]
- **论文:** [更多信息待补充]
- **许可证:** apache-2.0
- **任务目标:** 将OAK-D-LITE摄像头(OAK-D-LITE)安装至配套安装盒中并锁紧盒盖。
- **操作对象:** OAK-D-LITE摄像头(OAK-D-LITE)及其全套原厂包装(购买链接:【淘宝】7天无理由退货 https://e.tb.cn/h.606wnDDmrTMhcch?tk=Dr7feJHVOyp CZ009 「OpenCV AI视觉套件 OAK-D-Lite智能开发 深度摄像头RGB高清相机」点击链接直接打开 或 直接通过淘宝搜索获取)
- **操作时长:** 单次操作耗时约40秒。
- **录制帧率:** 30 Hz。
- **机器人类型:** 7自由度双臂G1机器人(G1)
- **末端执行器:** 三指灵巧手。
- **双臂操作:** 是。
- **图像分辨率:** 640×480。
- **摄像头安装位置:** 腕部安装(单目摄像头)+ 头部安装(双目摄像头)。
- **数据内容:**
• 机器人当前状态
• 机器人待执行的下一动作
• 当前摄像头采集的画面图像
- **机器人初始姿态:** 每个数据条目的首个机器人状态。
- **物体摆放要求:** 将摄像头安装盒放置于机器人初始双臂垂直状态时的双臂中点位置,距离桌面朝向机器人一侧的内壁内缘20cm处;将摄像头置于安装盒右侧,盒盖置于安装盒左侧。
- **摄像头视角:** 遵循[AVP遥操作文档](https://github.com/unitreerobotics/avp_teleoperate)第5部分的指南。
- **重要注意事项:**
1. 由于无法精准描述空间位置,在按照[AVP遥操作文档](https://github.com/unitreerobotics/avp_teleoperate)第5部分完成硬件安装后,请调整场景至与数据集首帧高度匹配。
2. 数据采集并非单次完成,不同数据条目间存在差异,在模型训练阶段需充分考虑此类差异。
## 数据集结构
[meta/info.json]:
json
{
"codebase_version": "v2.0",
"robot_type": "Unitree_G1",
"total_episodes": 351,
"total_frames": 389708,
"total_tasks": 1,
"total_videos": 1404,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:351"
},
"data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4",
"features": {
"observation.state": {
"dtype": "float32",
"shape": [
16
],
"names": [
[
"kLeftShoulderPitch",
"kLeftShoulderRoll",
"kLeftShoulderYaw",
"kLeftElbow",
"kLeftWristRoll",
"kLeftWristPitch",
"kLeftWristyaw",
"kRightShoulderPitch",
"kRightShoulderRoll",
"kRightShoulderYaw",
"kRightElbow",
"kRightWristRoll",
"kRightWristPitch",
"kRightWristYaw",
"kLeftGripper",
"kRightGripper"
]
]
},
"action": {
"dtype": "float32",
"shape": [
16
],
"names": [
[
"kLeftShoulderPitch",
"kLeftShoulderRoll",
"kLeftShoulderYaw",
"kLeftElbow",
"kLeftWristRoll",
"kLeftWristPitch",
"kLeftWristyaw",
"kRightShoulderPitch",
"kRightShoulderRoll",
"kRightShoulderYaw",
"kRightElbow",
"kRightWristRoll",
"kRightWristPitch",
"kRightWristYaw",
"kLeftGripper",
"kRightGripper"
]
]
},
"observation.images.cam_left_high": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"observation.images.cam_right_high": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"observation.images.cam_left_wrist": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"observation.images.cam_right_wrist": {
"dtype": "video",
"shape": [
3,
480,
640
],
"names": [
"channels",
"height",
"width"
],
"info": {
"video.fps": 30.0,
"video.height": 480,
"video.width": 640,
"video.channels": 3,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"timestamp": {
"dtype": "float32",
"shape": [
1
],
"names": null
},
"frame_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"episode_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"task_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
}
}
}
## 引用
**BibTeX:**
bibtex
[More Information Needed]
提供机构:
maas
创建时间:
2025-01-06



