TANAY779/SmolVLA_Stacking

---
license: apache-2.0
task_categories:
- robotics
tags:
- LeRobot
configs:
- config_name: default
data_files: data/*/*.parquet
---

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

## Dataset Structure

[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v3.0",
"robot_type": "so_follower",
"total_episodes": 53,
"total_frames": 89706,
"total_tasks": 1,
"chunks_size": 1000,
"data_files_size_in_mb": 100,
"video_files_size_in_mb": 200,
"fps": 30,
"splits": {
"train": "0:53"
},
"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",
"features": {
"action": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6
]
},
"observation.state": {
"dtype": "float32",
"names": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"shape": [
6
]
},
"observation.images.overhead": {
"dtype": "video",
"shape": [
960,
1280,
3
],
"names": [
"height",
"width",
"channels"
],
"info": {
"video.height": 960,
"video.width": 1280,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 30,
"video.channels": 3,
"has_audio": false
}
},
"observation.images.wrist": {
"dtype": "video",
"shape": [
960,
1280,
3
],
"names": [
"height",
"width",
"channels"
],
"info": {
"video.height": 960,
"video.width": 1280,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"video.fps": 30,
"video.channels": 3,
"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]
```

许可证：Apache-2.0
任务类别：
- 机器人学
标签：
- LeRobot
配置项：
- 配置名称：default
数据文件：data/*/*.parquet

本数据集基于[LeRobot](https://github.com/huggingface/lerobot)构建。

## 数据集说明
- **项目主页：** [需补充更多信息]
- **相关论文：** [需补充更多信息]
- **许可证：** Apache-2.0

## 数据集结构
[meta/info.json]：
json
{
"代码库版本（codebase_version）": "v3.0",
"机器人类型（robot_type）": "so_follower",
"总回合数（total_episodes）": 53,
"总帧数（total_frames）": 89706,
"总任务数（total_tasks）": 1,
"分块大小（chunks_size）": 1000,
"数据文件总大小（MB，data_files_size_in_mb）": 100,
"视频文件总大小（MB，video_files_size_in_mb）": 200,
"帧率（fps）": 30,
"数据集划分（splits）": {
"训练集（train）": "0:53"
},
"数据路径（data_path）": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"视频路径（video_path）": "videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4",
"数据特征（features）": {
"动作（action）": {
"数据类型（dtype）": "float32",
"字段名称（names）": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"形状（shape）": [
6
]
},
"观测状态（observation.state）": {
"数据类型（dtype）": "float32",
"字段名称（names）": [
"shoulder_pan.pos",
"shoulder_lift.pos",
"elbow_flex.pos",
"wrist_flex.pos",
"wrist_roll.pos",
"gripper.pos"
],
"形状（shape）": [
6
]
},
"顶视图观测图像（observation.images.overhead）": {
"数据类型（dtype）": "video",
"形状（shape）": [
960,
1280,
3
],
"维度名称（names）": [
"高度（height）",
"宽度（width）",
"通道数（channels）"
],
"详细信息（info）": {
"视频高度（video.height）": 960,
"视频宽度（video.width）": 1280,
"视频编码格式（video.codec）": "av1",
"视频像素格式（video.pix_fmt）": "yuv420p",
"是否为深度图（video.is_depth_map）": false,
"视频帧率（video.fps）": 30,
"视频通道数（video.channels）": 3,
"是否包含音频（has_audio）": false
}
},
"腕部视角观测图像（observation.images.wrist）": {
"数据类型（dtype）": "video",
"形状（shape）": [
960,
1280,
3
],
"维度名称（names）": [
"高度（height）",
"宽度（width）",
"通道数（channels）"
],
"详细信息（info）": {
"视频高度（video.height）": 960,
"视频宽度（video.width）": 1280,
"视频编码格式（video.codec）": "av1",
"视频像素格式（video.pix_fmt）": "yuv420p",
"是否为深度图（video.is_depth_map）": false,
"视频帧率（video.fps）": 30,
"视频通道数（video.channels）": 3,
"是否包含音频（has_audio）": false
}
},
"时间戳（timestamp）": {
"数据类型（dtype）": "float32",
"形状（shape）": [
1
],
"维度名称（names）": null
},
"帧索引（frame_index）": {
"数据类型（dtype）": "int64",
"形状（shape）": [
1
],
"维度名称（names）": null
},
"回合索引（episode_index）": {
"数据类型（dtype）": "int64",
"形状（shape）": [
1
],
"维度名称（names）": null
},
"全局索引（index）": {
"数据类型（dtype）": "int64",
"形状（shape）": [
1
],
"维度名称（names）": null
},
"任务索引（task_index）": {
"数据类型（dtype）": "int64",
"形状（shape）": [
1
],
"维度名称（names）": null
}
}
}

## 参考文献
**BibTeX格式：**
bibtex
[需补充更多信息]