stanford_kuka_multimodal_dataset

This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).

## Dataset Description

- **Homepage:** https://sites.google.com/view/visionandtouch
- **Paper:** https://arxiv.org/abs/1810.10191
- **License:** mit

## Dataset Structure

[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v2.0",
"robot_type": "unknown",
"total_episodes": 3000,
"total_frames": 149985,
"total_tasks": 1,
"total_videos": 3000,
"total_chunks": 3,
"chunks_size": 1000,
"fps": 20,
"splits": {
"train": "0:3000"
},
"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.images.image": {
"dtype": "video",
"shape": [
128,
128,
3
],
"names": [
"height",
"width",
"channel"
],
"video_info": {
"video.fps": 20.0,
"video.codec": "av1",
"video.pix_fmt": "yuv420p",
"video.is_depth_map": false,
"has_audio": false
}
},
"language_instruction": {
"dtype": "string",
"shape": [
1
],
"names": null
},
"observation.state": {
"dtype": "float32",
"shape": [
7
],
"names": {
"motors": [
"motor_0",
"motor_1",
"motor_2",
"motor_3",
"motor_4",
"motor_5",
"motor_6"
]
}
},
"action": {
"dtype": "float32",
"shape": [
7
],
"names": {
"motors": [
"motor_0",
"motor_1",
"motor_2",
"motor_3",
"motor_4",
"motor_5",
"motor_6"
]
}
},
"timestamp": {
"dtype": "float32",
"shape": [
1
],
"names": null
},
"episode_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"frame_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"next.reward": {
"dtype": "float32",
"shape": [
1
],
"names": null
},
"next.done": {
"dtype": "bool",
"shape": [
1
],
"names": null
},
"index": {
"dtype": "int64",
"shape": [
1
],
"names": null
},
"task_index": {
"dtype": "int64",
"shape": [
1
],
"names": null
}
}
}
```

## Citation

**BibTeX:**

```bibtex
@inproceedings{lee2019icra,
title={Making sense of vision and touch: Self-supervised learning of multimodal representations for contact-rich tasks},
author={Lee, Michelle A and Zhu, Yuke and Srinivasan, Krishnan and Shah, Parth and Savarese, Silvio and Fei-Fei, Li and Garg, Animesh and Bohg, Jeannette},
booktitle={2019 IEEE International Conference on Robotics and Automation (ICRA)},
year={2019},
url={https://arxiv.org/abs/1810.10191}
}
```

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

## 数据集说明
- **主页**：https://sites.google.com/view/visionandtouch
- **论文**：https://arxiv.org/abs/1810.10191
- **许可证**：MIT许可证

## 数据集结构
`meta/info.json` 文件包含如下元数据：
json
{
"代码库版本": "v2.0",
"机器人类型": "未知",
"总回合数": 3000,
"总帧数": 149985,
"总任务数": 1,
"总视频数": 3000,
"总分片数": 3,
"单分片大小": 1000,
"帧率": 20,
"数据拆分": {
"训练集": "0:3000"
},
"数据文件路径": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"视频文件路径": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4",
"数据特征": {
"observation.images.image": {
"数据类型": "视频",
"形状": [128, 128, 3],
"维度名称": ["高度", "宽度", "通道数"],
"视频信息": {
"视频帧率": 20.0,
"视频编码格式": "av1",
"视频像素格式": "yuv420p",
"是否为深度图": false,
"是否含音频": false
}
},
"language_instruction": {
"数据类型": "字符串",
"形状": [1],
"维度名称": null
},
"observation.state": {
"数据类型": "float32",
"形状": [7],
"维度名称": {
"电机": ["motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6"]
}
},
"action": {
"数据类型": "float32",
"形状": [7],
"维度名称": {
"电机": ["motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6"]
}
},
"timestamp": {
"数据类型": "float32",
"形状": [1],
"维度名称": null
},
"episode_index": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
},
"frame_index": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
},
"next.reward": {
"数据类型": "float32",
"形状": [1],
"维度名称": null
},
"next.done": {
"数据类型": "bool",
"形状": [1],
"维度名称": null
},
"index": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
},
"task_index": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
}
}
}

## 引用
**BibTeX 引用格式：**
bibtex
@inproceedings{lee2019icra,
title={理解视觉与触觉：面向密集接触任务的多模态表征自监督学习},
author={Lee, Michelle A and Zhu, Yuke and Srinivasan, Krishnan and Shah, Parth and Savarese, Silvio and Fei-Fei, Li and Garg, Animesh and Bohg, Jeannette},
booktitle={2019 IEEE国际机器人与自动化会议(ICRA)},
year={2019},
url={https://arxiv.org/abs/1810.10191}
}