cmu_stretch

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

## Dataset Description

- **Homepage:** https://robo-affordances.github.io/
- **Paper:** https://arxiv.org/abs/2304.08488
- **License:** mit

## Dataset Structure

[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v2.0",
"robot_type": "unknown",
"total_episodes": 135,
"total_frames": 25016,
"total_tasks": 5,
"total_videos": 135,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 5,
"splits": {
"train": "0:135"
},
"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": 5.0,
"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": [
4
],
"names": {
"motors": [
"motor_0",
"motor_1",
"motor_2",
"motor_3"
]
}
},
"action": {
"dtype": "float32",
"shape": [
8
],
"names": {
"motors": [
"motor_0",
"motor_1",
"motor_2",
"motor_3",
"motor_4",
"motor_5",
"motor_6",
"motor_7"
]
}
},
"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{bahl2023affordances,
title={Affordances from Human Videos as a Versatile Representation for Robotics},
author={Bahl, Shikhar and Mendonca, Russell and Chen, Lili and Jain, Unnat and Pathak, Deepak},
booktitle={CVPR},
year={2023}
}
@article{mendonca2023structured,
title={Structured World Models from Human Videos},
author={Mendonca, Russell and Bahl, Shikhar and Pathak, Deepak},
journal={CoRL},
year={2023}
}
```

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

## 数据集说明
- **主页**：https://robo-affordances.github.io/
- **论文**：https://arxiv.org/abs/2304.08488
- **许可证**：MIT许可证

## 数据集结构
[meta/info.json](meta/info.json):
json
{
"代码库版本": "v2.0",
"机器人类型": "未知",
"总回合数": 135,
"总帧数": 25016,
"总任务数": 5,
"总视频数": 135,
"总分片数": 1,
"分片大小": 1000,
"帧率": 5,
"数据集划分": {
"训练集": "0:135"
},
"数据路径格式": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"视频路径格式": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4",
"特征项": {
"观测.图像.图像": {
"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": 5.0,
"视频.编码格式": "av1",
"视频.像素格式": "yuv420p",
"视频.非深度图": false,
"无音频轨道": false
}
},
"语言指令": {
"数据类型": "字符串",
"形状": [1],
"维度名称": null
},
"观测.状态": {
"数据类型": "float32",
"形状": [4],
"维度名称": {
"电机": ["motor_0", "motor_1", "motor_2", "motor_3"]
}
},
"动作": {
"数据类型": "float32",
"形状": [8],
"维度名称": {
"电机": ["motor_0", "motor_1", "motor_2", "motor_3", "motor_4", "motor_5", "motor_6", "motor_7"]
}
},
"时间戳": {
"数据类型": "float32",
"形状": [1],
"维度名称": null
},
"回合索引": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
},
"帧索引": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
},
"下一时刻奖励": {
"数据类型": "float32",
"形状": [1],
"维度名称": null
},
"回合终止标记": {
"数据类型": "bool",
"形状": [1],
"维度名称": null
},
"全局索引": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
},
"任务索引": {
"数据类型": "int64",
"形状": [1],
"维度名称": null
}
}
}

## 引用
**BibTeX格式引用：**
bibtex
@inproceedings{bahl2023affordances,
title={基于人类视频的可及性作为机器人学通用表征},
author={Bahl, Shikhar and Mendonca, Russell and Chen, Lili and Jain, Unnat and Pathak, Deepak},
booktitle={计算机视觉与模式识别会议（CVPR）},
year={2023}
}
@article{mendonca2023structured,
title={基于人类视频的结构化世界模型},
author={Mendonca, Russell and Bahl, Shikhar and Pathak, Deepak},
journal={机器人学习会议（CoRL）},
year={2023}
}