iamlab_cmu_pickup_insert

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

## Dataset Description

- **Homepage:** https://openreview.net/forum?id=WuBv9-IGDUA
- **Paper:** https://arxiv.org/abs/2401.14502
- **License:** mit

## Dataset Structure

[meta/info.json](meta/info.json):
```json
{
"codebase_version": "v2.0",
"robot_type": "unknown",
"total_episodes": 631,
"total_frames": 146241,
"total_tasks": 7,
"total_videos": 1262,
"total_chunks": 1,
"chunks_size": 1000,
"fps": 20,
"splits": {
"train": "0:631"
},
"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": [
360,
640,
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
}
},
"observation.images.wrist_image": {
"dtype": "video",
"shape": [
240,
320,
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": [
8
],
"names": {
"motors": [
"motor_0",
"motor_1",
"motor_2",
"motor_3",
"motor_4",
"motor_5",
"motor_6",
"motor_7"
]
}
},
"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{saxena2023multiresolution,
title={Multi-Resolution Sensing for Real-Time Control with Vision-Language Models},
author={Saumya Saxena and Mohit Sharma and Oliver Kroemer},
booktitle={7th Annual Conference on Robot Learning},
year={2023},
url={https://openreview.net/forum?id=WuBv9-IGDUA}
}
```

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

## 数据集说明

- **主页**：https://openreview.net/forum?id=WuBv9-IGDUA
- **论文**：https://arxiv.org/abs/2401.14502
- **许可证**：MIT

## 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": 631,
"总帧数": 146241,
"总任务数": 7,
"总视频数": 1262,
"总分片数": 1,
"分片大小": 1000,
"帧率": 20,
"数据集划分": {
"训练集": "0:631"
},
"数据路径": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet",
"视频路径": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4",
"特征项": {
"观测.图像.主摄像头": {
"数据类型": "video",
"形状": [
360,
640,
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
}
},
"观测.图像.腕部摄像头": {
"数据类型": "video",
"形状": [
240,
320,
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
}
},
"语言指令": {
"数据类型": "string",
"形状": [
1
],
"维度名称": null
},
"观测.状态": {
"数据类型": "float32",
"形状": [
8
],
"维度名称": {
"电机": [
"电机_0",
"电机_1",
"电机_2",
"电机_3",
"电机_4",
"电机_5",
"电机_6",
"电机_7"
]
}
},
"动作": {
"数据类型": "float32",
"形状": [
7
],
"维度名称": {
"电机": [
"电机_0",
"电机_1",
"电机_2",
"电机_3",
"电机_4",
"电机_5",
"电机_6"
]
}
},
"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
},
"下一时刻终止标记": {
"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：**
bibtex
@inproceedings{saxena2023multiresolution,
title={面向视觉语言模型实时控制的多分辨率感知},
author={Saumya Saxena and Mohit Sharma and Oliver Kroemer},
booktitle={第7届机器人学习年度会议},
year={2023},
url={https://openreview.net/forum?id=WuBv9-IGDUA}
}