avatarrobotics/bin-pick-panel-suction-v2
收藏Hugging Face2026-03-24 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/avatarrobotics/bin-pick-panel-suction-v2
下载链接
链接失效反馈官方服务:
资源简介:
---
license: apache-2.0
task_categories:
- robotics
tags:
- LeRobot
- lerobot
- avatar-robotics
- bin-picking
- suction-gripper
configs:
- config_name: default
data_files: data/*/*.parquet
---
This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).
## Dataset Description
**Robot:** Agibot G1 humanoid robot
**Task:** Bin picking with suction gripper — pick up items from a bin and place in a moving box or bag
**Episodes:** 325
**Total Frames:** 102525
**FPS:** 30
**Format:** LeRobot v3.0
V2 with enriched features: EE pose, velocity, other-arm state, and success labels.
### Cameras
- `observation.images.camera` — Camera camera (1280x800)
- `observation.images.wrist` — Wrist camera (1280x720)
### Features
| Feature | Type | Shape |
|---------|------|-------|
| `observation.state` | float32 | [8] |
| `action` | float32 | [8] |
| `observation.images.camera` | video | [800, 1280, 3] |
| `observation.images.wrist` | video | [720, 1280, 3] |
| `observation.force` | float32 | [6] |
| `observation.state_other` | float32 | [7] |
| `observation.velocity` | float32 | [7] |
| `observation.ee_pose` | float32 | [7] |
| `action.ee_target` | float32 | [7] |
| `next.success` | bool | [1] |
## Usage
```python
from lerobot.datasets.lerobot_dataset import LeRobotDataset
dataset = LeRobotDataset("avatarrobotics/bin-pick-panel-suction-v2")
sample = dataset[0]
```
## Citation
Created by [Avatar Robotics](https://avatarrobotics.ai).
许可证:Apache-2.0
任务类别:
- 机器人学
标签:
- LeRobot
- lerobot
- Avatar Robotics
- 箱拣选
- 吸盘抓手
配置项:
- 配置名称:默认
数据文件:data/*/*.parquet
本数据集基于[LeRobot(LeRobot)](https://github.com/huggingface/lerobot)框架构建。
## 数据集说明
**机器人平台:** Agibot G1人形机器人(Agibot G1 humanoid robot)
**任务类型:** 采用吸盘抓手的箱拣选作业——从储物箱中抓取物品并放置于移动箱具或收纳袋中
**轨迹段数量:** 325段
**总帧数:** 102525
**帧率:** 30
**数据格式:** LeRobot v3.0
本V2版本新增丰富特征:末端执行器位姿、运动速度、对侧机械臂状态以及成功标记标签。
### 相机配置
- `observation.images.camera`:场景相机(分辨率1280×800)
- `observation.images.wrist`:腕部相机(分辨率1280×720)
### 特征列表
| 特征名称 | 数据类型 | 张量形状 |
|---------|------|-------|
| `observation.state` | 单精度浮点型(float32) | [8] |
| `action` | 单精度浮点型 | [8] |
| `observation.images.camera` | 视频流 | [800, 1280, 3] |
| `observation.images.wrist` | 视频流 | [720, 1280, 3] |
| `observation.force` | 单精度浮点型 | [6] |
| `observation.state_other` | 单精度浮点型 | [7] |
| `observation.velocity` | 单精度浮点型 | [7] |
| `observation.ee_pose` | 单精度浮点型 | [7] |
| `action.ee_target` | 单精度浮点型 | [7] |
| `next.success` | 布尔型(bool) | [1] |
## 使用方法
python
from lerobot.datasets.lerobot_dataset import LeRobotDataset
dataset = LeRobotDataset("avatarrobotics/bin-pick-panel-suction-v2")
sample = dataset[0]
## 引用声明
本数据集由[Avatar Robotics(Avatar Robotics)](https://avatarrobotics.ai)研发制作。
提供机构:
avatarrobotics


