GenieSimAssets

<img src="geniesim.jpg" alt="Image Alt Text" width="80%" style="display: block; margin-left: auto; margin-right: auto;" />

<div align="center">
<a href="https://github.com/AgibotTech/genie_sim">
<img src="https://img.shields.io/badge/GitHub-grey?logo=GitHub" alt="GitHub">
</a>
<a href="https://huggingface.co/datasets/agibot-world/GenieSimAssets">
<img src="https://img.shields.io/badge/HuggingFace-yellow?logo=HuggingFace" alt="HuggingFace">
</a>
<a href="https://agibot-world.com/sim-evaluation">
<img src="https://img.shields.io/badge/Genie%20Sim%20Benchmark-blue?style=plastic" alt="Genie Sim Benchmark">
</a>
<a href="https://genie.agibot.com/en/geniestudio">
<img src="https://img.shields.io/badge/Genie_Studio-green?style=flat" alt="Genie Studio">
</a>
</div>

# Key Features 🔑
- **22 scenarios** including supermarket, cafeteria and home
- **600+** objects 1:1 replicated from real-life

# Get started 🔥
## Download the Simulation Assets
To download the full assets, you can use the following code. If you encounter any issues, please refer to the official Hugging Face documentation.
```
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install

# When prompted for a password, use an access token with write permissions.
# Generate one from your settings: https://huggingface.co/settings/tokens
git clone https://huggingface.co/datasets/agibot-world/GenieSimAssets

# If you want to clone without large files - just their pointers
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/agibot-world/GenieSimAssets
```

## Assets Structure
### Folder hierarchy
```
assets
├── G1_120s # G1_120s Robot
│   ├── G1_120s.usda
│   └── ...
├── G1_omnipicker # G1_omnipicker Robot
│   ├── G1_omnipicker.usda
│   └── ...
├── materials # materials
│   ├── carpet
│   ├── hdri
│   ├── stone
│   └── wood
├── objects # objects
│   ├── benchmark
│   ├── genie
│   ├── iros
│   └── lightwheelai
├── README.md
└── scenes # scenes
├── genie
├── guanglun
└── iros
```

# License and Citation
All the data and code within this repo are under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/). Please consider citing our project if it helps your research.

```BibTeX
@misc{contributors2025geniesimrepo,
title={Genie Sim Assets},
author={Genie Sim Team},
howpublished={https://github.com/AgibotTech/genie_sim},
year={2025}
}
```

<img src="geniesim.jpg" alt="图片替代文本" width="80%" style="display: block; margin-left: auto; margin-right: auto;" />

<div align="center">
<a href="https://github.com/AgibotTech/genie_sim">
<img src="https://img.shields.io/badge/GitHub-grey?logo=GitHub" alt="GitHub">
</a>
<a href="https://huggingface.co/datasets/agibot-world/GenieSimAssets">
<img src="https://img.shields.io/badge/HuggingFace-yellow?logo=HuggingFace" alt="HuggingFace">
</a>
<a href="https://agibot-world.com/sim-evaluation">
<img src="https://img.shields.io/badge/Genie%20Sim%20Benchmark-blue?style=plastic" alt="Genie Sim Benchmark">
</a>
<a href="https://genie.agibot.com/en/geniestudio">
<img src="https://img.shields.io/badge/Genie_Studio-green?style=flat" alt="Genie Studio">
</a>
</div>

# 核心特性 🔑
- **22个场景**，涵盖超市、餐厅与家庭场景
- **600+** 实物1:1复刻的仿真物体

# 快速开始 🔥
## 获取仿真资产
如需下载完整资产包，可使用如下代码。若遇到问题，请参阅官方Hugging Face（HuggingFace）文档。

# 请确保已安装Git大文件存储（Git Large File Storage，git-lfs），访问地址：https://git-lfs.com
git lfs install

# 当提示输入密码时，请使用具备写入权限的访问令牌。可从以下地址生成令牌：https://huggingface.co/settings/tokens
git clone https://huggingface.co/datasets/agibot-world/GenieSimAssets

# 若仅需克隆大文件的指针而非完整文件（跳过大文件下载）
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/agibot-world/GenieSimAssets

## 资产结构
### 文件夹层级结构

assets
├── G1_120s # G1_120型机器人
│ ├── G1_120s.usda
│ └── ...
├── G1_omnipicker # G1_omnipicker型机器人
│ ├── G1_omnipicker.usda
│ └── ...
├── materials # 材质库
│ ├── carpet # 地毯材质
│ ├── hdri # HDRI环境贴图
│ ├── stone # 石材材质
│ └── wood # 木材材质
├── objects # 物体库
│ ├── benchmark # 基准测试物体
│ ├── genie # Genie系列物体
│ ├── iros # IROS相关物体
│ └── lightwheelai # LightWheelAI相关物体
├── README.md # 项目说明文档
└── scenes # 场景库
├── genie # Genie系列场景
├── guanglun # 广轮系列场景
└── iros # IROS相关场景

# 许可与引用
本仓库内的所有数据与代码均遵循[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)知识共享署名-非商业性使用-相同方式共享4.0国际许可协议。若本项目对您的研究有所帮助，请考虑引用我们的工作。

BibTeX
@misc{contributors2025geniesimrepo,
title={Genie Sim Assets},
author={Genie Sim Team},
howpublished={https://github.com/AgibotTech/genie_sim},
year={2025}
}

搜集汇总

背景与挑战

背景概述

GenieSimAssets是一个机器人操作仿真数据集，包含22个真实场景(如超市、餐厅)和600多个1:1复刻的真实物体，数据规模15.32GB。该数据集专为机器人双臂操作仿真设计，采用Apache 2.0开源协议。