five

GenieSimAssets

收藏
魔搭社区2026-05-16 更新2025-08-09 收录
下载链接:
https://modelscope.cn/datasets/agibot_world/GenieSimAssets
下载链接
kingsoft__icon
金山云加速下载
链接失效反馈
官方服务:
资源简介:
![geniesim.jpg](geniesim.jpg) <div align="center"> <a href="https://arxiv.org/abs/2601.02078"> <img src='https://img.shields.io/badge/arXiv-Paper-red?logo=arxiv&logoColor=white' alt='arXiv'> </a> <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="http://agibot-world.com/genie-sim"> <img src="https://img.shields.io/badge/Webpage-green?" alt="Webpage"> </a> <a href="https://modelscope.cn/datasets/agibot_world/GenieSim3.0-Dataset"> <img src="https://img.shields.io/badge/Modelscope-blue" alt="Genie Studio"> </a> </div> # Key Features 🔑 - **5000+** objects 1:1 replicated from real-life # Get started 🔥 ## Download the Assets To download the full assets, please refer to the official Hugging Face/Modelscope documentation. ## Assets Structure ### Folder hierarchy ``` assets ├── background # Background environments │ └── ... ├── robot # Robot models │ ├── G1_120s │ ├── G1_omnipicker │ ├── G2_omnipicker │ └── curobo_robot ├── objects # Object assets │ └── ... ├── interaction # Interaction data ├── real2sim # Real-to-sim assets │ └── ... ├── external # External assets ├── README.md └── ... ``` # 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{yin2026geniesim30, title={Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot}, author={Chenghao Yin and Da Huang and Di Yang and Jichao Wang and Nanshu Zhao and Chen Xu and Wenjun Sun and Linjie Hou and Zhijun Li and Junhui Wu and Zhaobo Liu and Zhen Xiao and Sheng Zhang and Lei Bao and Rui Feng and Zhenquan Pang and Jiayu Li and Qian Wang and Maoqing Yao}, year={2026}, eprint={2601.02078}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2601.02078}, } ```

<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} }
提供机构:
maas
创建时间:
2025-08-27
搜集汇总
数据集介绍
main_image_url
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。
以上内容由遇见数据集搜集并总结生成
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作