EmbodiedGen：迈向具身智能的生成式3D世界引擎

EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence

June 12, 2025

作者: Wang Xinjie, Liu Liu, Cao Yu, Wu Ruiqi, Qin Wenkang, Wang Dehui, Sui Wei, Su Zhizhong

cs.AI

摘要

构建一个物理真实且比例精确的模拟3D世界，对于具身智能任务的训练与评估至关重要。3D数据资产的多样性、真实性、低成本获取及经济性，是实现具身AI泛化与可扩展性的关键。然而，当前大多数具身智能任务仍严重依赖手工创建与标注的传统3D计算机图形资产，这些资产存在生产成本高、真实感有限的问题，极大地制约了数据驱动方法的可扩展性。我们提出EmbodiedGen，一个用于交互式3D世界生成的基础平台。它能够以低成本大规模生成高质量、可控且逼真的3D资产，这些资产具备精确的物理属性和真实世界比例，采用统一机器人描述格式（URDF），可直接导入多种物理仿真引擎进行细粒度物理控制，支持训练与评估中的下游任务。EmbodiedGen是一个易于使用、功能齐全的工具包，由六大核心模块组成：图像转3D、文本转3D、纹理生成、关节物体生成、场景生成与布局生成。通过利用生成式AI，EmbodiedGen构建了由生成式3D资产组成的多样化、交互式3D世界，有效应对了具身智能相关研究在泛化与评估需求上的挑战。代码可在https://horizonrobotics.github.io/robot_lab/embodied_gen/index.html 获取。

English

Constructing a physically realistic and accurately scaled simulated 3D world is crucial for the training and evaluation of embodied intelligence tasks. The diversity, realism, low cost accessibility and affordability of 3D data assets are critical for achieving generalization and scalability in embodied AI. However, most current embodied intelligence tasks still rely heavily on traditional 3D computer graphics assets manually created and annotated, which suffer from high production costs and limited realism. These limitations significantly hinder the scalability of data driven approaches. We present EmbodiedGen, a foundational platform for interactive 3D world generation. It enables the scalable generation of high-quality, controllable and photorealistic 3D assets with accurate physical properties and real-world scale in the Unified Robotics Description Format (URDF) at low cost. These assets can be directly imported into various physics simulation engines for fine-grained physical control, supporting downstream tasks in training and evaluation. EmbodiedGen is an easy-to-use, full-featured toolkit composed of six key modules: Image-to-3D, Text-to-3D, Texture Generation, Articulated Object Generation, Scene Generation and Layout Generation. EmbodiedGen generates diverse and interactive 3D worlds composed of generative 3D assets, leveraging generative AI to address the challenges of generalization and evaluation to the needs of embodied intelligence related research. Code is available at https://horizonrobotics.github.io/robot_lab/embodied_gen/index.html.