发表机构
Horizon Robotics; WuwenAI（地平线机器人; 悟文智能）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出EmbodiedGen V2这个用于具身智能的3D世界引擎，通过统一表示解决资产组装问题。其生成环境支持多种任务，评估中资产管道表现良好，强化学习提升了模拟成功率，确立了它作为可扩展模拟基础设施的地位。
AI 中文摘要
我们展示了EmbodiedGen V2，这是一个用于构建可执行的、适用于模拟的具身智能环境的生成式3D世界引擎。适用于模拟的3D资产生成发展迅速，但将这些资产组装成适用于策略的任务环境在很大程度上仍需人工操作，限制了可扩展的闭环学习。EmbodiedGen V2通过统一的适用于模拟的表示来解决这一差距，该表示将跨模拟器资产、交互能力、任务驱动的世界、大规模多房间场景和有状态的Vibe编码连接到一个生成式、可编辑和可重复使用的模拟管道中。生成的环境支持操纵、导航、移动操纵、跨模拟器部署和具身策略训练。在评估中，资产管道实现了96.5%的人类接受度和98.6%的碰撞成功率，83.3%的任务驱动世界无需人工修改即可直接用于下游模拟。使用生成的环境进行在线强化学习进一步将模拟成功率从9.7%提高到79.8%，并转移到真实机器人上，任务成功率从21.7%提高到75.0%。这些结果确立了EmbodiedGen V2作为用于训练、评估和部署具身策略的可扩展模拟基础设施的地位。
英文摘要
We present EmbodiedGen V2, a generative 3D world engine for building executable policy-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapidly, yet assembling such assets into policy-ready task environments remains largely manual, limiting scalable closed-loop learning. EmbodiedGen V2 addresses this gap through a unified sim-ready representation that connects cross-simulator assets, interaction affordances, task-driven worlds, large-scale multi-room scenes, and stateful Vibe Coding into a generative, editable, and reusable simulation pipeline. The generated environments support manipulation, navigation, mobile manipulation, cross-simulator deployment, and embodied policy training. In evaluation, the asset pipeline achieves 96.5% human acceptance and 98.6% collision success, and 83.3% of task-driven worlds are directly usable for downstream simulation without manual modification. Online reinforcement learning with generated environments further improves simulation success from 9.7% to 79.8%, and transfers to real robots with task success increasing from 21.7% to 75.0%. These results establish EmbodiedGen V2 as scalable simulation infrastructure for training, evaluating, and deploying embodied policies.
CommentsProject page: horizonrobotics.github.io/EmbodiedGen
