Awomo-SimDataEngine：智能体式仿真就绪世界生成
Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation
浏览论文内容
中文总结 AI 辅助
提出Awomo-SimDataEngine智能体系统，整合资产、场景和演示生成，通过图原生协调与修复，生成仿真就绪数据，并在LIBERO-Plus上提升世界动作模型成功率至89.43%。
中文摘要 AI 辅助
生成有用的机器人训练数据不仅需要视觉上合理的场景：物体必须支持交互，放置必须保持物理有效，任务必须允许可重复执行。我们提出Awomo-SimDataEngine，一个智能体系统，将资产和场景生成与机器人演示合成连接起来。共享资产服务提供刚体和铰接物体，包括使用ISArt进行基于结构的零件和关节生成。场景生成支持两条互补路线：Unravel从图像重建可编辑场景，而SimForge从文本构建单房间和多房间环境。一个图原生的协调器协调构建、验证和有限修复，将失败路由到负责模块，同时保留未受影响的场景状态。PolicyForge将验证的世界绑定到任务和机器人实体，以生成可重放的演示。评估涵盖资产几何、场景质量和下游策略学习。在基于MuJoCo的LIBERO-Plus上，与Isaac Sim演示的联合训练将世界动作模型（WAM）的整体成功率从77.17%提高到89.43%。目标和空间成功率分别提高31.66和6.25个百分点。这些结果支持生成的数据对跨模拟器策略训练的实用性，而在长时程任务上的收益较为有限。
英文摘要
Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable execution. We present\textbf{Awomo-SimDataEngine}, an agentic system that connects asset and scenegeneration to robot demonstration synthesis. Shared asset services providerigid and articulated objects, including structure-grounded part and jointgeneration with ISArt. Scene generation supports two complementary routes:Unravel reconstructs editable scenes from images, while SimForge buildssingle-room and multi-room environments from text. A graph-native harnesscoordinates construction, validation, andbounded repair, routing failures to the responsible module while retainingunaffected scene state. PolicyForge binds validated worlds to tasks and robotembodiments to produce replayable demonstrations. Evaluations cover assetgeometry, scene quality, and downstream policy learning. On MuJoCo-basedLIBERO-Plus, co-training with Isaac Sim demonstrations improves the overallsuccess rate of a World-Action Model (WAM) from $77.17\%$ to $89.43\%$. Goal and spatialsuccess improve by $31.66$ and $6.25$ percentage points, respectively.These results support the utility of the generated data for cross-simulatorpolicy training, with more limited gains on long-horizon tasks.
