发表机构
Singapore Management University; Technical University Berlin; Max Planck Institute; Technical University Braunschweig（新加坡管理大学; 柏林工业大学; 马克斯·普朗克研究所; 布伦瑞克工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
D3D-GEN是一种新型3D世界生成系统，结合领域智能体与RAG流水线，可快速生成领域锚定的交互式3D世界，已构建多领域数据库并生成数十种仿真环境，适配Isaac Sim等仿真器。
AI 中文摘要
针对社交导航的具身AI的训练与验证高度依赖真实的仿真环境，但当前诸多方法难以在真实感与可仿真性之间取得平衡。我们提出D3D-GEN，这是一种新型世界生成系统，它将领域智能体与锚定该领域的检索增强生成（RAG）流水线相结合。我们的系统可让用户快速生成领域锚定、完全交互式的3D世界，它通过自动化收集领域知识以及合成真实的平面图与物体放置来实现，且不依赖任何固定的3D模型数据库。给定一个领域描述提示，研究智能体会收集公开可获取的领域特定数据并构建一个持久的领域数据库。利用该数据库，我们的RAG流水线通过动态查询用户提供的语义数据库（该数据库可轻松扩展或修改）来生成合理的平面图与物体放置。输出为完全交互式的3D世界，可被流行的仿真器Isaac Sim与Gazebo加载。借助我们的方法，我们已为多个常见领域（室内住宅、医院、办公室）构建了数据库，并为每个领域生成了数十个不同、合理的仿真环境。我们推出的D3D-GEN带有一个本地网页前端，可促进机器人仿真的快速交互式世界生成。
英文摘要
Training and validation of Embodied AI for social navigation critically depends on realistic simulation environments, yet many current approaches fail to find a balance between realism and simulability. We propose D3D-GEN, a novel world generation system that combines a domain agent with a retrieval-augmented generation (RAG) pipeline grounded in that domain. Our system enables users to rapidly generate domain-grounded, fully interactive 3D worlds by automating both the collection of domain knowledge and the synthesis of realistic floorplans and object placements, without dependence on any fixed 3D model database. Given a domain description prompt, the research agent collects publicly accessible domain-specific data and constructs a persistent domain database. Using this database, our RAG pipeline generates plausible floorplans and object placements by dynamically querying a user-provided semantic database, which can be easily extended or modified. The output is a fully interactive 3D world loadable by the popular simulators Isaac Sim and Gazebo. With our approach, we have built databases for several common domains (indoor residential, hospital, office) and generated dozens of distinct, plausible simulation environments for each domain. We present D3D-GEN with a local web frontend that facilitates rapid, interactive world generation for robot simulation.
Comments8 pages, 5 figures, and 5 tables. Accepted at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)
