MANSION：面向长程任务的多楼层语言到 3D 场景生成
MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks
把语言驱动的程序化生成扩展到带垂直结构约束的多层建筑级 3D 场景，为视觉/具身研究者提供可导航、可编辑的大规模室内环境生成器与评测床，可直接用于长程跨楼层导航与空间推理智能体的训练与压力测试。
原文依据 the first language-driven framework for generating building-scale, multi-floor 3D environments
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论真实世界的机器人任务是长程的，且常常跨越多个楼层，需要丰富的空间推理能力。然而，现有的具身基准大多局限于单层的室内环境，无法反映真实任务的复杂性。我们提出 MANSION，这是首个用于生成建筑级、多楼层 3D 环境的语言驱动框架。MANSION 能够感知垂直结构约束，生成真实、可导航的整栋建筑结构以及多样、宜人的场景，从而支持跨楼层长程任务的开发与评测。在该框架基础上，我们发布了 MansionWorld，一个包含 1000 多栋多样建筑（从医院到办公室）的数据集，并提供一个任务语义场景编辑智能体，可利用开放词表指令定制这些环境以满足特定用户需求。基准测试表明，最优的智能体在我们的设定下性能急剧下降，这确立了 MANSION 作为下一代空间推理与规划关键测试平台的地位。
英文原文摘要 1059 字符
Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning.