Floor plans encapsulate compact spatial priors, enabling agents to navigate unseen scenes more efficiently. While prior work has explored floor plan-guided navigation, it has focused mainly on PointNav and a limited set of environments. To bridge this gap, we introduce FloVerse, a new task for floor plan-guided embodied navigation that unifies PointNav, ObjectNav, and ImageNav. To support FloVerse, we assemble FloVerse-1.6K, a large-scale dataset of 1.6K scenes from HM3D and Gibson 4+, paired with corresponding floor plans, comprising 240K expert trajectories and 12M RGBD frames. We further propose ThreeDiff, a two-stage imitation learning policy comprising a planner, a diffusion-based multimodal goal-reasoning module trained via masked-modality modeling, and a refiner, a depth-based trajectory-refinement module for safe execution. Extensive experiments demonstrate that (1) floor-plan priors improve navigation performance across all goal modalities, and (2) ThreeDiff implicitly captures spatial information from floor plans. These results underscore the effectiveness of spatial priors and validate our proposed unified approach for floor plan-guided embodied navigation.

翻译：平面图蕴含了紧凑的空间先验信息，使智能体能够更高效地探索未知场景。尽管已有研究探索了基于平面图引导的导航，但主要集中于PointNav任务及有限的场景集合。为填补这一空白，我们提出了FloVerse——一种平面图引导的具身导航新任务，统一了PointNav、ObjectNav和ImageNav三种导航模式。为支撑FloVerse研究，我们构建了FloVerse-1.6K大规模数据集，包含来自HM3D和Gibson 4+的1600个场景及其对应平面图，涵盖24万条专家轨迹与1200万帧RGBD图像。我们进一步提出ThreeDiff两阶段模仿学习策略：由规划器、基于扩散的多模态目标推理模块（通过掩码模态训练实现）和精炼器组成。其中扩散模块用于目标推理，深度轨迹精炼模块则通过深度信息确保安全执行。大量实验表明：（1）平面图先验能提升所有目标模态下的导航性能；（2）ThreeDiff能从平面图中隐式捕获空间信息。这些结果凸显了空间先验的有效性，并验证了所提出的平面图引导具身导航统一方法的可行性。