发表机构
Nanyang Technological University（南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SOR-Nav提出一种分层导航系统，通过上下文门控的LLM监督器在探索与跨区域重定位间决策，在HM3D和MP3D基准上取得最优SR和SPL，MP3D上SPL提升至38.5%。
AI 中文摘要
目标导航要求具身智能体在部分可观测和有限运动预算的条件下，在未见环境中找到目标物体。现有方法主要通过排序候选目的地来优化机器人下一步应该去哪里。与这些方法不同，我们提出了SOR-Nav，一个分层导航系统，它明确地在继续探索当前上下文与放弃当前上下文并转向更有希望的可达区域之间进行仲裁。首先，构建了一个自主语义探索系统，该系统累积持久的3D物体聚类，并将可达前沿组织成聚类决策图，以提供高效的搜索抽象。然后，SOR-Nav使用一个上下文门控的、由LLM驱动的物体搜索监督器来评估当前搜索上下文的适用性，并决定是继续探索还是执行跨区域重定位到另一个可达的前沿聚类。在HM3D-v1、HM3D-v2和MP3D的完整、未过滤的验证集上，SOR-Nav在所有三个基准上取得了报告的最强成功率（SR）和按路径长度加权的成功率（SPL）。特别是在MP3D上，它将之前最佳的SPL从18.1%提高到38.5%，翻了一倍多，同时将SR从50.7%提高到61.8%。嵌套的HM3D-v2消融实验验证了所提出的决策结构，而连续三目标物理部署则展示了在真实世界场景中的持久ObjectNav操作。
英文摘要
Object navigation requires an embodied agent to find an object in an unseen environment under partial observability and a limited motion budget. Existing methods primarily optimize where the robot should go next by ranking candidate destinations. In contrast to these methods, we present SOR-Nav, a hierarchical navigation system that explicitly arbitrates between continuing to explore the current context and abandoning it for a more promising reachable region. First, an autonomous semantic exploration system is built that accumulates persistent 3D object clusters and organizes reachable frontiers into a cluster decision graph to provide an efficient search abstraction. Then, SOR-Nav uses a context-gated LLM-driven object-search supervisor to evaluate the suitability of the current search context and decide whether to continue exploration or perform cross-region relocation to another reachable frontier cluster. Across the complete, unfiltered validation sets of HM3D-v1, HM3D-v2, and MP3D, SOR-Nav achieves the strongest reported Success Rate (SR) and Success weighted by Path Length (SPL) on all three benchmarks. On MP3D in particular, it more than doubles the previous best SPL from 18.1\% to 38.5\% while increasing SR from 50.7\% to 61.8\%. Nested HM3D-v2 ablations validate the proposed decision structure, while a continuous three-target physical deployment demonstrates persistent ObjectNav operation in real-world scenarios.
