# SAP-Nav：空间语义表示结合主动感知用于层次化开放词汇对象导航

> 原文链接：https://robotics.hellobike.com/papers/2026-08-13-2608-12707
> 频道：papers | 更新日期：2026-08-13 | 标签：arxiv, cs.RO
> 核心摘要：SAP-Nav以在线零样本主动感知构建可查询空间语义表示，并在LangMap、HM3D-OVON和真实机器人上验证层次化OVON。

# SAP-Nav：空间语义表示结合主动感知用于层次化开放词汇对象导航

::: v-pre
> 原文链接：[SAP-Nav: Spatial Semantic Representation Meets Active Perception for Hierarchical Open-Vocabulary Object Navigation](https://arxiv.org/abs/2608.12707)（arXiv 2608.12707 · 发布日期：2026-08-13）

**SAP-Nav: Spatial Semantic Representation Meets Active Perception for Hierarchical Open-Vocabulary Object Navigation**

SAP-Nav以在线零样本主动感知构建可查询空间语义表示，并在LangMap、HM3D-OVON和真实机器人上验证层次化OVON。

## 核心要点

- 层次化OVON需在未知环境中依据多层级自由指令导航，局部观测下空间定位与目标核验仍困难。
- 方法在线增量构建可查询空间语义表示，并通过主动获取房间视图支持已探索位置查询。
- 主动视点验证判断当前观测证据是否充分，必要时重定位到信息量更高的视点再核验候选。
- 在LangMap和HM3D-OVON上总体表现最佳，区域级SR较训练式方法提升12.2%；代码接收后公开。

**验证范围与局限**：验证范围包括LangMap、HM3D-OVON实验和真实机器人实验。

## 英文摘要 (Abstract)

Hierarchical open-vocabulary object navigation (OVON) requires agents to follow free-form instructions that may specify targets through scene-, room-, region-, and instance-level cues in unseen environments. Although recent work LangMap has formalized this setting, reliably solving it under partial observations remains challenging: spatial grounding requires persistent environment-level evidence, whereas target verification requires clear and discriminative candidate views. We present SAP-Nav, a fully online, zero-shot framework that addresses both requirements through active perception. SAP-Nav incrementally constructs a Queryable Spatial-Semantic Representation from actively acquired room views, enabling spatial semantic queries from any explored location. It further employs Active Viewpoint Verification to assess whether the current observation provides sufficient evidence and, when necessary, reposition the agent to a more informative viewpoint before verifying candidates against category and attribute constraints. Although designed for hierarchical OVON, SAP-Nav supports both hierarchical and standard category-level OVON without task-specific training or precomputed scene maps. Experiments on LangMap and HM3D-OVON show that SAP-Nav achieves the overall best performance, including a 12.2% improvement in SR over training-based methods on region-level navigation. Real-world robot experiments further demonstrate its practical feasibility. Code will be made publicly available upon acceptance.

作者：Xuetong Pei, Jian Liu, Vidura Munasinghe, Bo Miao, U-Xuan Tan, Wenrui Ding, Na Zhao
:::

## 原始参考来源 (Sources)

- [arXiv 2608.12707：SAP-Nav: Spatial Semantic Representation Meets Active Perception for Hierarchical Open-Vocabulary Object Navigation](https://arxiv.org/abs/2608.12707)