外观
论文arXiv 2610.1943114 天前
$S^3$-Nav：面向语言引导机器人导航的结构化空间-语义决策
原文链接：$S^3$-Nav: Structured Spatial-Semantic Decision Making for Language-Guided Robot Navigation（arXiv 2610.19431 · 发布日期：2026-10-14）
$S^3$-Nav: Structured Spatial-Semantic Decision Making for Language-Guided Robot Navigation
S^3-Nav面向部分可观测的语言引导导航，构建持久空间语义状态并控容呈现，在多环境物体与关系目标任务验证。
核心要点
- 针对部分可观测下语言导航缺少完整环境表示的设定。
- 增量构建持久空间语义状态，并向高层策略暴露控容任务视图。
- 高层导航输出在执行或终止前，由语义证据和几何观测独立验证。
- 多环境物体与关系目标任务显示，可靠性提升且策略推理成本降低。
验证范围与局限：验证范围为多个环境中的物体目标和关系目标任务；摘要未说明仿真或真机。
英文摘要 (Abstract)
This paper presents $S^3$-Nav, a structured spatial-semantic decision-making framework for language-guided robot navigation under partial observability. Rather than assuming a complete environment representation in advance, $S^3$-Nav incrementally constructs persistent spatial-semantic state while exposing only a capacity-controlled, task-conditioned view to the high-level policy. This separation decouples what the robot must retain from what the policy needs to inspect, allowing decision complexity to be controlled without discarding grounded evidence required for subsequent reasoning and validation. High-level navigation outputs remain provisional and are independently grounded and validated against persistent semantic evidence and current geometric observations before physical execution or task termination. Evaluations across multiple environments and object- and relation-goal tasks demonstrate that separating persistent state, decision-facing evidence, and execution authority improves closed-loop navigation reliability while reducing policy reasoning cost.
作者：Chaemin Lee, Hae Min Cho
来源
本页事实对应的公开页面，以原文为准。