SpaceVLN：具有在线空间认知记忆与推理的零样本视觉与语言导航智能体
SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning
AI总结：
提出SpaceVLN，通过空间认知记忆和任务引导的空间推理，在零样本设置下实现连续环境中的视觉与语言导航，在多个基准上达到最优性能。
摘要：
连续环境中的视觉与语言导航要求智能体理解未见环境的空间结构以遵循语言指令。尽管基础模型为无需任务特定策略训练的零样本导航开辟了有希望的路径，但许多导航器仍依赖局部视觉线索和基于线性历史的推理，忽视了探索区域、穿越路径、地标及其空间关系的空间本质。本文提出SpaceVLN，一种围绕空间认知记忆和任务引导的空间推理构建的导航智能体。具体而言，SpaceVLN引入了一个高效的分阶段闭环框架，其中规划和执行围绕可验证的空间-地标阶段组织。导航过程中，智能体逐步将探索区域抽象为空间航点，并动态维护子任务基础的地标证据，形成层次化的空间认知记忆以进行进度定位和空间关系理解。基于此记忆，Spatial-CoT将任务进度推理与空间感知、分析和预测相结合，实现任务引导的空间推理以用于具身导航。统一阶段接口使SpaceVLN能够在统一的零样本设置下处理视觉与语言导航和目标导向导航，无需任务特定策略训练。在R2R-CE、RxR-CE、GN-Bench和HM3D-OVON上，SpaceVLN实现了最先进的零样本性能，真实机器人部署进一步验证了其适用性。这些结果突显了空间认知记忆和任务引导的空间推理作为更强具身导航智能体的实用基础。
英文摘要：
Vision-and-Language Navigation in continuous environments requires agents to understand the spatial structure of previously unseen environments in order to follow language instructions. Although foundation models have opened a promising path toward zero-shot navigation without task-specific policy training, many navigators still rely on local visual cues and linear history-based reasoning, overlooking the spatial nature of navigation across explored regions, traversed paths, landmarks, and their spatial relations. In this paper, we propose SpaceVLN, a navigation agent built around Spatial Cognitive Memory and Task-Guided Spatial Reasoning. Specifically, SpaceVLN introduces an efficient stagewise closed-loop framework where planning and execution are organized around verifiable space--landmark stages. During navigation, the agent progressively abstracts explored regions into Spatial Waypoints and dynamically maintains subtask-grounded landmark evidence, forming a hierarchical Spatial Cognitive Memory for progress localization and spatial-relation understanding. Built on this memory, Spatial-CoT integrates task-progress reasoning with spatial perception, analysis, and prediction, enabling Task-Guided Spatial Reasoning for embodied navigation. The unified stage interface enables SpaceVLN to address both Vision-and-Language Navigation and Object-Goal Navigation under a unified zero-shot setting, without task-specific policy training. Across R2R-CE, RxR-CE, GN-Bench, and HM3D-OVON, SpaceVLN achieves state-of-the-art zero-shot performance, and real-robot deployment further validates its applicability. These results highlight Spatial Cognitive Memory and Task-Guided Spatial Reasoning as a practical foundation for stronger embodied navigation agents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
