SPENav: Dynamic Object Filtering With Spatial Perception Enhancement for Vision-Language Navigation

The Vision-language navigation task requires agents to efficiently interpret visual cues in the environment and accurately follow long-range instructions, posing significant challenges to their scene memory and spatial reasoning capabilities. Existing methods typically construct memory systems directly from raw visual observations. However, task-irrelevant cues commonly present in the environment can continuously introduce localization errors during navigation, severely limiting the agent’s performance in complex scenes. Meanwhile, due to the lack of transferable general knowledge priors, existing agents exhibit notable limitations in spatial perception, which undermines the reliability of their decision-making in unseen environments. To address these issues, this paper proposes the dynamic object filtering with Spatial Perception Enhancement for Vision-Language Navigation (SPENav), which aggregates open-vocabulary perception with multi-level information modeling. At the local level, the Hierarchical Semantic Prior Extractor and Room-Information-Guided Filtering construct task-oriented semantic priors to capture critical objects and suppress irrelevant features. At the global level, the Spatial-Instructional Guided Dual Attention module leverages spatial information and instruction guidance to enable the agent to develop selective memory that is goal- and task-oriented. On the unseen test split of R2R, SPENav achieves a 76% Success Rate (SR) and a 65% Success weighted by Path Length (SPL). These results demonstrate the effectiveness of task-oriented feature selection and multi-level semantic modeling in enhancing cross-modal understanding and adaptive navigation performance.