UAV vision-language navigation (VLN) requires an agent to navigate complex 3D environments from an egocentric perspective while following ambiguous multi-step instructions over long horizons. Existing zero-shot methods remain limited, as they often rely on large base models, generic prompts, and loosely coordinated modules. In this work, we propose FineCog-Nav, a top-down framework inspired by human cognition that organizes navigation into fine-grained modules for language processing, perception, attention, memory, imagination, reasoning, and decision-making. Each module is driven by a moderate-sized foundation model with role-specific prompts and structured input-output protocols, enabling effective collaboration and improved interpretability. To support fine-grained evaluation, we construct AerialVLN-Fine, a curated benchmark of 300 trajectories derived from AerialVLN, with sentence-level instruction-trajectory alignment and refined instructions containing explicit visual endpoints and landmark references. Experiments show that FineCog-Nav consistently outperforms zero-shot baselines in instruction adherence, long-horizon planning, and generalization to unseen environments. These results suggest the effectiveness of fine-grained cognitive modularization for zero-shot aerial navigation. Project page: https://smartdianlab.github.io/projects-FineCogNav.

翻译：无人机视觉语言导航（VLN）要求智能体从自我中心视角在复杂三维环境中导航，同时遵循长时域上的模糊多步骤指令。现有零样本方法存在局限性，通常依赖大型基础模型、通用提示词及松散协调的模块。本文提出受人类认知启发的自上而下框架FineCog-Nav，将导航分解为语言处理、感知、注意力、记忆、想象、推理与决策等细粒度模块。各模块由中等规模基础模型驱动，辅以角色特定提示词与结构化输入输出协议，实现高效协作并增强可解释性。为支撑细粒度评估，我们构建了AerialVLN-Fine基准数据集，包含从AerialVLN中筛选的300条轨迹，提供句子级指令-轨迹对齐及包含显式视觉终点与地标参照的优化指令。实验表明，FineCog-Nav在指令遵循度、长时域规划及未知环境泛化能力上持续优于零样本基线方法。该结果验证了细粒度认知模块化对零样本空中导航的有效性。项目主页：https://smartdianlab.github.io/projects-FineCogNav。