Paper Overview
- Field: Computer Vision (CV)
- Authors: Dian Shao, Zhengzheng Xu, Peiyang Wang, Like Liu, Yule Wang, Jieqi Shi, Jing Huo
- Published: 2026-04-17
- arXiv: 2604.16298
- Project page: https://smartdianlab.github.io/projects-FineCogNav
- FineCog-Nav framework: 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.
- Module design: 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.
- AerialVLN-Fine benchmark: A fine-grained evaluation benchmark of 300 curated trajectories from AerialVLN, featuring sentence-level instruction-trajectory alignment and refined instructions with explicit visual endpoints and landmark references.
Summary
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.
Key Contributions
Results
Experiments show that FineCog-Nav consistently outperforms zero-shot baselines in instruction following, long-horizon planning, and generalization to unseen environments. These results demonstrate the effectiveness of fine-grained cognitive modularization for zero-shot aerial navigation.
---
*Auto-collected on 2026-04-21.*