History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation

Aerial Vision-and-Language Navigation (AVLN) requires Unmanned Aerial Vehicle (UAV) agents to localize targets in complex urban environments using linguistic instructions. While successful navigation demands both global environmental reasoning and fine-grained scene comprehension, existing UAV agents typically rely on single-step planning paradigms that struggle to balance these two aspects. To address this limitation, this work proposes a History-Enhanced Two-Stage Transformer (HETT) framework, which navigates in a coarse-to-fine manner. Specifically, HETT first predicts coarse-grained target positions using spatial landmarks and historical context, then refines actions through fine-grained visual analysis. Moreover, a historical grid map is designed to dynamically aggregate and organize visual features into a structured spatial memory, enhancing comprehensive scene awareness. Additionally, the CityNav dataset annotations are manually refined to enhance data quality. Experimental results demonstrate that HETT achieves state-of-the-art Success Rate (SR) on our refined CityNav dataset. The refined dataset and code will be released.