mlsanityData to 14 Oct 2026

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

arXiv 2512.14222 ↗First posted 16 Dec 2025cs.CV cs.ROcited by 6

Not on the map. Why?

Abstract (arXiv)

Aerial Vision-and-Language Navigation (AVLN) requires Unmanned Aerial Vehicle (UAV) agents to localize targets in large-scale urban environments based on linguistic instructions. While successful navigation demands both global environmental reasoning and local scene comprehension, existing UAV agents typically adopt mono-granularity frameworks that struggle to balance these two aspects. To address this limitation, this work proposes a History-Enhanced Two-Stage Transformer (HETT) framework, which integrates the two aspects through a coarse-to-fine navigation pipeline. Specifically, HETT first predicts coarse-grained target positions by fusing spatial landmarks and historical context, then refines actions via fine-grained visual analysis. In addition, a historical grid map is designed to dynamically aggregate visual features into a structured spatial memory, enhancing comprehensive scene awareness. Additionally, the CityNav dataset annotations are manually refined to enhance data quality. Experiments on the refined CityNav dataset show that HETT delivers significant performance gains, while extensive ablation studies further verify the effectiveness of each component.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 16 Dec 2025.

Builds on

21 of 34 references.

References · 21

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  3. 2018YOLOv3: An Incremental Improvementcited by 2,659
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  5. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  6. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  7. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  8. 2022Visual Language Maps for Robot Navigationcited by 365
  9. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  10. 2021History Aware Multimodal Transformer for Vision-and-Language Navigationcited by 271
  11. 2019Vision-and-Dialog Navigationcited by 250
  12. 2023ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environmentscited by 169
9 more
  1. 2023AerialVLN: Vision-and-Language Navigation for UAVscited by 121
  2. 2024Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodologycited by 95
  3. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  4. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 72
  5. 2024Volumetric Environment Representation for Vision-Language Navigationcited by 63
  6. 2022Target-Driven Structured Transformer Planner for Vision-Language Navigationcited by 58
  7. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 51
  8. 2024Controllable Navigation Instruction Generation with Chain of Thought Promptingcited by 21
  9. 2024Vision-Language Navigation with Energy-Based Policycited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescuecited by 4
  2. 2026See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of Viewcited by 2
  3. 2026Uncertainty-Aware Gaussian Map for Vision-Language Navigationcited by 1
  4. 2026DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigationcited by 1
  5. 2026RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigationcited by 0
  6. 2026LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregationcited by 0