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

• URL: http://arxiv.org/abs/2512.14222v2
• Date: Wed, 17 Dec 2025 02:51:52 GMT
• Title: History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigation
• Authors: Xichen Ding, Jianzhe Gao, Cong Pan, Wenguan Wang, Jie Qin,
• Abstract summary: Aerial Vision-and-Language Navigation (AVLN) requires Unmanned Aerial Vehicle (UAV) agents to localize targets in large-scale urban environments.<n>Existing UAV agents typically adopt mono-granularity frameworks that struggle to balance these two aspects.<n>This work proposes a History-Enhanced Two-Stage Transformer (HETT) framework, which integrates the two aspects through a coarse-to-fine navigation pipeline.
• Score: 64.51891404034164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation [67.68165784193556]
  Nav-$R2$ is a framework that explicitly models two types of relationships, target-environment modeling and environment-action planning.<n>Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives.<n>Nav-R2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline.
  arXiv  Detail & Related papers  (2025-12-02T04:21:02Z)
• GoViG: Goal-Conditioned Visual Navigation Instruction Generation [69.79110149746506]
  We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to autonomously generate precise and contextually coherent navigation instructions.<n>GoViG exclusively leverages raw egocentric visual data, substantially improving its adaptability to unseen and unstructured environments.
  arXiv  Detail & Related papers  (2025-08-13T07:05:17Z)
• Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation [54.04601077224252]
  Embodied scene understanding requires not only comprehending visual-spatial information but also determining where to explore next in the 3D physical world.<n>underlinetextbf3D vision-language learning enables embodied agents to effectively explore and understand their environment.<n>model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images.
  arXiv  Detail & Related papers  (2025-07-05T14:15:52Z)
• CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory [39.76840258489023]
  Aerial vision-and-language navigation (VLN) requires drones to interpret natural language instructions and navigate complex urban environments.<n>We propose textbfCityNavAgent, a large language model (LLM)-empowered agent that significantly reduces the navigation complexity for urban aerial VLN.
  arXiv  Detail & Related papers  (2025-05-08T20:01:35Z)
• CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance [13.922655150502365]
  CREStE is a scalable learning-based mapless navigation framework.<n>It addresses the open-world generalization and robustness challenges of outdoor urban navigation.<n>We evaluate CREStE on the task of kilometer-scale mapless navigation in a variety of city, offroad, and residential environments.
  arXiv  Detail & Related papers  (2025-03-05T21:42:46Z)
• Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments [10.953629652228024]
  Vision-and-Language Navigation (VLN) agents associate time-sequenced visual observations with corresponding instructions to make decisions.<n>In this paper, we address the mismatch between human-centric instructions and quadruped robots with a low-height field of view.<n>We propose a Ground-level Viewpoint Navigation (GVNav) approach to mitigate this issue.
  arXiv  Detail & Related papers  (2025-02-26T10:30:40Z)
• NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation [15.628308089720269]
  Vision-and-Language Navigation (VLN) aims to enable embodied agents to navigate in complicated visual environments through natural language commands. We propose NavAgent, the first urban UAV embodied navigation model driven by a large Vision-Language Model. We build a visual recognizer for landmark capable of identifying and linguisticizing fine-grained landmarks. To train the visual recognizer for landmark, we develop NavAgent-Landmark2K, the first fine-grained landmark dataset for real urban street scenes.
  arXiv  Detail & Related papers  (2024-11-13T12:51:49Z)
• CityNav: A Large-Scale Dataset for Real-World Aerial Navigation [25.51740922661166]
  We introduce CityNav, the first large-scale real-world dataset for aerial VLN.<n>Our dataset consists of 32,637 human demonstration trajectories, each paired with a natural language description.<n>We provide a methodology of creating geographic semantic maps that can be used as an auxiliary modality input during navigation.
  arXiv  Detail & Related papers  (2024-06-20T12:08:27Z)
• Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation [87.03299519917019]
  We propose a dual-scale graph transformer (DUET) for joint long-term action planning and fine-grained cross-modal understanding. We build a topological map on-the-fly to enable efficient exploration in global action space. The proposed approach, DUET, significantly outperforms state-of-the-art methods on goal-oriented vision-and-language navigation benchmarks.
  arXiv  Detail & Related papers  (2022-02-23T19:06:53Z)
• History Aware Multimodal Transformer for Vision-and-Language Navigation [96.80655332881432]
  Vision-and-language navigation (VLN) aims to build autonomous visual agents that follow instructions and navigate in real scenes. We introduce a History Aware Multimodal Transformer (HAMT) to incorporate a long-horizon history into multimodal decision making.
  arXiv  Detail & Related papers  (2021-10-25T22:54:41Z)
• Structured Scene Memory for Vision-Language Navigation [155.63025602722712]
  We propose a crucial architecture for vision-language navigation (VLN) It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment.
  arXiv  Detail & Related papers  (2021-03-05T03:41:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.