AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation

• URL: http://arxiv.org/abs/2609.08442v1
• Date: Tue, 08 Sep 2026 08:47:54 GMT
• Title: AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation
• Abstract summary: Aerial Vision-and-Language Navigation requires drones to follow natural-language instructions and navigate through complex urban environments.<n>We propose AirAnchor, a new paradigm that bridges local and global spatial information through spatial anchors and integrates both into a shared navigation framework.<n>AirAnchor substantially outperforms existing zero-shot baselines, validating the effectiveness and efficiency of the proposed paradigm.
• Score: 12.53394125609704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aerial Vision-and-Language Navigation requires drones to follow natural-language instructions and navigate through complex urban environments. Accurate navigation relies on both local and global spatial information, which support immediate action grounding and long-horizon path planning, respectively. However, existing zero-shot methods typically operate at a single spatial scale, relying either on local representations constructed online from current observations or on global memories built offline from historical experience. To address this limitation, we propose AirAnchor, a new paradigm that bridges local and global spatial information through spatial anchors and integrates both into a shared navigation framework, enabling comprehensive spatial grounding for decision-making. AirAnchor consists of three core components: (1) Query-Driven Spatial Anchor Grounding, which identifies decision-relevant anchors from visual observations and organizes them into local spatial representations; (2) Persistent Object Spatial Memory, which incrementally maintains an object knowledge base as persistent global spatial memory and retrieves landmark-related spatial priors; and (3) a Spatially-Informed Navigation Agent, which explicitly integrates both local and global spatial information into an agentic framework for decision-making. Extensive experiments on AerialVLN demonstrate that AirAnchor substantially outperforms existing zero-shot baselines, validating the effectiveness and efficiency of the proposed paradigm.

Related papers

• SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning [59.64305326980364]
  SpaceVLN is a navigation agent built around Spatial Cognitive Memory and Task-Guided Spatial Reasoning.<n>Built on this memory, Spatial-CoT integrates task-progress reasoning with spatial perception, analysis, and prediction.<n>Across R2R-CE, RxR-CE, GN-Bench, and HM3D-OVON, SpaceVLN achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2026-06-08T03:42:08Z)
• SPAN-Nav: Generalized Spatial Awareness for Versatile Vision-Language Navigation [26.52802135982273]
  We introduce SPAN-Nav, an end-to-end foundation model designed to infuse embodied navigation with universal 3D spatial awareness.<n>SPAN-Nav extracts spatial priors across diverse scenes through an occupancy prediction task.<n>We present a massive dataset of 4.2 million occupancy annotations that covers both indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2026-03-10T03:59:34Z)
• SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation [48.17712857341527]
  We introduce a zero-shot vision-and-language navigation (VLN) agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation.<n>Experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods.
  arXiv  Detail & Related papers  (2026-01-11T08:39:19Z)
• From reactive to cognitive: brain-inspired spatial intelligence for embodied agents [50.99942960312313]
  Brain-inspired Spatial Cognition for Navigation (BSC-Nav) is a unified framework for constructing and leveraging structured spatial memory in embodied agents.<n> BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals.
  arXiv  Detail & Related papers  (2025-08-24T03:20:48Z)
• Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation [35.71602601385161]
  We present a novel vision-language model (VLM)-based navigation framework.<n>Our approach enhances spatial reasoning and decision-making in long-horizon tasks.<n> Experimental results demonstrate that the proposed method surpasses previous state-of-the-art approaches in object navigation tasks.
  arXiv  Detail & Related papers  (2025-02-20T04:41:40Z)
• 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)
• SIRI: Spatial Relation Induced Network For Spatial Description Resolution [64.38872296406211]
  We propose a novel relationship induced (SIRI) network for language-guided localization. We show that our method is around 24% better than the state-of-the-art method in terms of accuracy, measured by an 80-pixel radius. Our method also generalizes well on our proposed extended dataset collected using the same settings as Touchdown.
  arXiv  Detail & Related papers  (2020-10-27T14:04:05Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)

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.