mlsanityData to 14 Oct 2026

See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View

arXiv 2606.20045 ↗First posted 18 Jun 2026cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial embodied agents, namely whether a UAV can accurately ground a visible target and translate vision-language evidence into precise 3D motion once the target enters its field of view. To address this limitation, we introduce UAV-VLN-FOV, a target-visible navigation task that isolates the see-and-reach stage and enables a more diagnostic evaluation of terminal reaching ability. We further propose 3DG-VLN, a vision-language waypoint prediction framework guided by dynamic 3D direction cues to enhance fine-grained visual grounding and spatial direction alignment for precise target reaching. Specifically, 3DG-VLN adaptively processes high-resolution front-view and downward-view observations to preserve fine-grained visual and geometric details for target grounding. It also updates the target-relative direction online during closed-loop navigation, allowing the agent to maintain spatial alignment with the target and reduce accumulated direction drift. To support this task, we construct a dedicated high-resolution benchmark which contains 2,717 trajectories with target-oriented high-level instructions, high-resolution front-view and downward-view egocentric observations, and continuous 3D waypoint annotations. Experiments show that 3DG-VLN outperforms competitive UAV-VLN baselines, achieving a 13.82% improvement in success rate. Real-world trials further demonstrate the potential of 3DG-VLN for practical see-and-reach navigation. The source code and benchmark are available at https://github.com/xuefanfu/3DG-VLN.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

31 of 45 references.

References · 31

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  4. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  5. 2023AerialVLN: Vision-and-Language Navigation for UAVscited by 121
  6. 2024Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodologycited by 95
  7. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 50
  8. 2022Aerial Vision-and-Dialog Navigationcited by 49
  9. 2025UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agentscited by 33
  10. 2025CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memorycited by 32
  11. 2025UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learningcited by 31
  12. 2025Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigationcited by 23
19 more
  1. 2025VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environmentscited by 23
  2. 2025FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Modelscited by 22
  3. 2025Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understandingcited by 19
  4. 2024NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigationcited by 18
  5. 2025FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Taskscited by 17
  6. 2025COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigationcited by 15
  7. 2025SkyVLN: Vision-and-Language Navigation and NMPC Control for UAVs in Urban Environmentscited by 14
  8. 2025AeroDuo: Aerial Duo for UAV-based Vision and Language Navigationcited by 13
  9. 2025OpenVLN: Open-world Aerial Vision-Language Navigationcited by 12
  10. 2025AirSim360: A Panoramic Simulation Platform within Drone Viewcited by 12
  11. 2026AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Controlcited by 11
  12. 2025Generalized Incremental Learning under Concept Drift across Evolving Data Streamscited by 7
  13. 2025History-Enhanced Two-Stage Transformer for Aerial Vision-and-Language Navigationcited by 6
  14. 2026VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptationcited by 5
  15. 2025Multimodal Inverse Attention Network with Intrinsic Discriminant Feature Exploitation for Fake News Detectioncited by 4
  16. 2025Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigationcited by 4
  17. 2026OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiencycited by 4
  18. 2026LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigationcited by 3
  19. 2025Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimizationcited by 1
  2. 2026Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Mapscited by 1