# ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation

arXiv: https://arxiv.org/abs/2603.08007 · HTML: https://mlsanity.com/paper/2603.08007/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 20 of 20)

- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want](https://mlsanity.com/paper/2403.20271/) (2024)
- [Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology](https://mlsanity.com/paper/2410.07087/) (2024)
- [Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models](https://mlsanity.com/paper/2407.07035/) (2024)
- [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024)
- [CityNav: A Large-Scale Dataset for Real-World Aerial Navigation](https://mlsanity.com/paper/2406.14240/) (2024)
- [CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory](https://mlsanity.com/paper/2505.05622/) (2025)
- [Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2406.16449/) (2024)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models](https://mlsanity.com/paper/2505.12835/) (2025)
- [Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation](https://mlsanity.com/paper/2410.08500/) (2024)
- [CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data](https://mlsanity.com/paper/2310.18773/) (2023)
- [Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models](https://mlsanity.com/paper/2404.04514/) (2024)
- [GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigation](https://mlsanity.com/paper/2504.09587/) (2025)
- [Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts](https://mlsanity.com/paper/2406.02208/) (2024)
- [SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models](https://mlsanity.com/paper/2507.13152/) (2025)
- [The Spatial Blindspot of Vision-Language Models](https://mlsanity.com/paper/2601.09954/) (2026)
- [Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts](https://mlsanity.com/paper/2601.04073/) (2026)
- [VPN: Visual Prompt Navigation](https://mlsanity.com/paper/2508.01766/) (2025)

## Built on by (most cited first, 2 of 2)

- [CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation](https://mlsanity.com/paper/2606.28397/) (2026)
- [Structured World-State Reasoning for Agentic Robotic Search](https://mlsanity.com/paper/2609.23841/) (2026)

## Abstract (arXiv)

Existing aerial Vision-Language Navigation (VLN) methods predominantly adopt a detection-and-planning pipeline, which converts open-vocabulary detections into discrete textual scene graphs. These approaches are plagued by inadequate spatial reasoning capabilities and inherent linguistic ambiguities. To address these bottlenecks, we propose a Visual-Spatial Reasoning (ViSA) enhanced framework for aerial VLN. Specifically, a triple-phase collaborative architecture is designed to leverage structured visual prompting, enabling Vision-Language Models (VLMs) to perform direct reasoning on image planes without the need for additional training or complex intermediate representations. Comprehensive evaluations on the CityNav benchmark demonstrate that the ViSA-enhanced VLN achieves a 70.3% improvement in success rate compared to the fully trained state-of-the-art (SOTA) method, elucidating its great potential as a backbone for aerial VLN systems.