# Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4

arXiv: https://arxiv.org/abs/2510.02728 · HTML: https://mlsanity.com/paper/2510.02728/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2025.

## Built on by (most cited first, 3 of 3)

- [Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation](https://mlsanity.com/paper/2511.13269/) (2025)
- [SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Prediction](https://mlsanity.com/paper/2602.21589/) (2026)
- [Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection](https://mlsanity.com/paper/2604.05405/) (2026)

## Abstract (arXiv)

Cross-modal drone navigation remains a challenging task in robotics, requiring efficient retrieval of relevant images from large-scale databases based on natural language descriptions. The RoboSense 2025 Track 4 challenge addresses this challenge, focusing on robust, natural language-guided cross-view image retrieval across multiple platforms (drones, satellites, and ground cameras). Current baseline methods, while effective for initial retrieval, often struggle to achieve fine-grained semantic matching between text queries and visual content, especially in complex aerial scenes. To address this challenge, we propose a two-stage retrieval refinement method: Caption-Guided Retrieval System (CGRS) that enhances the baseline coarse ranking through intelligent reranking. Our method first leverages a baseline model to obtain an initial coarse ranking of the top 20 most relevant images for each query. We then use Vision-Language-Model (VLM) to generate detailed captions for these candidate images, capturing rich semantic descriptions of their visual content. These generated captions are then used in a multimodal similarity computation framework to perform fine-grained reranking of the original text query, effectively building a semantic bridge between the visual content and natural language descriptions. Our approach significantly improves upon the baseline, achieving a consistent 5% improvement across all key metrics (Recall@1, Recall@5, and Recall@10). Our approach win TOP-2 in the challenge, demonstrating the practical value of our semantic refinement strategy in real-world robotic navigation scenarios.