发表机构
Distributed Systems Group, TU Wien; University of Helsinki; University of Klagenfurt; University of Messina; ICREA（维也纳工业大学分布式系统研究组; 赫尔辛基大学; 克拉根福大学; 墨西拿大学; 加泰罗尼亚高级研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文探讨无人机检测从目标检测向边缘原生语义理解转变，利用轻量级视觉语言模型，在Jetson硬件上验证可行性，并展望自主协作的未来方向。
AI 中文摘要
桥梁、隧道、水坝和电力线网络等关键基础设施资产需要及时且可扩展的检测。虽然传统的人工检测成本高昂且存在危险，但基于无人机（UAV）的检测已成为监测难以到达结构的有效替代方案。现有的无人机检测流程已从以云为中心的离线处理演变为基于边缘的感知，使用诸如YOLO之类的轻量级目标检测器进行实时缺陷定位。本文探讨了向完全边缘原生语义检测的转变，该检测由轻量级视觉语言模型（VLMs）驱动，使无人机超越目标检测，实现上下文结构理解。文章对现有无人机检测架构进行了分类，识别了其关键系统挑战和架构要求，并使用COCO-Bridge数据集在NVIDIA Jetson无人机级硬件上实验评估了语义边缘智能的可行性。评估集成了用于目标定位的微调YOLO-26M和用于语义推理的轻量级SmolVLM-256。最后，文章概述了在边缘-云连续体中实现代理式、自主、可信和协作的语义无人机检测的未来方向。
英文摘要
Critical infrastructure assets such as bridges, tunnels, dams, and power line networks require timely and scalable inspection. While conventional manual inspection remains costly and hazardous, unmanned aerial vehicle (UAV)-based inspection has emerged as an efficient alternative for monitoring difficult-to-access structures. Existing UAV inspection pipelines have evolved from cloud-centric offline processing toward edge-based perception using lightweight object detectors such as YOLO for real- time defect localization. This article explores the transition toward fully edge-native semantic inspection powered by lightweight vision language models (VLMs), where UAVs move beyond object detection toward contextual structural understanding. It categorizes existing UAV inspection architectures, identifies their key system challenges and architectural requirements, and experimentally assesses the feasibility of semantic edge intelligence on NVIDIA Jetson UAV-class hardware using the COCO-Bridge dataset. The evaluation integrates a fine-tuned YOLO-26M for object localization and a lightweight SmolVLM-256 for semantic reasoning. Finally, it outlines future directions toward agentic, autonomous, trustworthy, and collaborative semantic UAV inspection across the edge-cloud continuum.
Comments8 pages, 3 figures, 2 tables, Sumbitted to IEEE Internet Computing 2026
