云端、边缘还是拆分？面向无人机AI的机载与拆分视觉语言模型部署剖析
Cloud, Edge, or Split? Profiling Onboard and Split Vision-Language Model Deployment for Drone AI
浏览论文内容
中文总结 AI 辅助
本文以SmolVLM-256M为轻量级VLM代表，系统剖析机载、云端和拆分三种部署范式，发现无普遍最优策略，首选方案取决于网络条件与图像分辨率的交互。
中文摘要 AI 辅助
视觉语言模型（VLMs）使无人机（UAVs）等边缘设备能够通过自然语言指令解释视觉观察并推理复杂环境。然而，其实际部署仍具挑战性，因为机载推理受限于有限的计算、内存和能源资源，而基于云的推理则引入通信延迟、带宽开销以及对网络连接的依赖。为解决这些限制，拆分计算提供了一种有前景的替代方案，即在资源受限的无人机与能力更强的远程服务器之间划分VLM推理。然而，针对轻量级VLM，完全机载、基于云和拆分计算架构之间的性能权衡尚未被系统性地剖析。本文以SmolVLM-256M作为代表性轻量级VLM，对这三种部署范式进行基准测试。我们量化了它们在不同图像分辨率和网络条件下的推理延迟、计算资源利用率、通信开销和能耗。结果表明，没有一种部署策略是普遍最优的；相反，首选策略取决于网络条件与输入图像分辨率之间的交互作用。
英文摘要
Vision-Language Models (VLMs) enable edge devices like unmanned aerial vehicles (UAVs) to interpret visual observations and reason about complex environments using natural-language instructions. However, their practical deployment remains challenging as onboard inference is constrained by limited computational, memory, and energy resources, whereas cloud-based inference introduces communication latency, bandwidth overhead, and dependence on network connectivity. To address these limitations, split computing offers a promising alternative by partitioning VLM inference between the resource-constrained UAVs and more capable remote servers. However, the performance trade-offs among fully onboard, cloud-based, and split-computing architectures for lightweight VLMs have not yet been systematically profiled. This paper benchmarks these three deployment paradigms using SmolVLM-256M as a representative lightweight VLM. We quantify their inference latency, computational resource utilization, communication overhead, and energy consumption across varying image resolutions and network conditions. Our results show that no deployment strategy is universally optimal; instead, the preferred strategy depends on the interaction between network conditions and input image resolution.
发表机构
- University of Klagenfurt（克拉根福大学）
- TU Wien（维也纳科技大学）
机构由 AI 辅助整理，请以论文原文为准。
