边缘端具身基础模型：部署约束及缓解策略综述
Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
AI总结：
本文综述了在边缘端部署具身基础模型时面临的系统性约束及缓解策略，重点探讨了内存带宽、计算延迟和执行成本等关键因素对自动回归视觉-语言-动作策略和扩散控制器的影响，强调了内存、调度、通信和模型架构的协同设计的重要性。
摘要：
在具身边缘系统中部署基础模型本质上是一个系统问题，而不仅仅是模型压缩的问题。实时控制必须在严格的尺寸、重量和功率约束下运行，其中内存交通、计算延迟、定时变化性和安全余量直接相互作用。部署地狱将这些约束组织成八个相互关联的障碍，决定了具身基础模型能否实际可靠运行。在代表性边缘工作负载中，自回归视觉-语言-动作策略主要受内存带宽限制，而基于扩散的控制器则更多受计算延迟和持续执行成本限制。可靠的部署因此依赖于内存、调度、通信和模型架构的系统级协同设计，包括将快速控制与较慢的语义推理分离的分解方法。
英文摘要：
Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
