针对视觉语言动作模型的边缘云协同部署，提升实时性与稳定性。
RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
- 根据模型结构与硬件特性动态划分边缘云任务
- 在不同网络条件下实现3.28倍加速，开销仅2.55%~2.62%
- 适合需要低延迟部署的机器人智能系统
视觉语言动作（VLA）模型是具身智能主流，但推理成本高。边缘-云协同（ECC）部署通过分担边缘设备计算压力，满足实时需求。然而，现有框架对VLA模型不理想，主要受两大挑战制约：(1) 模型结构多样，难以确定最优分割点；(2) 即使找到最优分割点，网络带宽变化仍会导致性能下降。为此，我们提出面向多种VLA模型的新型ECC部署框架RoboECC。具体而言，提出模型-硬件协同感知的分割策略，以适配不同VLA模型的最优分割点；同时提出网络感知的部署自适应方法，应对网络波动，维持最佳性能。实验表明，RoboECC在保持2.55%~2.62%开销的前提下，实现最高达3.28倍的加速。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) deployment offers an effective fix by easing edge-device computing pressure to meet real-time needs. However, existing ECC frameworks are suboptimal for VLA models due to two challenges: (1) Diverse model structures hinder optimal ECC segmentation point identification; (2) Even if the optimal split point is determined, changes in network bandwidth can cause performance drift. To address these issues, we propose a novel ECC deployment framework for various VLA models, termed RoboECC. Specifically, we propose a model-hardware co-aware segmentation strategy to help find the optimal segmentation point for various VLA models. Moreover, we propose a network-aware deployment adjustment approach to adapt to the network fluctuations for maintaining optimal performance. Experiments demonstrate that RoboECC achieves a speedup of up to 3.28x with only 2.55%~2.62% overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。