RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models

2026-03-21

AI Summary

This work addresses the unstable inference performance of Vision-Language-Action (VLA) models when deployed at the edge, which stems from architectural heterogeneity and network fluctuations. To tackle this challenge, the authors propose RoboECC, a novel multi-factor-aware edge-cloud collaborative deployment framework tailored for VLA models. RoboECC determines the optimal model partitioning point through a model-hardware co-aware splitting strategy and dynamically adapts to bandwidth variations via a network-aware adjustment mechanism. Experimental results demonstrate that RoboECC achieves up to 3.28× acceleration across diverse VLA models, with only a modest 2.55–2.62× increase in communication overhead, effectively balancing real-time responsiveness and computational efficiency.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Language and Vision
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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 2.55x~2.62x overhead.

Problem

• Vision-Language-Action models
• Edge-Cloud Collaboration
• model segmentation
• network bandwidth fluctuation
• embodied intelligence

Innovation

• Edge-Cloud Collaboration
• Vision-Language-Action Models
• Model-Hardware Co-aware Segmentation
• Network-aware Adaptation
• Embodied Intelligence