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

TL;DR

RoboECC is a novel deployment framework for VLA models that optimizes edge-cloud collaboration by considering model structures and network fluctuations, significantly improving inference speed.

Contribution

It introduces a co-aware segmentation strategy and a network-aware adjustment method to enhance VLA model deployment across edge and cloud environments.

Findings

Achieves up to 3.28x speedup in inference.

Maintains performance with only 2.55%~2.62% overhead.

Effectively handles network fluctuations for VLA models.

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 2.55%~2.62% overhead.