Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies

TL;DR

This survey examines the challenges and strategies for deploying foundation models on embodied edge systems, emphasizing system-level co-design to meet strict real-time constraints.

Contribution

It introduces the Deployment Gauntlet framework, categorizing eight key barriers and analyzing how different models are constrained by system resources in edge environments.

Findings

Vision-Language-Action policies are limited by memory bandwidth.

Diffusion-based controllers are constrained by compute latency.

Reliable deployment requires integrated system-level co-design.

Abstract

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.