Work

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

Year: 2026

Type: preprint

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.

Source: arXiv (Cornell University)

Authors: Grover, Utkarsh, Ranjan, Ravi, Mao, Mingyang, Dong, Trung Tien, Praveen, Satvik, Wu, Zhenqi, Chang, J. Morris, Mohsenin, Tinoosh, Sheng, Yi, Polyzou, Agoritsa, Kanjo, Eiman, Lin, Xiaomin

Institutions: University of South Florida, Nottingham Trent University, Florida International University

Topic: IoT and Edge/Fog Computing

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7140001054

Cites:

Cited by:

Related to: