Layered Architecture for Mobile Intelligence

2026-07-30

AI Summary

This work addresses the limitations of prevailing AI architectures, which are predominantly rooted in static cloud-centric paradigms and thus ill-suited for mobile intelligent systems—such as autonomous vehicles and drones—that operate in dynamic environments and require tight co-deployment of energy, computation, and intelligence. To bridge this gap, the paper proposes the “Mobile AI Stack,” a novel five-layer cooperative framework that, for the first time, explicitly incorporates mobility as a core design constraint across the entire AI stack. The architecture integrates mobile energy networks, energy-efficient AI chips, cloud-edge-device infrastructure, distributed AI models, and embodied intelligent applications. Through cross-layer co-evolution mechanisms spanning energy, computation, communication, and algorithms, the framework establishes a theoretically grounded and technically viable blueprint for scalable, energy-efficient, and reliable large-scale mobile intelligent systems, while also outlining key directions for future research.

Abstract

Artificial intelligence (AI) is rapidly evolving from a centralized computing capability into a pervasive infrastructure that interacts directly with the physical world. While recent perspectives highlight the roles of energy, chips, infrastructure, models, and applications in enabling large-scale AI systems, these frameworks primarily assume a static, cloud-centric computing paradigm. However, emerging intelligent applications, including autonomous vehicles, drones, robots, and wearable systems, require AI to operate in highly dynamic and mobile environments. This shift introduces mobility as a fundamental constraint across the entire AI ecosystem, affecting energy supply, computation, and intelligence deployment. In this article, we introduce the concept of the Mobile AI Stack, a mobility-aware architectural framework that integrates five tightly coupled layers: mobile energy networks, energy-efficient AI chips, cloud-edge-mobile infrastructure, distributed AI models, and embodied AI applications. The proposed framework provides a systematic perspective for understanding how energy delivery, computing architectures, communication networks, and AI algorithms must co-evolve to support large-scale mobile intelligence. We further discuss key research challenges and future directions toward building scalable, reliable, and energy-efficient mobile AI systems. Mobile AI Stack offers a conceptual blueprint of the next-generation infrastructure which deeply integrates the networks of computation, energy, and communications for mobile intelligence.

Problem

• mobile intelligence
• mobility constraint
• dynamic environments
• AI ecosystem
• energy-aware computing

Innovation

• Mobile AI Stack
• mobility-aware architecture
• energy-efficient AI chips
• distributed AI models
• embodied AI applications