The Internet of Things in the Era of Generative AI: Vision and Challenges

TL;DR

This paper discusses how Generative AI, particularly large language and multimodal models, can transform the Internet of Things by enhancing data generation, processing, and device interfacing across domains such as mobile networks, autonomous vehicles, metaverse, robotics, healthcare, and cybersecurity. It outlines concrete applications, including simulation and codec design for networks, improved ADAS and testing data for autonomous systems, immersive Metaverse experiences, enhanced human-robot interaction, AI-assisted medical reporting and multimodal diagnostics, and proactive security analytics. The authors identify seven main challenges (e.g., IoT-data modality coverage, resource constraints, latency, personalization, IoT-native AI agents, privacy, and tooling) and eight opportunities (modeling IoT data, compression, edge-cloud collaboration, efficient fine-tuning, on-device agents, federated learning with TEEs, and IoT-focused development tools and benchmarks) to address them. The work aims to catalyze research and development by providing a structured view of where Generative AI can add value to IoT and what technical advances are needed to enable practical, private, and scalable AIoT systems with real-world impact.

Abstract

Advancements in Generative AI hold immense promise to push Internet of Things (IoT) to the next level. In this article, we share our vision on IoT in the era of Generative AI. We discuss some of the most important applications of Generative AI in IoT-related domains. We also identify some of the most critical challenges and discuss current gaps as well as promising opportunities on enabling Generative AI for IoT. We hope this article can inspire new research on IoT in the era of Generative AI.

Figures (3)

• Figure 1: IoT in the era of Generative AI.
• Figure 2: Representative application domains of Generative AI for IoT.
• Figure 3: Challenges and opportunities of enabling Generative AI for IoT.