AutoBridge: Automating Smart Device Integration with Centralized Platform

2025-07-30

AI Summary

Manually coding for IoT device integration faces high expertise barriers and poor cross-platform compatibility. Method: This paper proposes an automated code generation framework for multimodal IoT systems, adopting a “divide-and-conquer” strategy that integrates device-specific knowledge via progressive retrieval, platform-compliance–constrained code synthesis, and LLM-driven iterative refinement. It introduces a novel multi-stage debugging pipeline combining virtual-device-based automated validation with hardware-in-the-loop interactive debugging requiring only binary user feedback—significantly reducing domain expertise requirements. Contribution/Results: Evaluated on 34 real-world IoT devices, the framework achieves a 93.87% average code generation success rate and 94.87% functional coverage, reaching 100% with minimal user feedback. A user study demonstrates that generated code accuracy surpasses that of expert programmers by 50–80%.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Multimodal IoT systems coordinate diverse IoT devices to deliver human-centered services. The ability to incorporate new IoT devices under the management of a centralized platform is an essential requirement. However, it requires significant human expertise and effort to program the complex IoT integration code that enables the platform to understand and control the device functions. Therefore, we propose AutoBridge to automate IoT integration code generation. Specifically, AutoBridge adopts a divide-and-conquer strategy: it first generates device control logic by progressively retrieving device-specific knowledge, then synthesizes platformcompliant integration code using platform-specific knowledge. To ensure correctness, AutoBridge features a multi-stage debugging pipeline, including an automated debugger for virtual IoT device testing and an interactive hardware-in-the-loop debugger that requires only binary user feedback (yes and no) for real-device verification. We evaluate AutoBridge on a benchmark of 34 IoT devices across two open-source IoT platforms. The results demonstrate that AutoBridge can achieves an average success rate of 93.87% and an average function coverage of 94.87%, without any human involvement. With minimal binary yes and no feedback from users, the code is then revised to reach 100% function coverage. A user study with 15 participants further shows that AutoBridge outperforms expert programmers by 50% to 80% in code accuracy, even when the programmers are allowed to use commercial code LLMs.

Problem

• Automating IoT device integration with centralized platforms
• Reducing human effort in programming complex IoT code
• Ensuring correctness through multi-stage debugging pipeline

Innovation

• Automates IoT integration code generation
• Uses divide-and-conquer strategy for control logic
• Features multi-stage debugging pipeline for correctness