AutoBridge: Automating Smart Device Integration with Centralized Platform

TL;DR

AutoBridge automates the generation of IoT device integration code for centralized platforms, significantly reducing human effort and outperforming expert programmers in accuracy.

Contribution

It introduces an automated approach for IoT integration code synthesis with a multi-stage debugging pipeline and minimal user feedback, enhancing efficiency and accuracy.

Findings

Achieves 93.87% success rate across 34 devices

Reaches 94.87% function coverage without human involvement

Outperforms expert programmers by 50-80% in code accuracy

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.