AutoIoT: Automated IoT Platform Using Large Language Models

TL;DR

AutoIoT leverages large language models and formal verification to automate the creation of conflict-free IoT automation rules, simplifying user interaction and aiding developers in conflict detection.

Contribution

The paper introduces AutoIoT, a novel platform combining LLMs and formal verification for end-to-end automation in IoT systems, including conflict detection and code generation.

Findings

AutoIoT effectively generates conflict-free automation rules.

The platform assists developers in conflict detection code creation.

AutoIoT demonstrates successful integration with existing IoT platforms.

Abstract

IoT platforms, particularly smart home platforms providing significant convenience to people's lives such as Apple HomeKit and Samsung SmartThings, allow users to create automation rules through trigger-action programming. However, some users may lack the necessary knowledge to formulate automation rules, thus preventing them from fully benefiting from the conveniences offered by smart home technology. To address this, smart home platforms provide pre-defined automation policies based on the smart home devices registered by the user. Nevertheless, these policies, being pre-generated and relatively simple, fail to adequately cover the diverse needs of users. Furthermore, conflicts may arise between automation rules, and integrating conflict detection into the IoT platform increases the burden on developers. In this paper, we propose AutoIoT, an automated IoT platform based on Large Language Models (LLMs) and formal verification techniques, designed to achieve end-to-end automation through device information extraction, LLM-based rule generation, conflict detection, and avoidance. AutoIoT can help users generate conflict-free automation rules and assist developers in generating codes for conflict detection, thereby enhancing their experience. A code adapter has been designed to separate logical reasoning from the syntactic details of code generation, enabling LLMs to generate code for programming languages beyond their training data. Finally, we evaluated the performance of AutoIoT and presented a case study demonstrating how AutoIoT can integrate with existing IoT platforms.