Generating HomeAssistant Automations Using an LLM-based Chatbot

TL;DR

This paper explores using Large Language Models to generate smart home automation routines within HomeAssistant, aiming to promote sustainable household practices and evaluating user engagement and system accuracy.

Contribution

It demonstrates the potential of GPT models to create valid home automation routines and assesses their effectiveness in encouraging sustainable habits.

Findings

LLMs can generate accurate automation routines with some syntax errors.

Participants preferred LLM-generated routines over rule-based systems.

Qualitative feedback indicates increased sustainability awareness.

Abstract

To combat climate change, individuals are encouraged to adopt sustainable habits, in particular, with their household, optimizing their electrical consumption. Conversational agents, such as Smart Home Assistants, hold promise as effective tools for promoting sustainable practices within households. Our research investigated the application of Large Language Models (LLM) in enhancing smart home automation and promoting sustainable household practices, specifically using the HomeAssistant framework. In particular, it highlights the potential of GPT models in generating accurate automation routines. While the LLMs showed proficiency in understanding complex commands and creating valid JSON outputs, challenges such as syntax errors and message malformations were noted, indicating areas for further improvement. Still, despite minimal quantitative differences between "green" and "no green" prompts, qualitative feedback highlighted a positive shift towards sustainability in the routines generated with environmentally focused prompts. Then, an empirical evaluation (N=56) demonstrated that the system was well-received and found engaging by users compared to its traditional rule-based counterpart. Our findings highlight the role of LLMs in advancing smart home technologies and suggest further research to refine these models for broader, real-world applications to support sustainable living.