Indoor Air Quality Detection Robot Model Based on the Internet of Things (IoT)
Anggiat Mora Simamora, Asep Denih, Mohamad Iqbal Suriansyah
TL;DR
This work tackles the need for spatially contextual indoor air quality data by introducing an IoT-based mobile robot that autonomously maps enclosed spaces while monitoring IAQ indicators. The platform integrates an ESP32 with sensors for VOCs, CO$_2$, smoke, temperature, and humidity, and employs a Mamdani fuzzy logic classifier for IAQ categorization, complemented by a simple linear regression-based mapping of room geometry from the collected data ($Y = a + bX$). Contributions include a low-cost, integrated IoT robotic system, a web-based visualization/control interface, and laboratory validation of both mapping/navigation and sensing accuracy. Results show localization errors below $5\%$, motion errors below $2\%$, sensor errors up to around $12\%$, and a significant reduction in IAQ classification error from $9.47\%$ to $1.92\%$ via fuzzy logic, along with wall-dimension mapping errors around $5.39\%$ and a homing error of $9.09$ cm, indicating practical viability for real-time indoor IAQ mapping. The approach enables real-time, location-aware IAQ monitoring in indoor environments with an open-source codebase for further development.
Abstract
This paper presents the design, implementation, and evaluation of an IoT-based robotic system for mapping and monitoring indoor air quality. The primary objective was to develop a mobile robot capable of autonomously mapping a closed environment, detecting concentrations of CO$_2$, volatile organic compounds (VOCs), smoke, temperature, and humidity, and transmitting real-time data to a web interface. The system integrates a set of sensors (SGP30, MQ-2, DHT11, VL53L0X, MPU6050) with an ESP32 microcontroller. It employs a mapping algorithm for spatial data acquisition and utilizes a Mamdani fuzzy logic system for air quality classification. Empirical tests in a model room demonstrated average localization errors below $5\%$, actuator motion errors under $2\%$, and sensor measurement errors within $12\%$ across all modalities. The contributions of this work include: (1) a low-cost, integrated IoT robotic platform for simultaneous mapping and air quality detection; (2) a web-based user interface for real-time visualization and control; and (3) validation of system accuracy under laboratory conditions.