<![CDATA[Disaster mitigation is a global challenge that requires innovation to enhance the effectiveness of emergency response, particularly in the rapid and safe detection of victims. Although much research focuses on optimizing individual components such as sensors or algorithms, a gap remains in the development of holistically integrated frameworks. This study develops and evaluates an integrated explorer robot system based on Message Queuing Telemetry Transport (MQTT) and artificial intelligence for real-time disaster victim detection. Using a Design Science Research approach, the system architecture integrates an explorer robot based on ESP32-CAM and GPS for data acquisition, a central server running the You Only Look Once (YOLO) algorithm for image analysis, and involves a human operator for critical decision validation. Experimental results show that the system can detect victims with an average accuracy of 87.3% across various simulated scenarios. Communication via the MQTT protocol proved to be highly reliable and efficient, with an average latency of 127 ms and a packet loss rate of only 2.3%, enabling swift coordination between components. This research successfully validates an effective and replicable end-to-end architectural model, thereby presenting a practical blueprint for the development of low-cost Search and Rescue (SAR) robotic systems]]>
Copyrights © 2025
