In the wake of catastrophic earthquakes, rescue operations encounter significant obstacles in locating and reaching individuals trapped under debris. This study introduces the Smart Earthquake Rescue Robot (SERR) prototype, a cutting-edge solution designed to enhance the efficiency and effectiveness of earthquake rescue missions. The SERR is a mobile robot with advanced features, including live video streaming through an integrated camera, Grid-Eye temperature detection, and provisions for communication via built-in speakers and microphones, although these audio communication capabilities are pending implementation in the current prototype. It can be remotely controlled using a smartphone application, offering a safer and more efficient method for conducting rescue operations. Unlike recent advances discussed in the literature, SERR uniquely combines visual, thermal, and audio data with a multi-modal Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM) model (RescueNet), achieving high accuracy (0.94), precision (0.90), recall (0.96), and F1-score (0.92) in detecting survivors, as validated by MATLAB simulations using USGS-PAGER data. The SERR’s rapid runtime (35 ms) highlights its promise as a tool to improve earthquake rescue outcomes.
In this paper, a prototype of the Smart Earthquake Rescue Robot (SERR) has been proposed to address the challenges faced by human rescuers in locating and communicating with survivors trapped under earthquake debris. The SERR has advanced features such as live video streaming, thermal detection capabilities, and wireless control via a smartphone application. The SERR model is enhanced using a novel machine-learning model for real-time data analysis. This model, named RescueNet, is a Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) layers tailored explicitly for analysing the data transmitted by the robot, including video feeds and thermal images. The performance tests were conducted using MATLAB simulations and real-world data from the USGS - PAGER system, which offers critical impact estimates for large earthquakes. By using PAGER system data, a more accurate evaluation of the SERR's effectiveness in detecting and locating individuals trapped under debris was achieved. The SERR demonstrated high accuracy, precision, recall, and F1-score in detecting trapped individuals and a fast runtime. These findings validate the SERR's potential to enhance the effectiveness and safety of earthquake rescue operations. The SERR's ability to wirelessly search for and detect survivors under debris while providing real-time information to rescue teams makes it a valuable tool for improving disaster response and saving lives in the aftermath of devastating earthquakes.
While the SERR demonstrates significant potential with high performance metrics (accuracy of 0.94, runtime of 35 ms) in simulations, it is acknowledged that there are key limitations that temper these findings. The reliance on synthetic data (USGS-PAGER with simulated audio) may not fully capture real world complexities like unpredictable noise or debris acoustics, and the lack of physical field testing limits validation of the prototype under actual disaster conditions. Additionally, the two-way audio communication feature remains unimplemented, restricting direct survivor interaction. These constraints highlight the need for real-world testing and data integration to ensure practical applicability in earthquake rescue missions. The SERR has the potential to integrate sophisticated communication capabilities to improve the real-time interaction between the robot and rescuers. These future improvements will encompass two way audio communication, enabling the robot to relay audio messages between trapped individuals and rescue teams through microphones and speakers. Additionally, remote monitoring will enable rescuers to access live audio and video feeds from the SERR through the control application, improving situational awareness and facilitating decision-making. Future work will prioritize real-world field testing to bridge the gap between simulation results and practical deployment. Planned tests in controlled disaster simulation environments will provide critical insights into the SERR’s operational challenges and performance under authentic conditions, ensuring its readiness for actual earthquake rescue missions.
Sources:
Scientific Reports
https://www.nature.com/articles/s41598-025-16003-7 .
Provided by the IKCEST Disaster Risk Reduction Knowledge Service System
Comment list ( 0 )
