Skip to main content
Guest homeNews home
Story
22 of 50

LSU Electrical, Computer Engineering Professor Designs Intelligent Drone for Rescue Operations

September 18, 2024BATON ROUGE, LA - The National Fire Protection Association estimates that one home fire-related death occurs in the U.S. every three hours and 14 minutes, and one home fire-related injury occurs every 53 minutes. These are numbers LSU Electrical and Computer Engineering Assistant Professor Xiangyu Meng hopes to change for the better through his design of an intelligent drone that will use thermal technology during rescue operations, particularly for firefighters.

Xiangyu MengSeptember 18, 2024

BATON ROUGE, LA – The National Fire Protection Association estimates that one home fire-related death occurs in the U.S. every three hours and 14 minutes, and one home fire-related injury occurs every 53 minutes. These are numbers LSU Electrical and Computer Engineering Assistant Professor Xiangyu Meng hopes to change for the better through his design of an intelligent drone that will use thermal technology during rescue operations, particularly for firefighters.

“The emergence of drones has found various significant applications in industries, including aiding emergency responders to locate victims in rescue operations,” Meng said. “However, these responders face challenges when it comes to detecting victims in obscured areas due to smoke or dust. Victims may be unable to provide visual cues but can only shout for help.”

Recent advancements in deep learning—a subset of machine learning that involves training artificial neural networks to learn and make intelligent decisions from data—have shown significant ability in predicting and decision making in various domains, such as disaster management. Meng also integrates online gas sensing for hydrogen fluoride and carbon monoxide that can leak from lithium-powered vehicles and create unseen danger.

Meng’s project, sponsored by NASA, began with data collection—thermal images of humans, animals, audio data, and more. His team then trained a deep-learning model using state-of-the-art algorithms. Next came drone development and system integration. Lastly, testing and evaluation were done in which Meng conducted experiments using simulated emergency response scenarios before collaborating with the Baton Rouge Fire Department for actual testing. After this was done, the research team fine-tuned the design based on the results and performance metrics.

“The project has the potential for success because it addresses a specific challenge in emergency response by employing advanced machine learning that has proven to be efficient,” Meng said. “The impact of this project is mainly in saving lives and expanding the knowledge of machine-learning applications in the aviation industry.”

Like us on Facebook (@lsuengineering) or follow us on X (formerly Twitter) and Instagram (@lsuengineering).​

###

Contact: Libby Haydel
Communications Manager
225-578-4840
ehaydel1@lsu.edu

Latest College of Engineering News