Download

Download Full Text (991 KB)

Description

With the rise of artificial intelligence and machine learning algorithms, self-driving cars are becoming increasingly prevalent on our roads. By utilizing these technologies, we can reduce the number of accidents caused by distracted driving. Before implementing these systems in vehicles, however, it is essential to conduct numerous tests. Traditional evaluation of driverless cars on real-world roads can be both expensive and hazardous. To address this, creating a digital twin of an actual road minimizes unexpected hazards, allowing researchers to safely and efficiently test self-driving car programs in high-risk scenarios using computer simulations. This research outlines the process of generating a digital map of the UNLV campus by gathering LiDAR elevation measurements and 3D models of buildings taken from Google Earth for the open-source CARLA car simulator, a platform used to train algorithms in autonomous vehicles. Employing this strategy enables faster and more efficient calibration of driverless cars.

Publisher Location

Las Vegas (Nev.)

Publication Date

Fall 11-21-2025

Publisher

University of Nevada, Las Vegas

Language

English

Keywords

Computer Simulation; Artificial Intelligence; Software Programming; Data Scientist; Machine Learning

Disciplines

Electrical and Computer Engineering | Engineering

File Format

PDF

File Size

931 KB

Permissions

Google Drive\Institutional Repository\OUR_OfficeOfUGResearch\Symposia\2025 Fall Symposium

Comments

Mentor: Brendan Morris

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Digital Twin of the UNLV Campus for Safe Autonomous Vehicle Simulation


Share

COinS