Fusion-Based Sensor Data Processing and Visualization Framework for Autonomous Vehicle Testing in GCC Terrains

Ismail Hamieh
Department of Electrical and Computer Engineering,
The University of Western Ontario

1151 Richmond St, London, ON N6A 3K7 Canada
ihamieh@uwo.ca

Mazen Kiki

Department of Mechanical Engineering

The University of Akron,

244 Sumner Street, Akron, OH 44325, United States

mak259@uakron.edu

Abstract

Autonomous driving in the Gulf Cooperation Council (GCC) region presents unique environmental challenges including high temperatures, reflective surfaces, sand particles, and variable lighting conditions. These factors degrade the performance of single-sensor systems, making multi-sensor fusion a crucial approach for reliable perception and decision-making. This study develops a ROS2-based sensor fusion framework to process and visualize LiDAR and camera data specifically under GCC-like terrain conditions. The system integrates calibration parameters from the KITTI dataset and applies them within a containerized environment to synchronize 3D point clouds with 2D visual frames. By visualizing the fused data through Foxglove Studio, the framework demonstrates enhanced scene understanding, robust depth estimation, and improved object boundary recognition under environmental distortions typical of desert and coastal landscapes. The modular design allows adaptation for real-world GCC deployments, offering a foundational step toward perception algorithm validation, AI-driven sensor alignment, and autonomous vehicle testing in complex regional conditions.

Keywords

Autonomous Vehicles, GCC Terrain, Sensor Fusion, LiDAR, ROS2, AI and Machine Learning Based Perception

Biography

Ismail Hamieh holds a Ph.D. in Electrical and Computer Engineering from the University of Windsor, where his research focused on developing an AI-driven filtering algorithm for road surface detection using LiDAR point cloud data. He also holds a Bachelor and Master’s degree in Computer and Electrical Engineering from the University of Michigan, specializing in digital control systems. As an Adjunct Professor at the University of Western Ontario, he contributes to research and mentorship in artificial intelligence, robotics, and autonomous mobility. His expertise spans autonomous driving systems, robotics, AI/ML, and smart mobility planning, with strong foundations in system and software architecture. He is a certified Design for Six Sigma (DFSS) Master Black Belt and SAFe® 5 Agilist, applying structured engineering and agile practices to develop intelligent mobility and robotic perception systems. Previously, he held senior engineering positions at General Motors, where he contributed to the development of autonomous driving technologies, active safety systems, and AI-based sensor alignment frameworks. His current research interests focus on AI-based perception, multimodal sensor fusion, and autonomous mobility in complex terrains.

Mazen Kiki earned his Ph.D. in Mechanical Engineering from the University of Akron, specializing in additive manufacturing, smart materials, and sensor technologies. His research focused on developing 3D-printed conformal sensors for robotic applications and innovative sensing solutions for tire systems under the Center for Tire Research (CenTiRe). He has published work on the creation of a 3D-printed conformal sensor for robotic fingertips, highlighting his contribution to advancing tactile sensing and robotic perception. Mazen’s expertise extends to engineering simulation, predictive studies, and the application of Industry 4.0 principles to improve production efficiency. His academic and research background also includes teaching assistant roles and practical engineering experience in designing and fabricating components for a gyroplane motor project. His interests lie in advanced manufacturing, robotics integration, and the use of smart materials and data-driven methods to enhance mechanical system intelligence.