LiDAR Perception for Autonomous Mobility
Team: Dr. Muhammad Shahbaz (Post-Doc, 3D Computer Vision & AI), Dr. Shakib Mustavee (Post-Doc, Mathematical Modeling)
Light Detection and Ranging (LiDAR) is a remote sensing method that uses LASER (Light Amplification by Stimulated Emission of Radiation) pulses to accurately measure range (variable distance) information by measuring the time for the reflected light beam to return. It finds its applications in many areas including land and structural surveying, powerline inspections, forestry, farming, mining, and quite intuitively in intelligent transportation systems such as intelligent driver aid systems all the way to fully autonomous driving. Recently, URBANITY Lab started research in the LiDAR perception domain with a goal to improve pedestrian and work-zone safety applications. The research focuses on developing real-time 3D object detection and identification algorithms for point-cloud data received from LiDAR devices to maximize real-world applicability. Please scroll down to our video section below to find more.
Physics-Informed Machine Learning for Transportation
Team: Jiheng Huang (alumni), Dr. Shakib Mustavee, Dr. Muhammad Shahbaz
A newer and rapidly growing research direction in the lab involves combining the power of machine learning with the rigor of physics-based models. Specifically, we are looking at physics-informed deep learning approaches for traffic state estimation — where the model is trained not just on data but also constrained to obey known traffic flow equations (like the LWR model and Cell Transmission Model). Recent publications have also explored the limitations of this approach, which is an important and honest scientific contribution.
Koopman Theory and Dynamical Systems for Traffic
Team: Dr. Shakib Mustavee (Post-Doc, Mathematical Modeling – primary research area), Md. Mahmudul Islam (Post-Doc, C-V2X & ITS – applied aspects)
This research area uses an advanced mathematical framework called Koopman operator theory to model complex, nonlinear dynamical systems relevant to transportation — particularly signalized intersections and traffic corridors. The Koopman approach allows us to treat nonlinear systems in a linear framework, which makes analysis and control much more tractable. This work has been applied to signal timing optimization and understanding quasi-periodic driving patterns in traffic.
Smart Urban Mobility and Connected Autonomous Vehicles (CAVs)
Team: Md. Mahmudul Islam (Post-Doc, C-V2X & ITS) is the most directly aligned with this area. Incoming PhD students Muhammad Luqman and Jehanzaib Hafeez (joining Spring 2026)
This is a broader area that encompasses much of the lab’s foundational work on intelligent transportation systems, connected and autonomous vehicle coordination, traffic state estimation, and traffic control. This includes work on macroscopic traffic flow modeling, ramp metering, V2X (vehicle-to-everything) communication, observability of traffic networks, and optimization-based control strategies. Much of this work has been published in top IEEE and transportation journals.
Cyber-Physical Systems and Smart Cities
Team: Teresa Lewis (M.S., Smart City) is working directly in this area. Undergraduate researchers Gabrielle Gilles and Gaurav Kanoujia may also be contributing to projects here
This area ties together the lab’s broader interest in how digital technologies, data, and physical infrastructure interact in urban environments. Smart city applications, sensor placement, infrastructure monitoring, and the integration of transportation with city-scale systems fall under this umbrella. Dr. Agarwal is also the director of UCF’s Future City Initiative, and this broader smart city vision is reflected in this area of the lab’s work.
Socio-Technical Systems and Information Diffusion
Team: Dr. Shaurya Agarwal
A somewhat distinct but important part of the lab’s portfolio involves modeling how information spreads through social networks and the interaction between human behavior and technological systems. This includes work on event-triggered social media chatter, modeling social contagion, and automated audit inquiry using Hidden Markov Models. A book titled Information Spread in a Social Media Age: Modeling and Control (co-authored by Michael Muhlmeyer and Dr. Agarwal) comes directly from this body of work.
Research Posters
