I develop and apply artificial intelligence, machine learning, statistical methods, and advanced data analytics to transportation problems involving large-scale and complex datasets.

Research topics include:

• Machine learning and deep learning for transportation

• Artificial intelligence applications in transportation

• Travel demand analysis and forecasting

• Transportation safety data analytics

• Explainable and interpretable machine learning

• Discrete choice and behavioral modeling

• Traffic and travel-time prediction

• Data-driven transportation system analysis

My research investigates how connected, autonomous, and electric vehicle technologies can transform transportation systems and how transportation infrastructure and operations can adapt to these emerging technologies.

Research topics include:

• Connected and automated vehicles (CAVs)

• Connected vehicle technologies and communications

• Autonomous vehicle operations and control

• Vehicle trajectory planning and optimization

• CAV impacts on traffic flow and capacity

• Mixed traffic environments

• Electric vehicle mobility and infrastructure

• Simulation and performance assessment of emerging vehicle technologies

My transportation safety research combines statistical modeling, machine learning, spatial analysis, and transportation engineering to better understand and predict transportation safety outcomes.

Research topics include:

• Crash frequency and severity analysis

• Pedestrian and bicyclist safety

• Vulnerable road user safety

• Large-truck and vehicle safety

• Injury-severity modeling

• Spatiotemporal safety analysis

• Explainable machine learning for safety

• Safety implications of emerging vehicle technologies

• Transportation system reliability and resilience

I study how different transportation modes and emerging mobility services can be integrated to provide more efficient, accessible, and sustainable mobility.

Research topics include:

• Public transportation

• Urban rail and bus systems

• Transit operations and optimization

• Transit signal priority

• Shared mobility

• Carsharing and bikesharing

• Active transportation

• Multimodal transportation systems

• Emerging mobility services

My research addresses the modeling, optimization, and control of transportation systems at the intersection, corridor, and network levels.

Research topics include:

• Traffic flow modeling and simulation

• Traffic signal control

• Intelligent traffic management

• Deep reinforcement learning for traffic control

• Variable speed limits and speed harmonization

• Managed lanes

• Freeway operations

• Traffic assignment

• Transportation network design

• Bottleneck mitigation

• Travel-time reliability

• Congestion pricing

• Transportation system optimization

The Center for Advanced Multimodal Mobility Solutions and Education (CAMMSE) was a U.S. Department of Transportation University Transportation Center led by UNC Charlotte under the FAST Act.

As Director, I led a multi-university research and education program focused on improving the mobility of people and goods through advanced transportation technologies, methods, and models.

CAMMSE brought together researchers from five universities, transportation agencies, industry partners, and students to conduct interdisciplinary research addressing emerging transportation challenges.

CAMMSE Research & Education

• 87 research projects

• 219 journal publications across the consortium

• More than 200 students engaged in research

• Undergraduate and graduate transportation education and workforce development

• Annual research symposium and seminar activities

• National dissemination through TRB and other transportation conferences

• Research partnerships with universities, government agencies, and industry

[Learn More About CAMMSE → ]

The NC Transportation Center of Excellence on Connected and Autonomous Vehicle Technology (NC-CAV) supports interdisciplinary research, education, and technology development related to connected and autonomous transportation systems.

My research leadership within NC-CAV focuses on the development, evaluation, and application of connected and autonomous vehicle technologies, including their impacts on transportation operations, mobility, safety, and infrastructure.

Research activities include:

• Connected and autonomous vehicle operations

• CAV traffic flow and capacity

• Vehicle trajectory planning

• Traffic control in connected environments

• CAV simulation and impact assessment

• Connected infrastructure and intelligent transportation systems

• Emerging transportation technologies

[Learn More About NC-CAV → ]

The Smart, Safe & Sustainable Transportation Lab (S³ Transportation Lab) is an interdisciplinary research group at UNC Charlotte focused on developing next-generation transportation systems through the integration of artificial intelligence, data analytics, transportation modeling, and emerging mobility technologies.

The lab brings together graduate and undergraduate students, faculty collaborators, transportation agencies, and industry partners to address real-world transportation challenges.

Major Research Themes

Smart Transportation
AI, machine learning, data analytics, intelligent transportation systems, and transportation modeling.

Safe Transportation
Transportation safety analytics, vulnerable road users, crash modeling, and safety applications of emerging technologies.

Sustainable Transportation
Public transportation, multimodal mobility, shared mobility, electric vehicles, and sustainable transportation systems.

Connected & Autonomous Mobility
Connected vehicles, autonomous vehicles, intelligent infrastructure, simulation, optimization, and control.

[Visit the S³ Transportation Lab → ]

AI and Machine Learning for Transportation Prediction and Decision-Making

Developing data-driven models for travel-time prediction, traffic forecasting, transportation safety analysis, and transportation system optimization using machine learning and explainable AI.

Connected and Autonomous Vehicle Operations and Impact Assessment

Investigating vehicle trajectory planning, CAV market penetration, intersection capacity, traffic operations, mixed traffic environments, and the mobility and environmental impacts of connected and autonomous vehicles.

Deep Reinforcement Learning for Traffic Operations and Control

Developing reinforcement-learning approaches for traffic signal control, variable speed limits, speed harmonization, transit signal priority, and coordinated traffic management.

Data-Driven Modeling of Transportation Safety and Injury Severity

Applying advanced statistical and machine-learning methods to investigate crash patterns and injury severity involving pedestrians, bicyclists, large trucks, and other road users.

Data-Driven Optimization of Transit and Rail Operations

Developing optimization and machine-learning approaches for bus operations, transit priority, rail scheduling, train composition, passenger-flow analysis, and transportation network reliability.

Emerging Mobility and Multimodal Transportation Systems

Investigating shared mobility, active transportation, public transit, electric mobility, and the integration of emerging transportation services into multimodal transportation networks.