AI for Smart Transportation

Michael Wilbur
,
Amutheezan Sivagnanam
Amutheezan Sivagnanam
,
Afiya Ayman
Afiya Ayman
,
Samitha Samaranayake
,
Abhishek Dubey
,
Aron Laszka
Aron Laszka
Abstract
Public transportation systems worldwide face persistent challenges of efficiency, reliability, and sustainability. In this chapter, we explore how AI-powered approaches can reimagine transportation planning and operations, with particular emphasis on optimization and learning-based methods. We discuss predictive demand modeling, vehicle routing, and multimodal integration, illustrated through case studies on on-demand paratransit services, energy-efficient vehicle assignment, and microtransit operations. These examples demonstrate how AI can lower operational costs, improve system performance, and reduce emissions while managing the trade-offs between efficiency and service coverage. By highlighting the role of AI in advancing both operational effectiveness and energy sustainability, the chapter positions transportation as a critical testbed for understanding how AI can deliver practical improvements in large, complex infrastructure systems.
Type
Venue
Artificial Intelligence and Society, 11–45. River Publishers, 2026
publications

Authors

Amutheezan Sivagnanam
Ph.D. 2025
Amutheezan joined the Applied Artificial Intelligence Lab as a Ph.D. student in fall 2019 and received his Ph.D. in 2025. His research interest is in Machine Learning and Data Science. Previously, he graduated with a Bachelor’s Degree in Computer Science and Engineering from the University of Moratuwa, Sri Lanka in 2017. He worked as an intern at WSO2 Lanka (PVT) Ltd., as part of the Data Analytics Team in 2016. He also worked as a software engineer in MillenniumIT Software PVT Ltd. from 2018 to 2019. He has previously worked on a machine learning project on semi-supervised based sentiment analysis of microblogging platforms and on a data analytics project on monitoring flows of HL7 messages. His Ph.D. research focused on optimizing bus-route scheduling and minimizing energy costs.
Afiya Ayman
Ph.D. 2025
Afiya Ayman joined the Applied Artificial Intelligence Lab as a Ph.D. student in January 2019 and received her Ph.D. in 2025. Her research interest is in contemporary computational sciences, including data science, machine learning, and cybersecurity. She earned her bachelor’s degree in Computer Science & Engineering from Chittagong University of Engineering & Technology, Bangladesh. Her Ph.D. research focused on the application of neural networks and machine learning to restructure the operational planning of a regional transportation authority to be more energy-efficient.
Aron Laszka
Associate Professor

Aron Laszka is an Associate Professor in the College of Information Sciences and Technology at the Pennsylvania State University, where he directs the Applied Artificial Intelligence Lab. Before joining Penn State in 2022, he was an Assistant Professor at the University of Houston (2017 – 2022), a Research Assistant Professor at Vanderbilt University (2016 – 2017), and a Postdoctoral Scholar at the University of California, Berkeley (2015 – 2016).

His research focuses on machine learning for decision making and optimization, in particular reinforcement learning and learning-augmented combinatorial optimization, with applications in cyber-physical systems, such as transportation and power systems, and in cybersecurity. He is a recipient of the NSF CAREER Award. His research is funded by the National Science Foundation, the Department of Energy, the Department of Transportation, and other agencies.