C2SMART researchers shine at the recent ITS-NY annual meeting & technology exhibition

The Intelligent Transportation Society of New York (ITS-NY) provides a forum for anyone interested in technology aimed at making transportation systems smarter, more robust, and more efficient — goals mirroring those of NYU Tandon’s C2SMART, a research center devoted to studying challenging transportation problems and drawing solutions from the unprecedented recent advances in technology.

This year, the organization held its 32nd Annual Meeting & Technology Exhibition in Saratoga Springs, New York, and C2SMART Assistant Director of Research Jingqin Gao was there to present “AI in Motion: Video Analytics for Automating Pavement Inspection and Work Zone Detection” during a panel on safety and AI analytics.

While Gao — who earned her doctoral degree in transportation planning and engineering from NYU Tandon — is a veteran of many ITS-NY events, Zerun Liu was attending for the very first time, and Shuo Zhang had been only once before. Despite being relative neophytes, the two, both current Ph.D. candidates, acquitted themselves admirably, with each earning top honors at the poster session.

Liu’s first-place poster was titled “The Effects of Increased Electric Truck Weights on Road Infrastructure.” She explains that although the damaging effects of diesel trucks on pavement and bridge infrastructure are well-documented, the impact of e-trucks remains underexplored — a significant problem since e-trucks can weigh up to 9,000 pounds more than their diesel counterparts because of their heavier battery packs, potentially accelerating infrastructure wear if not properly accounted for.

One obstacle to studying the problem is that there is not yet significant data on e-trucks, since they still have not been widely adopted. Liu’s solution involves a novel methodological framework that follows four key phases: defining future e-truck adoption scenarios, generating applicable data by integrating historical truck travel patterns with literature-based assumptions, evaluating infrastructure impacts using the Pavement Damage Assessment Cost (PDAC) estimation method, and, finally, identifying policy-relevant infrastructure indicators to guide decision-making.

Liu and her collaborators, led by C2SMART Director and NYU Tandon Professor Kaan Ozbay, applied their framework to a case study of New York City, modeling e-truck adoption for 2030 and 2050 under various weight and penetration rate scenarios. Their analysis shows that the current average annual total damage cost from conventional oversized trucks in the city is approximately $4 million. With the projected adoption of electric trucks, damage costs can be expected to increase by up to 12%, posing a significant added burden on pavement and bridge infrastructure. Their recommendations for policymakers include developing a more flexible permit fee strategy and updating road and bridge design requirements to accommodate e-trucks' weight and dimensions.

Zhang’s poster, “Integrating VR-CARLA Co-Simulation and Eye Tracking for Behavior Analysis of Drivers Around Work Zones,” which came in at second place, also had practical implications, especially given how difficult it currently is to ensure safety around roadway work zones.

Some of the problem stems from our incomplete understanding of driver behavior and how it contributes to accidents. Zhang explains that advances in digital technologies, combined with major developments in traffic simulation tools such as eye-tracking and the Car Learning to Act (CARLA) simulation platform, allow for safe and realistic environments that virtually simulate diverse hazardous work zone scenarios. This enables researchers to capture driver behaviors without actually exposing them to real-world risks.

His study presents a multi-module immersive car simulation and interactive driving platform to capture authentic driver reactions and behaviors around unstructured work zones, with a focus on measuring awareness via gaze duration and fixation ratios (the proportion of time the eyes spend fixated on a specific area of interest relative to the total viewing time). He and his collaborators found that drivers focus their attention on workers exhibiting risky behaviors over warning signs, with increased emphasis on those individuals despite the existence of signage. Warning signs enhanced the awareness of normal workers, but in hazardous conditions, drivers’ attention was disproportionately diverted to risky workers, diminishing their focus on normal workers.

These differing awareness patterns suggest that multi-type notification systems, such as dynamic digital displays, wearable devices for workers, and auditory alerts, with human notifiers at the center, could be effective in preventing accidents. Drivers, he stresses, are paying attention, and it’s up to policymakers to do what they can to help them.

"It’s incredibly rewarding to see our researchers being recognized for their innovative and timely contributions to the rapidly evolving challenges in transportation,” Gao concludes. “Events like ITS-NY remind us why we do this work: to connect cutting-edge research with real-world solutions, while staying mindful of the new challenges that innovation can bring. I’m proud of our team’s dedication and excited for what’s ahead."