UT Dallas AI Team Builds Road Repair Priority System for Japanese Highway Company
Researchers at the University of Texas at Dallas have developed an automated system that helps city governments decide which roads to fix first when budgets are tight. The Center for Applied AI and Machine Learning partnered with NEXCO-Central, a Japan-based expressway operator, to build the tool.
NEXCO-Central already used AI and mobile camera footage to assess pavement conditions across road networks. The new system adds a scoring mechanism that ranks repair priorities based on road condition, cost, and budget constraints.
"The new system emulates the mind of a city manager who has to decide the priority for fixing various road segments," said Dr. Gopal Gupta, director of the center and a computer science professor at UT Dallas.
How the System Works
The tool processes video data from mobile cameras to evaluate road conditions, then applies machine learning algorithms to recommend which segments need repair and how much to spend on each. The system also explains the reasoning behind each recommendation - a feature that helps city officials understand why certain roads were prioritized.
Koshiro Mori, a developer at NEXCO-Central, said the company serves clients mainly in North Texas through its subsidiary NEXCO Highway Solutions of America. "Our technology aims to optimize the complex decision-making to determine which roads are most in need of repairs, the predicted financial investment and prioritizing who gets the money and when," Mori said.
From University to Market
The collaboration was structured so NEXCO-Central retains ownership of the intellectual property. Computer science doctoral students Abhiramon Rajasekharan and Keegan Kimbrell contributed to the project alongside Gupta.
Atsushi Onishi, vice president of NEXCO Highway Solutions of America, said the ability to allocate budgets efficiently across different road types was critical. "It is important to have the technologies to determine which segment has to be done within the budget and how much should be spent on specific road types," Onishi said.
Mori noted that NEXCO-Central found the center through online research. "NEXCO-Central researched academic institutions online, and the name CAIML came up and caught our eye because AI and machine learning are the core technologies that we use in our business," he said.
Gupta described the center's role as serving companies without their own research divisions. "We think of ourselves as the research and development center for companies that do not have an R & D arm," he said.
For IT and development professionals building similar decision-support systems, understanding how to apply AI for IT & Development can help structure projects that deliver business value. The technical approaches used here - combining computer vision with machine learning for decision-making - are applicable across infrastructure and operations domains.
Your membership also unlocks:
