Which pothole to fix? AI team helps company develop city system

Artificial intelligence (AI) experts from The University of Texas at Dallas have partnered with a Japanese company through its Irving, Texas-based subsidiary to help local governments prioritize road repairs. The system builds on NEXCO-Central's existing technology, which combines artificial intelligence and video footage gathered from mobile cameras to assess road conditions and provide a network-wide view of pavement conditions.

Researchers in the UT Dallas Center for Applied AI and Machine Learning (CAIML) collaborated with Japan-based Central Nippon Expressway Co. Ltd. (NEXCO-Central) to develop an automated software system to help cities prioritize which roads to repair when faced with limited resources and competing interests. The company serves clients mainly in the North Texas area through its subsidiary NEXCO Highway Solutions of America Inc.

"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, CAIML director and professor of computer science in the Erik Jonsson School of Engineering and Computer Science.

The resulting technology, which has been integrated into NEXCO-Central's software, includes a scoring system to make the process more efficient.

"Pavement assessment is crucial for cities," said Koshiro Mori, a developer at NEXCO-Central. "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."

In addition to Gupta, UT Dallas computer science doctoral students Abhiramon Rajasekharan and Keegan Kimbrell contributed to the project.

"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," said Atsushi Onishi, vice president of NEXCO Highway Solutions of America.

Mori said, "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. We saw a collaboration opportunity, and we're very happy with how the team has handled this project."

An added benefit is that the tool explains the factors behind each recommendation, Mori said.

Gupta said the project is an example of how UT Dallas can help industry.

"We think of ourselves as the research and development center for companies that do not have an R & D arm," Gupta said. "NEXCO collaborated with us in this way and created a phenomenal product."

Provided by University of Texas at Dallas