As AI (artificial intelligence) continues to transform how communities manage critical infrastructure, universities are investing in research and innovation that can help public agencies make smarter, faster, and more cost-effective decisions about road maintenance. As one example, PaveX, a Purdue University-related startup founded by Purdue civil engineering researcher Mohammad Jahanshahi, recently received a $305,000 Phase I Small Business Innovation Research grant from the National Science Foundation to advance its AI-powered technology for automating road condition assessments. The technology is designed to help public works departments evaluate road conditions and plan repairs sooner and more efficiently. What makes this technology innovative is its use of advanced AI to streamline a traditionally time-consuming process. Instead of relying primarily on manual road inspections, PaveX’s technology can help agencies collect and analyze road condition data more efficiently, giving decision-makers better information about where repairs are needed and when they should be prioritized. Here is how this can help: Looking to the future, AI-driven infrastructure management has the potential to play an increasingly important role in maintaining the nation’s roads and other critical public assets. As communities face aging infrastructure and limited resources, technologies that provide faster, more accurate, and data-driven insights can help public agencies plan repairs strategically. PaveX’s NSF-supported work demonstrates how university research and entrepreneurship can translate emerging AI technologies into practical solutions for…

Technology is transforming transportation by helping researchers better understand why crashes happen and where safety improvements can have the greatest impact. A new research approach uses AI (artificial intelligence) to connect roadway condition data with crash reports, giving transportation agencies clearer insights into road safety risks. Researchers at the University of Houston have developed an AI-powered method that uses large language models to analyze thousands of police crash narratives alongside roadway data, including pavement conditions, road geometry, and surface characteristics. By combining information that has traditionally been evaluated separately, the approach helps identify roadway segments where pavement conditions may contribute to higher crash risk. Here is how this can help: Looking ahead, AI-driven analysis could become an increasingly valuable tool for transportation agencies, helping them make data-informed decisions that improve roadway maintenance, reduce crash risks, and enhance safety for drivers. As AI capabilities continue to advance, similar approaches may play a growing role in building smarter, safer transportation…