One of the main tasks of any city government is to keep infrastructure such as roads, signs, accessibility ramps, and sewers in perpetual working order. The first step of maintenance is timely identification of the need for it. However, many infrastructure defects are undetected and unattended for long periods of time. This issue could be addressed by building AI technologies into existing city resources. The City of Austin has several vehicle fleets that conduct maintenance work around the city. This project will leverage the fleets by using state-of-the-art computer vision, robotics, and data science techniques, to automate infrastructure inspection in such a way that is publicly acceptable, reduces costs, and increases the effectiveness of city maintenance efforts.

 

Project team: Peter Stone (Department of Computer Science), Miriam Solis (School of Architecture), Bryan Thompson (City of Austin Public Works, Department Systems and Information Management), Marc Coudert (City of Austin Office of Sustainability), Harel Yedidsion (Department of Computer Science) and Xuesu Xiao (Department of Computer Science)