University of Michigan Engineering and Massachusetts Institute of Technology researchers are working with Japanese partners on AI-enabled robots designed to identify shipbuilding errors before they lead to rework or schedule delays.

The program is supported by a $6.2 million grant from Japan’s Ministry of Land, Infrastructure, Transport and Tourism. It is being overseen by Nippon Yusen Kaisha’s Monohakobi Technology Institute and is scheduled to continue through early 2027.

The project addresses a common problem in ship construction. When pipes, cables or equipment are fitted in the wrong order, later installation work can be blocked. That can force redesign, extra labor, and delays.

Under the plan, autonomous robots fitted with LiDAR and cameras will inspect ships while they are being built. AI models will compare the actual condition of the vessel with a digital twin based on the original design. The system will then identify differences and warn of potential fit-up issues before they become larger problems.

The developers are positioning the system as support for yard teams, not a substitute for workers. If the AI detects a mismatch, it will suggest possible options and explain the trade-offs. It will also show where human inspection is still needed.

Alan Papalia, assistant professor of naval architecture and marine engineering at the University of Michigan, said the goal is to create a co-pilot that uses AI and robotics to reduce the investigative burden on shipyard workers.

The technology will be trialled on a reconfigurable shipbuilding test block that can reproduce different construction and outfitting conditions.