Researchers from the United States and Japan are developing autonomous robots and Artificial Intelligence (AI) models to help shipyard workers identify instances where the physical structure of a vessel deviates from its original design, allowing them to adapt or fix issues earlier in the process.
The initiative is supported by a US$6.2 million grant from the Japanese Ministry of Land, Infrastructure, Transport and Tourism. The American research team is led by University of Michigan Engineering and includes researchers from the Massachusetts Institute of Technology (MIT).
The project is being overseen by the Monohakobi Technology Institute (MTI), a research and development centre within the Japanese shipping company NYK Line.
“It’s very complementary to our other research projects led by Japanese universities, in which the main focus is robots for automation of hull construction and steel welding,” said Hideyuki Ando, managing director of the Monohakobi Technology Institute.
“We wanted to partner with the University of Michigan because of their unique status as a high-output research university with a dedicated department for naval architecture and marine engineering.”
The technology focuses on the outfitting stage of construction, which involves the installation of thousands of internal components such as pipes, cables, and electrical systems. Because scheduling pressures can lead to parts being installed out of order, the original drawings can become impractical. If these discrepancies are not identified early, they can lead to costly rework and delivery delays.
To address this, robots equipped with LiDAR and cameras will navigate the vessel to collect data. This information is processed by an AI model to create a digital twin of the built structure, which is then compared against the intended design.
When a problem is detected, the system generates a list of potential remedies and the trade-offs associated with each. This allows workers to verify the issue and decide on the best course of action. The researchers will also interview tradespeople in both the United States and Japan to ensure the AI logic aligns with the reasoning of skilled workers on the job.
“We want to build a co-pilot system that uses AI and robotics to take some of the detective work off workers’ shoulders,” said Alan Papalia, Assistant Professor of Naval Architecture and Marine Engineering at U-M and the Principal Investigator of the American research team.
“The system should automatically map what’s installed, identify where reality is drifting from the design, and suggest workable alternatives when something needs to change.”
The researchers plan to test the AI models and robots using a reconfigurable Shipbuilding Test Block, which can represent various stages of outfitting and common shipbuilding challenges. The project is funded through the first quarter of 2027.
