In pursuit of the operation of an independent nuclear power plant
It turns out that master’s research is just the tip of the iceberg. It still had to be done.
For future nuclear power, small plants, located in rural areas, are a different possibility. Until now, the work carried out in legacy factories has involved intensive manual labor, working because these facilities operate at 100 percent capacity and the energy delivered can justify the cost of maintaining many workers. But microreactors distributed at scale and in remote locations cannot afford a large bench of human talent. This is where supervised and well-tested freelance jobs will help.
The main question was: “How do we transition to independent operation of nuclear power plants?” Fortier wanted a single, integrated approach, a centralized control system instead of multiple interconnected components. Although it was a legal requirement, the challenge here was to adapt the tasks that were now intended for humans to involve machines.
Fortier realized that no matter how comprehensive the framework of a surveillance control system, its scope would be severely limited if its robustness could not accommodate both people and equipment. “Because everything is person-centered, it doesn’t allow you to choose the best way to do the process,” Fortier notes. What if, instead, humans and computers could tag along and do what each other does best, with strategic human intervention delivered only as needed?
A collaboration made by MIT
The goal was good, but its scope went beyond a master’s thesis. A doctorate seemed like a natural progression, so Fortier continued his PhD research after completing his master’s in 2025.
It was in the pursuit of independent works that Fortier found the power to collaborate at MIT. His research advisor, Sacit Cetiner, has a joint appointment with MIT NSE and Idaho National Laboratory (INL). To tackle the challenge of designing an autonomous control system with an efficient and easily adopted human machine, Fortier worked with Katya Le Blanc, a senior human factors scientist at INL. Working with the Human System Simulation Laboratory at INL helped Fortier develop a better understanding of designing cyber-physical systems.
“I’m very much an engineer and I don’t have a lot of experience in human behavior, so working with INL has been very beneficial for me. I’ve gained a better understanding of many aspects, including what you want to see when a person should replace a machine when you no longer work,” said Fortier.
He also used the collaboration with Westinghouse, a leading design organization and supplier of current and next-generation nuclear power plants – Fortier completed a summer internship there in 2025 – to test the ideas he had about autonomous operating solutions.
At MIT, Fortier studied control theory from one of his collaborators, Anuradha Annaswamy, founder and director of the Active-Adaptive Control Laboratory in the Department of Mechanical Engineering. “He’s a control systems expert, which is very beneficial to me because even though I can explain what to do with a nuclear power plant, he can help me better understand how to operate from a control systems perspective,” said Fortier.
Annaswamy advised Fortier on the framework of the control system and implementation. Fortier also took related classes and systems related classes to build a learning foundation. Curtis Smith, former director of INL’s Nuclear Safety and Regulatory Research Division, and now KEPCO Professor of the Practice of Nuclear Science and Engineering at MIT NSE, is another mentor to Fortier.
A step-by-step progression to self-regulation
Forter clarifies that the operating systems he designs will include a slow and systematic move toward autonomy to build trust among users. “When we introduce an automated process that walks you step-by-step through what you would do anyway, it reassures us and builds trust,” notes Fortier. His doctoral work focuses on goal-directed operations in which the control system can create the sequence of events necessary to achieve a goal, rather than following a predetermined operating procedure.
Another point to confirm is that Fortier is developing automation based on a process called finite state automata, which, unlike AI, is very transparent in its operation. The advantages of finite state automata, which he also learned a lot during his training at INL in the summer of 2024, is that it is a discrete event system. This means that every movement in the automatic framework is event-driven – if this happens, do that – so it adapts to the current conditions in the plant and the transition between different states or events very clearly. It tackles a complex problem by using traditional automation, not AI-driven automation. “We don’t use a data-driven statistical approach like machine learning because we don’t yet have the tools to validate the performance of such systems,” said Fortier.
Future impact
So promising is Fortier’s work in developing automation in nuclear plants that he was one of the winners of the 2025 Innovations in Nuclear Energy Research and Development Student Competition from the Department of Energy Program of the University of Nuclear Energy.
Applying nuclear plant automation to next-generation reactors will provide the impetus needed to develop and deploy commercial microreactors.
But first will come the work of measuring the steering control system, borrowing from the information gained in the work on the small part of the control. Fortier is excited about the road and the opportunities that lie ahead. “Collaboration with other people, and the relationships we have established with stakeholders, have greatly helped to make an impact and support the value of the work,” he said. “Sometimes when you’re stuck in your own bubble, that outside perspective is really helpful.”
