Nuclear power faces a practical challenge as much as a technical one: for it to be treated as a viable clean energy source, it must be competitively priced and economical to produce. That question becomes sharper as future plants may be smaller, more distributed, and located in rural areas.
Lauren Fortier, a second-year doctoral student in the Department of Nuclear Science and Engineering (NSE), is working on one part of that challenge. Her research is focused on remote operation protocols for autonomous control of nuclear plants, with an emphasis on systems that can be supervised, vetted, and trusted by human operators.
From naval operations to nuclear automation
Fortier came to this research through direct operating experience. After earning an undergraduate degree in materials science and engineering from Northwestern University, where she attended on an ROTC scholarship, she supervised nuclear plant operations on a U.S. aircraft carrier deep in the South China Sea.
That environment gave her a clear view of what it means to depend on nuclear power in practice. As she put it, “It was a unique experience that you don’t easily see anywhere else, especially the complete reliance on nuclear power. The only way you’re moving through the ocean is if you have that nuclear reactor working.”
As a naval nuclear operator, Fortier became drawn to the operational side of nuclear energy. She learned the science behind plant operations while also seeing how much of the work depended on manual processes. That led to a central question in her thinking: whether plant operations could be made less manually intensive without losing the oversight and discipline that nuclear systems require.
Why small reactors change the staffing equation
Fortier later moved from operations into academia after the Navy offered her the opportunity to pursue a master’s degree from a list of approved disciplines. She chose nuclear engineering at MIT as a continuation of the work she already knew. “My experiences in nuclear up until then had been overwhelmingly positive, so I thought I would build on them and move from the operations realm to the academic realm,” Fortier says.
For her master’s degree, she developed a supervisory control system for nuclear plant operation. She worked with a simulator that had a strong thermal hydraulic response, using the assumption that lessons from simulation could translate to real-world equivalents.
The broader reason for this work is economic as well as operational. Existing legacy plants can support intensive manual operations because they operate at 100 percent capacity and generate enough power to justify a large staff. Microreactors distributed at scale and placed in remote areas face a different reality: they cannot afford a large bench of human talent.
That is where supervised autonomous operations could matter. The goal is not to remove humans from responsibility, but to design nuclear plant automation that lets people and machines share work more effectively. For remote operation, small nuclear plants need systems that can carry out procedures, adjust to plant conditions, and still keep human intervention available when it is needed.
A human-machine system, not automation for its own sake
Fortier’s core question became: “How do we transition to autonomous operations in nuclear power plants?” Her answer is an integrated approach centered on a supervisory control system, rather than a set of many interlinked parts.
The difficult part is that nuclear procedures have historically been designed around humans. Fortier saw that a rigid framework would not be enough if it could not accommodate both human operators and machines. “Because everything is human-centric, it doesn’t allow you to choose the best way to do a procedure,” Fortier observes.
Her research therefore points toward a more flexible division of labor. Computers could handle work they are well suited to perform, while humans could step in strategically when judgment, intervention, or takeover is needed. That shift depends not only on control logic, but also on the design of the human-machine interface.
MIT and Idaho National Laboratory (INL) collaborations have shaped that part of the work. Fortier’s research advisor, Sacit Cetiner, has a joint appointment with MIT NSE and INL. Fortier also worked with Katya Le Blanc, a senior human factors scientist at INL, to address the design of an autonomous supervisory control system that people can understand and adopt.
A collaboration with the Human System Simulation Laboratory at INL helped Fortier better understand cyber-physical systems. She described the value of that work directly: “I’m very much an engineer and don’t have a lot of experience in human behavior, so the collaboration with INL was a huge benefit for me. I got better insights into many aspects, including what you want to see when a human has to take over for a machine when it’s no longer working.”
Building trust through step-by-step autonomy
Fortier completed her master’s in 2025 and continued the research toward a PhD because the scope extended beyond a master’s thesis. Her doctoral work focuses on objective-oriented operations, where a control system can create the sequence of events needed to reach an objective rather than simply follow a predetermined operating procedure.
That move toward autonomy is designed to be gradual and systematic. Fortier emphasizes that users need to build trust in automated procedures. “When we introduce an automated procedure that walks you step by step through what you would be doing anyway, it is reassuring and builds trust,” she points out.
Her approach also avoids framing the work as AI-driven automation. Fortier is developing automation based on finite state automata, a process she studied extensively during an internship at INL in summer 2024. Unlike AI, this method is transparent in its execution.
Finite state automata operates as a discrete event system. In plain terms, every move in the automation framework is tied to events: if a condition occurs, the system takes the corresponding action. That structure lets the framework adjust to current plant conditions while moving clearly between different states or events.
This transparency is central to the work. Fortier says, “We’re not using a data-driven statistical approach like machine learning because we do not yet have the tools to validate the operation of such systems.” For nuclear plant operations, the ability to understand and validate system behavior is not a secondary feature. It is part of the foundation.
The research network behind the work
Fortier’s project sits at the intersection of nuclear engineering, control theory, and human factors. At MIT, she learned control theory from one of her co-advisors, Anuradha Annaswamy, a founder and director of the Active-Adaptive Control Laboratory in the Department of Mechanical Engineering. Annaswamy advises Fortier on the supervisory control system framework and execution.
Curtis Smith, the former director for INL’s Nuclear Safety and Regulatory Research Division and now KEPCO Professor of the Practice of Nuclear Science and Engineering at MIT NSE, is Fortier’s other co-advisor. Fortier has also worked with Westinghouse, described as a leading design organization and vendor for current- and next-generation nuclear power plants, and completed a summer internship there in 2025 to test ideas about autonomous operations solutions.
The work has already drawn recognition. Fortier was one of the winners of the 2025 edition of the Innovations in Nuclear Energy Research and Development Student Competition from the Department of Energy’s Nuclear Energy University Program.
The larger implication is straightforward: if nuclear power is to expand through small plants and microreactors in remote areas, operations will need to evolve. Fortier’s research is aimed at making that evolution careful, transparent, and compatible with human oversight.