In pursuit of autonomous nuclear plant operations
It seems the research for the master’s was just the tip of the iceberg. There was still work left to be done.
For the longer term viability of nuclear power, small plants, positioned in rural areas, are a definite possibility. Up to now, operations conducted in legacy plants have involved intensive manual operations, that are viable because these facilities operate at 100% capability and the ability delivered can justify the prices of maintaining a big staff. But microreactors distributed at scale and in distant areas can’t afford a big bench of human talent. It’s where supervised and thoroughly vetted autonomous operations will help.
A primary query was: “How will we transition to autonomous operations in nuclear power plants?” Fortier wanted one integrated approach, a central supervisory control system as an alternative of many interlinked parts. While a legitimate requirement, the challenge here was in modifying operations that were primarily meant for humans to now also include machines.
Fortier realized that irrespective of how thorough the framework for a supervisory control system, its scope can be severely limited if its rigidity couldn’t accommodate each humans and machines. “Because all the pieces is human-centric, it doesn’t will let you select one of the best technique to do a procedure,” Fortier observes. What if, as an alternative, humans and computers could tag-team and do what each does best, with strategic human intervention only delivered as obligatory?
MIT-facilitated collaborations
The goal was elegant, but its scope prolonged far beyond a master’s thesis. A doctorate gave the impression of a natural progression, so Fortier has continued her research toward a PhD after completing her master’s in 2025.
It was in pursuit of autonomous operations that Fortier discovered the ability of collaborations at MIT. Her research advisor, Sacit Cetiner, has a joint appointment with MIT NSE and the Idaho National Laboratory (INL). To deal with the challenge of devising an autonomous supervisory control system with an efficient and simply adopted human-machine interface, Fortier worked with Katya Le Blanc, a senior human aspects scientist at INL. A collaboration with the Human System Simulation Laboratory at INL helped Fortier develop a greater understanding of designing cyber-physical systems.
“I’m very much an engineer and don’t have loads of experience in human behavior, so the collaboration with INL was an enormous profit for me. I got higher insights into many facets, including what you wish to see when a human has to take over for a machine when it’s not working,” Fortier says.
She also availed of collaborations with Westinghouse, a number one design organization and vendor for current- and next-generation nuclear power plants — Fortier accomplished a summer internship there in 2025 — to check drive ideas she had about autonomous operations solutions.
At MIT, Fortier learned control theory from one in every of her co-advisors, Anuradha Annaswamy, a founder and director of the Energetic-Adaptive Control Laboratory within the Department of Mechanical Engineering. “She’s a control systems expert, which really advantages me because while I can explain what to do with a nuclear power plant, she may also help me understand higher go about operations from a control systems perspective,” Fortier says.
Annaswamy advises Fortier on supervisory control system framework and execution. Fortier has also been taking classes related to regulate systems related classes to construct a foundation within the discipline. Curtis Smith, the previous 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.
A step-by-step progression toward autonomy
Fortier clarifies that the operations systems she’s designing will incorporate a gradual and systematic move toward autonomy in order to construct trust with users. “After we introduce an automatic procedure that walks you step-by-step through what you can be doing anyway, it’s reassuring and builds trust,” Fortier points out. Her doctoral work focuses on incorporating objective-oriented operations where a control system can create the sequence of events needed to achieve the target, reasonably than follow a predetermined operating procedure.
One other point of reassurance is that Fortier is developing automation based on a process called finite state automata, which, unlike AI, could be very transparent in its execution. The benefits of finite state automata, which she also studied extensively during an internship at INL in summer 2024, is that it’s a discrete event system. Because of this every move within the automation framework is event-driven — if this happens, do this — so it adjusts for current conditions within the plant and transitions between various states or events very clearly. It’s addressing a posh problem through conventional automation, not AI-driven automation. “We’re not using a data-driven statistical approach like machine learning because we don’t yet have the tools to validate the operation of such systems,” Fortier says.
Future impact
So promising is Fortier’s work on developing automation for nuclear plants that she was one in every 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.
Using the nuclear plant automation program on next-generation equipment will deliver obligatory traction in developing and deploying business microreactors.
But first will come the work of scaling the supervisory control system, borrowing from insights gained from work on a small aspect of control. Fortier is worked up concerning the road and the chances that await. “The collaborations with other people, and the relationships now we have established with stakeholders, have really helped make an impact and supported the relevancy of the work,” she says. “Sometimes while you’re stuck in your individual bubble, that outside perspective is admittedly useful.”