125 lines
2.8 KiB
Markdown
125 lines
2.8 KiB
Markdown
# Thesis Ideas 2025-07-30
|
|
|
|
Following our group meeting from Monday, July 28th, Dan
|
|
suggested I write down 6 ideas, and from them we shall
|
|
figure out a possible topic idea that I can really start
|
|
working on.
|
|
|
|
I used ChatGPT to do some of the heavy lifting based on the
|
|
papers I've been reading, and leveraged the 'deep research'
|
|
feature. Here are some of my favorite ideas, broken down
|
|
into goals, outcomes, impact, and related papers.
|
|
|
|
___________________________________________________________
|
|
|
|
## **Integrating Shielding into Nuclear Power Control**
|
|
|
|
### Goal:
|
|
|
|
The goal of this research is to develop machine learning
|
|
control algorithms for nuclear power applications with
|
|
strict safety guarantees.
|
|
|
|
### Outcomes:
|
|
|
|
If this research is successful, I will have accomplished the
|
|
following:
|
|
|
|
1. Develop controller shielding methods for nuclear power
|
|
contexts
|
|
|
|
2. Provide concrete safety guarantees for autonomous control
|
|
of a nuclear asset.
|
|
|
|
3. ??? <!TODO!>
|
|
|
|
### Impact:
|
|
|
|
Machine learning based systems have been shown to be more
|
|
efficient than typical PID based controllers, and are able
|
|
to learn more complex objective functions than a typical
|
|
controller can. The problem with these controllers though is
|
|
that they are often unexplainable. This is not acceptable
|
|
for high assurance applications, where slight perturbations
|
|
on inputs can yield wildly different outputs. Shielding can
|
|
solve this problem, helping ensure safety of ML based
|
|
controllers while not limiting their development or
|
|
construction.
|
|
|
|
### Relevant Papers
|
|
|
|
[[safe-reinforcement-learning-via-shielding]]
|
|
[[evaluating-robustness-of-neural-networks-with-mixed-integer-programming]]
|
|
|
|
___________________________________________________________
|
|
|
|
## **Formally Verified Control of Reactor Systems**
|
|
|
|
### Goals:
|
|
The goal of this research is to use formal methods to ensure
|
|
that a neural network based control rod controller will never violate
|
|
safety guarantees of a reactor trip system.
|
|
|
|
### Outcomes:
|
|
If this research is successful, I will accomplish the
|
|
following.
|
|
|
|
### Impact:
|
|
|
|
### Related Papers:
|
|
|
|
|
|
___________________________________________________________
|
|
|
|
## **Temporal Logic Specifications for Autonomous Controller Synthesis**
|
|
(3)
|
|
|
|
### Goals:
|
|
|
|
### Outcomes:
|
|
|
|
### Impact:
|
|
|
|
### Related Papers:
|
|
___________________________________________________________
|
|
|
|
## **Formally Verified Runtime Monitoring and Fallback**
|
|
(4)
|
|
|
|
### Goals:
|
|
|
|
### Outcomes:
|
|
|
|
### Impact:
|
|
|
|
### Related Papers:
|
|
|
|
___________________________________________________________
|
|
|
|
## **Data-Driven Model Verification for High-Assurance Digital Twins**
|
|
(8)
|
|
|
|
### Goals:
|
|
|
|
### Outcomes:
|
|
|
|
### Impact:
|
|
|
|
### Related Papers:
|
|
|
|
___________________________________________________________
|
|
|
|
## **Verified Adaptive Control**
|
|
(10)
|
|
|
|
### Goals:
|
|
|
|
### Outcomes:
|
|
|
|
### Impact:
|
|
|
|
### Related Papers:
|
|
|
|
|
|
|