update

Zettelkasten/Fleeting Notes/Editing/thesis_ideas_notes.md

@@ -0,0 +1,3 @@
+# Notes on [[thesis-ideas-2025-07-30]]
+
+

Zettelkasten/Fleeting Notes/Journal/2025_08_07.md

@@ -0,0 +1,11 @@
+---
+---
+
+# 2025-08-06
+Today I have not gotten too much done, but I did get here
+early today. Today, I'll sell the truck and work on Sam's
+car. I saw Patrick today too, which was nice. Robert's stuff
+is all gone.
+
+My main focus for today is to finish the thesis ideas and
+tune up the writing. That'll be enough.

Zettelkasten/Permanent Notes/thesis-ideas.md

@@ -15,32 +15,45 @@ ___________________________________________________________
 ## **Integrating Shielding into Nuclear Power Control** 
 
 ### Goal:
-The goal of this research is to develop machine learning
+The goal of this research is develop machine learning
-control algorithms for nuclear power applications with
+enabled control algorithims for nuclear power applications
-strict safety guarantees.
+that incoporate shielding: a formal guarantee of adherence
+to system specifications without augmenting the machine
+learning process.
 
 ### Outcomes:
-If this research is successful, I will have accomplished the
+For this research to be successful, I will accomplish the
 following: 
 
-1. Develop controller shielding methods for nuclear power
+1. Identify key controllers in a nuclear power context with
-   contexts
+   the most benefit from using an ML-based controller
 
-2. Provide concrete safety guarantees for autonomous control
+2. Translate regulatory and system level requirements into a
-   of a nuclear asset.
+   formal specification to synthesize a controller 'shield'.
+   This shield monitors the ML controller and intervenes 
+   whenever a requirement is predicted to be violated.
 
-3. ??? <!TODO!>
+3. Evaluate performance of the ML controller with attached
+   shield, while assessing the amount of shield useage for
+   different operating scenarios (power up, shut down, regular
+   load following)
 
 ### Impact: 
-Machine learning based systems have been shown to be more
+
-efficient than typical PID based controllers, and are able to
+Machine learning controllers can outperform PID and
-learn more complex objective functions than a typical controller
+rule-based controllers by adapting to nonlinear dynamics,
-can. The problem with these controllers though is that they are
+optimizing over multi-objective cost functions, and changing
-often unexplainable. This is not acceptable for high assurance
+plant conditions. But, these ML controllers are often
-applications, where slight perturbations on inputs can yield
+*unexplainable*, meaning that their global behavior is not
-wildly different outputs. Shielding can solve this problem,
+easily understood.This unexplainability prevents ML based
-helping ensure safety of ML based controllers while not limiting
+controllers from being used in high-assurance usecases such
-their development or construction. 
+as nuclear power. Shielding can address this issue, by
+providing a formal runtime assurance, allieviating the
+burden of explainability away from the machine learning
+algorithm. This work would further bring regulatory
+requiremnts into the formal design of control systems and
+help bridge the gap between high assurance systems and the
+start of the art in control.
 
 ### Relevant Papers
 [[safe-reinforcement-learning-via-shielding]]
@@ -118,7 +131,7 @@ ___________________________________________________________
 ### Goals:
 If this research is successful, we will be able to generate
 autonomous controller shields that provably adhere to specifications
-written with temporal logic automatically.
+written with temporal logic.
 
 ### Outcomes:
 - Create an intermediary shield that mediates signals between an