danesabo/Obsidian
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

vault backup: 2025-07-07 14:36:54

Browse Source
This commit is contained in:
Dane Sabo 2025-07-07 14:36:54 -04:00
parent d90fed72fa
commit 6b8e312ce1
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Notes on Papers/On Using Real-Time Reachability for the Safety Assurance of Machine Learning Controllers.md
View File

@ -13,16 +13,20 @@ to talking about the formal verification of the switching mechanism, but they
do make note that's future work. do make note that's future work.
**Contributions:** **Contributions:**
They show how a simplex system can work and the difficulties They show how a simplex system can work and the difficulties of the *sim2real* transition for machine learning controllers.
**Clarity:** **Clarity:**
Really nicely written.
# Second Pass # Second Pass
**What is the main thrust?** **What is the main thrust?**
They use a simplex style controller setup with real time reachability to know when to use a optimal ML based controller vs. a safety oriented controller. They use the reachability to do this in real time, and demonstrate how different ML models line up against one another.
**What is the supporting evidence?** **What is the supporting evidence?**
They ran a whole bunch of experiments. They published all of the results, with their main metrics being Mean ML usage.
**What are the key findings?** **What are the key findings?**
The biggest findings are that when obstacles are introduced (or other general advesary behavior),
# Third Pass # Third Pass
**Recreation Notes:** **Recreation Notes:**