HIGHLIGHTS
SUMMARY
This study is not aimed towards demonstrating a performance disparity between Fuzzy logicbased AI approaches and any other methodology, but rather to demonstrate how these systems can be created in a way that maintains explainability and formal verifiability. The corrected systems are then verified to not violate specifications showing definitive correctness with respect to the developed behavioral specifications. The aim for this study is to showcase an example of a fuzzy logic based AI system which can be formally verified to adhere to safety specifications within a mission/safety-critical scenario. Instead, at least . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.