HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Wed, 28 May 2025 16:55:14 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"68373ff2-69ac" expires: Tue, 30 Dec 2025 08:39:32 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: D020:444BC:9E21DA:B17FF3:69538D6C accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 08:29:32 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210087-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767083373.571947,VS0,VE224 vary: Accept-Encoding x-fastly-request-id: 58b200c1ecf20c22ba74d1662c00459390f4a1a7 content-length: 6227

Hello. I am Ruya.

I am a fifth-year PhD student in the Electrical and Computer Engineering Department at the University of Michigan - Ann Arbor, where I am advised by Professor Necmiye Ozay. My research is mainly focused on combination of formal methods and machine learning, where I am trying to combine the advantages of machine learning with formal methods to infer better specifications for systems. I am also interested in personalization, safety guarantees, and control synthesis of cyber-physical systems, especially in the context of autonomous vehicles.

Feel free to reach out to me using any of these channels:

Latest News

March 11, 2025

Recieved Rackham Predoctoral Fellowship

I received Rackham Predoctoral Fellowship! I am grateful for this opportunity and support!

February 4, 2025

Thesis Proposal Exam Passed

I successfully passed my thesis proposal exam! This marks approximately one year until my Ph.D. defense.

December 13, 2024

Talk at CPHS 2024

I presented our work on 4C: Custom-and-correct-by-construction controller synthesis using multi-modal human feedback at CPHS 2024 in Antalya, Turkey. It was a blast to get connected with researchers in my home country!

See more news ->

Last Projects

COMPLETED

Classification using Temporal Logic

In this project, we utilize temporal logic formalism to classify driving behaviors. The goal is to infer an STL formula that can distinguish two classes of behaviors. By using this formula, we can synthesize new behaviors that belong to the desired class.

#signal temporal logic #classification

ONGOING

Safe Preference Learning

In this project, we aim to capture user preferences for driving task to generate personalized and safe behaviors. We use temporal logic formalism to specify the safety. To capture the user preferences, we utilize preference learning methods. Specifically, we ask pairwise questions that compare two behaviors.

#preference learning #safety guarantees

See More Projects ->