Education
Experiences
Research
My research focuses on making robots and cyberphysical systems safer. Soecifically, I am interested in Machine Learning (ML) components and how they impact the safety of the system. To that end, I have developed an effective and efficient tool to identify the hazard boundary of ML components via scalable parallel simulations. Furthermore, I am developing methods and tools to monitor the ML component during its operation at runtime. My research is supported by Auxon Corporation, Mitacs and Ontario Graduate Scholarship.
Runtime Safety Monitoring of Learned Components
- This ongoing research focuses on developing safety monitors for learned components.
Hazard Boundary Identification of ML-enabled Autonomous Systems
- In this project we proposed MLCSHE, a cooperative coevolution algorithm with a probabilistic fitness function to identify the hazard boundary of a machine learning component which is embedded in an atuonomous system. MLCSHE uses the actual system and scalable parallel simulations to identify the hazard boundary.
Publications
ArXiv Preprints
Journal of Software and System Modeling, 21, 2395–2427, 2022
28th IEEE International Requirements Engineering Conference, 2020
39th International Conference on Conceptual Modeling, 2020
13th International i* Workshop, 2020
13th International i* Workshop, 2020