Draguna Vrabie

Papers

Total Citations

H-Index

About

Draguna Vrabie is a leading figure in the intersection of machine learning, control theory, and safety-critical systems. Her research focuses on developing data-driven and physics-informed methods for the modeling, control, and optimization of complex dynamical systems, with a particular emphasis on ensuring safety and reliability. A major contribution is her pioneering work on safe physics-informed machine learning, as exemplified by her highly cited tutorial paper (2025, 7 citations), which provides a comprehensive framework for integrating physical models with safety guarantees in dynamics and control. This work addresses a critical challenge in deploying learning-based controllers in real-world applications, from robotics to energy systems. Beyond this, Vrabie has made foundational advances in reinforcement learning for control, approximate dynamic programming, and optimal control of large-scale systems. Her research has garnered widespread recognition, with her most cited papers accumulating thousands of citations, reflecting her profound impact on the field. As a Senior Research Scientist at Pacific Northwest National Laboratory, she continues to shape the future of autonomous and resilient control systems, making her work essential reading for students and researchers at the intersection of machine learning and control.