Applied Scientist II

The petitioner proposes to employ machine learning and advanced data-driven models to enhance the safety, decision-making, and reliability of autonomous systems. Her work focuses on addressing challenges in autonomous navigation and trajectory prediction for self-driving cars, autonomous surface vessels, and intelligent water treatment systems.

The petitioner proposes to design machine learning models that detect rare and unexpected signals in autonomous driving, smart manufacturing, and critical infrastructure. This work focuses on rare-event modeling to simulate processes with minimal data, aiming to prevent system failures and enhance the reliability of AI-powered technologies. The intended impact includes improving autonomous vehicle navigation safety and ensuring consistency in manufacturing production lines.

The petitioner proposes to advance research at the intersection of artificial intelligence, machine learning, and advanced statistical methods for industrial data analysis. His work focuses on developing mathematical and probabilistic models and simulation tools to enhance the reliability, availability, and safety of sustainable and autonomous transportation systems.

The petitioner proposes to advance the robustness, safety, and data efficiency of machine learning models when used outside their training conditions. This work focuses on enabling the reliable deployment of AI systems in real-world applications across critical domains such as healthcare, transportation, finance, and national security.