Welcome

I am co-founder and technical lead of AZON-AI, a technical initiative focused on testing and safety validation of AI-driven autonomous systems. My research centers around risk-aware control and safety validation of safety-critical systems, focusing on understanding and formalizing their safety and performance boundaries under uncertainty.

Starting from classical control theory on dynamical systems, my work gradually expanded to learning-based approaches for adaptive agents in complex environments and more recently to formal methods for reasoning about decision-making processes in autonomous systems. Throughout this progression, my research has been driven by a consistent and persistent thread: how to reason about safety in systems that operate beyond idealized assumptions, such as under disturbance, partial observability, imperfect policies, and complex interaction environments.

I am interested in making safety validation interpretable, structural, and transparent, thus enabling rigorous analysis of edge cases, long-tail risks and rare events in AI-driven decision systems.

Elsewhere: 

ResearchGate ·  Youtube ·  GitHub

Recent Writings:

• High Accuracy, Low Understanding: The Hidden Gap in Autonomous Driving Safety. Mar 20, 2026. [link]

• Beyond Scenarios: Why AI-Driven Scenario Testing Is Incomplete Without Formal Methods. Mar 9, 2026. [link]