Ph.D. student in Computer Science and Engineering at University of California, San Diego (UCSD)
Research focus: Developing safe and resilient learning-based control strategies for robotic systems
Integrates data-driven function approximators (e.g., deep neural networks) with formal control-theoretic tools to provide provable stability and safety guarantees
Investigates versatile robotic controllers based on diffusion models, flow-matching paradigms, and large-scale foundation models for broad task generalization and rapid adaptation
Long-term goal: Engineering autonomous systems that combine strong theoretical reliability with aggressive performance optimization for trustworthy, high-efficiency real-world automation