Robotics researcher with nearly a decade of experience in robotics control systems
Expertise spans classical control methods (e.g., PID, model-based control) to advanced intelligent frameworks (e.g., reinforcement learning, MPC, vision-language-action models)
Work bridges theory and practice across diverse platforms: quadrupeds, wheeled-leg robots, mobile bases, robotic arms, dexterous hands, aerial robots, and soft robots
Ph.D. research focused on operator-based control, particularly Koopman Operator Theory, combining model-based and data-driven approaches
Current research centers on generalized Real-to-Sim-to-Real (RSR) pipelines, world models, and robust embodied AI systems adaptable across tasks and environments