Research
Research Vision
My research is positioned at the intersection of modern control theory, dynamic optimization, and robotics. My work spans two complementary directions: optimal control, including Model Predictive Control (MPC), reinforcement learning (RL), and deep reinforcement learning (DRL), and intelligent control, including direct adaptive fuzzy control (DAFC) and deep neural-network-based control — applied to control algorithms for robotic systems, including UAVs and other robot platforms, under nonlinear dynamics and disturbance.
A central objective of my work is to bridge control theory and practical implementation: deriving nonlinear plant models, designing controllers around them, and rigorously validating performance through MATLAB/Simulink simulation before any hardware deployment. Going forward, I’m looking to extend my optimal control work further into RL and DRL, and deepen my intelligent control work with deep neural network approaches, building controllers that can handle model uncertainty and generalize across robotic platforms and operating conditions, while keeping an eye on real-time computational feasibility.
My research activities are organized around the following themes in Projects.