Fangyu Wu
Papers
1
Total Citations
15
H-Index
1
About
Fangyu Wu is a researcher at the forefront of control theory and robotics, specializing in the intersection of model predictive control (MPC), optimization, and learning-based methods. Their work addresses a critical bottleneck in real-time control: the computational burden of solving MPC online. In their highly cited 2023 paper, "Composing MPC With LQR and Neural Network for Amortized Efficiency and Stable Control," Wu introduces a novel framework that combines implicit MPC with linear-quadratic regulators (LQR) and neural networks. This approach achieves amortized computational efficiency while preserving closed-loop stability, a significant advance over traditional explicit MPC or naive function approximation. By leveraging the strengths of both classical control and modern deep learning, Wu’s contributions offer a practical pathway for deploying advanced control in resource-constrained systems, from autonomous vehicles to industrial robotics. With 15 citations in just a short time, this work has already sparked interest in the control community for its elegant balance of theory and application. Wu’s research continues to push the boundaries of efficient, stable, and intelligent control systems.
Research Focus
Key Achievements
Top Papers
- 1