Kong Yao Chee
Papers
4
Total Citations
100
H-Index
3
About
Kong Yao Chee is a robotics and control systems researcher whose work sits at the intersection of machine learning and model predictive control (MPC), with a particular focus on aerial robots and quadrotor systems. His research addresses one of the central challenges in autonomous robotics: bridging the gap between idealized dynamic models and the messy uncertainties of real-world operation. Chee's most influential contribution, "KNODE-MPC" (2022, 81 citations), introduced a pioneering framework that fuses physics-based knowledge with data-driven learning — specifically Neural Ordinary Differential Equations — to derive highly accurate dynamic models for MPC. This work has garnered significant attention for its elegant combination of interpretability and performance. Building on this foundation, he has explored online dynamics learning, allowing robots to adapt their models in real time rather than relying solely on static offline training, as well as methods for enhancing sample efficiency and uncertainty compensation in learning-based control frameworks. More recently, Chee extended these ideas into state estimation through the LEARNEST framework, applying knowledge-based neural ODEs to improve how robots perceive their own state. Collectively, his contributions represent a cohesive and growing research program advancing reliable, intelligent autonomy for robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4