Xiaodi Yang

Papers

Total Citations

H-Index

About

Xiaodi Yang is a pioneering researcher in the intersection of control theory and robotics, with a primary focus on data-driven optimal control and Koopman operator theory. Their most notable contribution is the development of the Kalman-Koopman Linear Quadratic Regulator (KKLQR) control approach, a groundbreaking framework that integrates Kalman filtering with Koopman operator theory to enable optimal control of nonlinear robotic systems. This work, published in 2024 and already garnering 25 citations, introduces a neural-network-based method for constructing continuous Koopman eigenfunctions without relying on predefined dictionaries—a significant advancement that eliminates a major limitation of traditional Koopman approaches. By enabling linear control techniques to be applied to complex nonlinear dynamics, Yang's research bridges the gap between theoretical control methods and practical robotic applications. Their work has immediate implications for autonomous systems, robotic manipulation, and real-time control, offering a computationally efficient and theoretically sound alternative to existing nonlinear control strategies. Yang's innovative integration of machine learning with classical control theory positions them as a rising leader in the field of intelligent robotic systems.