Project Grant 2401391

This Project Grant award from the National Science Foundation's (NSF) Engineering program (CFDA 47.041) provides $250,000 in funding to Georgia TECH Research Corp, an academic research organization, to conduct collaborative research on stochastic nonlinear control and learning via spectral dynamics embedding. The key innovation of this 3-year research effort is a unified approach to reformulate stochastic nonlinear control systems into a linear spectral feature space, enabling tractable optimization and rigorous analysis. The team will develop computationally efficient methods for stochastic nonlinear control with known or unknown models, ensuring system robustness and safety. This interdisciplinary research combining expertise in control theory, reinforcement learning, and statistical learning aims to have transformative impacts on both control systems and machine learning, with potential applications in robotics, aerospace, manufacturing, and beyond.