This project leverages reservoir computing (RC) architecture to predict time-varying uncertainties in complex dynamical systems. By utilizing the computational efficiency of the RC architecture, we aim to efficiently predict unknown behaviors in dynamic environments.

This project utilizes VR technology to reimagine experiences for user-friendly urban mobility. By integrating autonomous devices into virtual environments, it aims to create immersive and personalized experiences, forecasting the next generation of urban transportation.

Inspired by the Miracle on the Hudson, we aim to design a decision-making architecture that can quickly make a sequence of decisions for autonomous systems. We will integrate neuroscience, control theory, and machine learning by adequately leveraging their advantages towards having a safety guarantee under large uncertainties.

This project aims to develop a multi-level adaptive control architecture, where the proactive level leverages data over a cloud network to cope with unforeseen environmental uncertainties and support high-level decision making, while the reactive level uses machine learning and robust adaptive control to compensate for uncertainties.

Recent developments of Cyber-Physical Systems (CPS) and their safety-critical applications, such as power systems, critical infrastructures, transportation networks, and industrial control systems, have led to a renewed interest in CPS security. In this project, we aim to study and develop attack-resilient estimation and detection algorithms for CPS.