The goal of my research program is to develop AI-based decision-making methods for cyber-physical systems to achieve unprecedented robustness and agility. Such systems include multiple, heterogeneous entities (humans, robots, digital models, physical assets, etc.), operate in dynamic and uncertain environments, and span multiple spatial and temporal scales in terms of action feasibility and execution. The methods, therefore, should be novel to address unsolved challenges, theoretically sound to provide performance guarantees, and both computationally efficient and easily realizable to be practically useful. These requirements lead to a tight coupling of mathematical and physical modeling of system behaviors or responses, model-based and data-driven entity-level perception and reasoning, and inter-entity coordination. Please visit the Projects and Publications pages for details on the specific methods and application domains.