Federal Project Grant Award Summary

The National Science Foundation's Division of Computer and Network Systems awarded the University of Florida a $659,317 CAREER grant effective June 1, 2026, through May 31, 2031, under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070). This project will develop comprehensive theory, algorithms, and open-source tools for assured reinforcement learning from human feedback (RLHF) applied to cyber-physical systems such as autonomous vehicles, service robots, and drones. The research deliverables include logic-aware methods for translating human feedback into reward models, deployment methodologies for human environments with temporal constraints, and validated implementations on real-world robotic platforms. The project will produce research publications, open-source software tools, and technical frameworks enabling cyber-physical systems to learn personalized control policies while maintaining safety, security, and privacy guarantees.

In addition to research outputs, the award supports significant workforce development and educational initiatives, including new course materials, immersive learning platforms, student mentoring programs, and K-12 outreach activities. The University of Florida will collaborate with the University of Florida Transportation Institute, the Florida Institute for National Security, and the Florida Institute for Cybersecurity Research to advance education across undergraduate and pre-collegiate levels. These integrated activities position the project to contribute both fundamental advances in assured machine learning for cyber-physical systems and human capital development in computing and autonomous systems domains.