Federal Project Grant Award Summary

The National Science Foundation (NSF), Division of Computing and Communication Foundations, awarded $341,006 to the University of Florida Division of Sponsored Research effective October 1, 2025, through January 31, 2030, under the Computer and Information Science and Engineering (CFDA 47.070) program. This CAREER award funds research to advance formal method foundations for verifying the safety, robustness, and reliability of machine learning (ML) components—particularly deep neural networks (DNNs)—integrated into complex autonomous systems. The project addresses critical gaps in system-level verification by developing new modeling, specification, verification, and toolchain technologies that extend beyond current state-of-the-art approaches focused solely on individual ML components. Deliverables include formal verification methodologies for learning-enabled unmanned systems and corresponding software tools to enhance the safety, explainability, and reliability of ML-powered autonomous vehicles and related applications.

In addition to research outputs, the award supports educational and workforce development initiatives centered in Gainesville, Florida. The project incorporates two foundational research thrusts in modeling/specification and quantitative verification, while simultaneously enhancing autonomy-focused research and education at the University of Nebraska-Lincoln through curriculum integration, undergraduate research assistant recruitment, and K-12 STEM outreach. The research team will also partner with the University of Nebraska-Lincoln Osher Lifelong Learning Institute to deliver public lectures and discussions on autonomy technologies for adult learners, thereby advancing both scientific literacy and professional development in the emerging field of trustworthy learning-enabled autonomous systems.