The National Science Foundation Division of Information and Intelligent Systems awarded the University of Florida $399,756 on October 1, 2025, to develop qualitative and quantitative safety assessment methodologies for learning-enabled autonomous systems operating in unfamiliar or unprecedented environments.
The research targets foundational challenges in system-level safety verification for learning systems that interact with the physical world—such as autonomous vehicles, robotics, and industrial automation—particularly as these systems encounter uncertainties and hazards including collisions with other vehicles, bicycles, and pedestrians. The project will produce both binary safety decisions and numerical safety measures to enable comprehensive verification in uncertain environments, with outcomes intended to boost trustworthiness and support safe integration of learning-enabled systems across multiple domains.
The award funds research performance at Gainesville, Florida, with a period of performance running through July 31, 2027. Educational and outreach activities integrated into the research include curriculum development, K-12 STEM outreach, and industrial engagement, with priority consideration and mentoring directed toward students in underrepresented minority groups.
The funding is provided under the Computer and Information Science and Engineering program (CFDA 47.070).