Federal Grant Award Summary

Louisiana State University received a $298,950 Project Grant from the National Science Foundation's Office of Integrative Activities under the Integrative Activities program (CFDA 47.083), awarded May 1, 2026, with completion targeted for April 30, 2028. This EPSCOR Research Fellows award supports the development of a multi-phase safety assurance framework for Advanced Driver Assistance Systems (ADAS) that integrates design-time validation with runtime monitoring. The research deliverables combine formal verification techniques with machine learning to improve transparency and verifiability of autonomous driving systems, utilizing program analysis, natural language processing, and reinforcement learning to identify critical fault-related variables and guide targeted fault injection testing.

The fellowship provides specialized training and infrastructure development at Louisiana State University through collaboration with experts at the University of California, Los Angeles. Key products include methodologies for detecting and preventing hidden system failures in vehicle technologies before they cause accidents, domain-informed predictive models for hazard detection at runtime, and workforce development outcomes through graduate student training in artificial intelligence, transportation safety, and cyber-physical systems. The project strengthens research capacity at the institution while advancing the state of the art in autonomous vehicle safety through integrated design and runtime assurance approaches applicable to next-generation advanced driver assistance systems.