The University of Delaware was awarded a $1,499,949 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to develop innovations in machine learning (ML) for autonomous vehicle (AV) safety. The key objectives are to: 1) Create rational ML models that produce accurate predictions with valid rationales, 2) Integrate hardware reliability into ML model design to tolerate runtime faults, and 3) Design a real-time operating system scheduler that ensures time predictability while considering model and hardware reliability. These advancements will be implemented and validated on real AV platforms to enhance end-to-end safety and promote safer, cleaner, and more efficient transportation. The project will also advance education and workforce development in AI and autonomous driving, with a focus on diversity and inclusion in STEM fields. Results and software will be disseminated through open-source platforms, educational programs, and industry outreach.