Modeling and Evaluating the Performance of Generative Artificial Intelligence Models in Requirements Engineering Processes for Advanced Driver Assistance Systems

Recent advances in generative artificial intelligence models open new perspectives for supporting activities in requirements engineering, particularly in complex domains such as the development of Advanced Driver Assistance Systems (ADAS). In these systems, requirements must be defined, analyzed, and validated within a context characterized by high technological complexity, large volumes of documentation, and strict safety and compliance constraints. The aim of this work is to explore the potential of using generative AI models to support specific requirements engineering activities, such as requirements analysis and clarification, identification of gaps or inconsistencies, generation of technical artifacts, and improvement of traceability. The presentation aims to analyze the perspective of including this research as a potential PhD topic, combining practical industry experience with domain-specific academic research.