Bridging the Gap Between AI and Reality • Rhodes, Greece
Time: Tuesday, 4.11
Room: Room B
Authors: Julian Müller, Thies de Graaff, Eike Möhlmann
Abstract: This paper investigates on the integration of Large Language Models (LLMs) with the QC-OpenDRIVE framework in order to generate syntactically and semantically correct OpenDRIVE files. OpenDRIVE files play an important role in the scenario-based validation of autonomous driving systems as they define the static part (e.g. road layout) on which the function are validated. While LLMs excel at generating code or similar tasks which mostly needs to be syntactically correct, the validation of semantic, especially normative, correctness remains challenging. To ensure norm-adherent correctness of generated OpenDRIVE files this paper proposes an integration of a feedback-loop with LLMs and QC-OpenDRIVE. While LLM allow to easily generate different road layouts, they often show issues like missing or unconnected roads or improper continuity. To address this issue, we have implemented E.5.9.1 to ensure geometric continuity between connected roads, which is a key contribution of this paper. State-of-the-art models are evaluated on three tasks to create OpenDRIVE road networks and validate the results featuring the feedbackloop. Results show that models leveraging Retrieval Augmented Generation (RAG) or internal reasoning and using the feedback loop can generate syntactically and semantically valid outputs after iterative corrections. However, challenges remain to prompt complex scenarios and tasks, especially following geometric rules without explicit feedback. The results demonstrate the necessity of domain-specific normative validation frameworks to prepare the use of LLMs for safety-critical applications. They can be used to enable scalable generation of edge-case scenarios while ensuring compliance with industry standards. This work bridges the gap between automated scenario generation and rigorous validation of reliable autonomous driving systems.