elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Accessibility | Contact | Deutsch
Fontsize: [-] Text [+]

Integrating LLMs with QC-OpenDRIVE: Ensuring Normative Correctness in Autonomous Driving Scenarios

Müller, Julian and de Graaff, Thies and Möhlmann, Eike (2025) Integrating LLMs with QC-OpenDRIVE: Ensuring Normative Correctness in Autonomous Driving Scenarios. In: 3rd International Conference on Bridging the Gap between AI and Reality, AISoLA 2025, 16220, pp. 103-116. Springer Nature. AISoLA 2025, 2025-11-01 - 2025-11-05, Rhodos, Griechenland. doi: 10.1007/978-3-032-07132-3_7. ISBN 978-303207131-6. ISSN 0302-9743.

[img] PDF
1MB
[img] PDF - Only accessible within DLR
1MB

Official URL: https://link.springer.com/chapter/10.1007/978-3-032-07132-3_7

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 feedback-loop. 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.

Item URL in elib:https://elib.dlr.de/216257/
Document Type:Conference or Workshop Item (Speech)
Title:Integrating LLMs with QC-OpenDRIVE: Ensuring Normative Correctness in Autonomous Driving Scenarios
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Müller, Julianjulian.mueller (at) dlr.dehttps://orcid.org/0009-0002-9126-9648198382962
de Graaff, Thiesthies.degraaff (at) dlr.dehttps://orcid.org/0009-0006-5918-9524UNSPECIFIED
Möhlmann, EikeEike.Moehlmann (at) dlr.dehttps://orcid.org/0000-0003-3815-6353225533759
Date:11 October 2025
Journal or Publication Title:3rd International Conference on Bridging the Gap between AI and Reality, AISoLA 2025
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Volume:16220
DOI:10.1007/978-3-032-07132-3_7
Page Range:pp. 103-116
Editors:
EditorsEmailEditor's ORCID iDORCID Put Code
Steffen, Bernhardbernhard.steffen (at) tu-dortmund.deUNSPECIFIEDUNSPECIFIED
Publisher:Springer Nature
Series Name:Lecture Notes in Computer Science
ISSN:0302-9743
ISBN:978-303207131-6
Status:Published
Keywords:Large Language Models, OpenDRIVE, QC-OpenDRIVE, Scenario Generation, Semantic Validation, Autonomous Driving
Event Title:AISoLA 2025
Event Location:Rhodos, Griechenland
Event Type:international Conference
Event Start Date:1 November 2025
Event End Date:5 November 2025
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Road Transport
DLR - Research area:Transport
DLR - Program:V ST Straßenverkehr
DLR - Research theme (Project):V - V&V4NGC - Methoden, Prozesse und Werkzeugketten für die Validierung & Verifikation von NGC
Location: Oldenburg
Institutes and Institutions:Institute of Systems Engineering for Future Mobility > Systems Theory and Design
Deposited By: Müller, Julian
Deposited On:01 Dec 2025 06:12
Last Modified:08 Sep 2026 13:07

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
OpenAIRE Validator logo electronic library is running on EPrints
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.