{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:02:30Z","timestamp":1781884950364,"version":"3.54.5"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032071316","type":"print"},{"value":"9783032071323","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:00:00Z","timestamp":1760140800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This paper investigates on the integration of Large Language Models (LLMs) with the  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 . 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.<\/jats:p>\n          <jats:p>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.<\/jats:p>","DOI":"10.1007\/978-3-032-07132-3_7","type":"book-chapter","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T05:27:42Z","timestamp":1760074062000},"page":"103-116","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Integrating LLMs with\u00a0QC-OpenDRIVE: Ensuring Normative Correctness in\u00a0Autonomous Driving Scenarios"],"prefix":"10.1007","author":[{"given":"Julian","family":"M\u00fcller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thies","family":"de Graaff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eike","family":"M\u00f6hlmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,11]]},"reference":[{"key":"7_CR1","unstructured":"ASAM: OpenDRIVE V1.8.1 (2024). https:\/\/www.asam.net\/standards\/detail\/opendrive, https:\/\/publications.pages.asam.net\/standards\/ASAM_OpenDRIVE\/ASAM_OpenDRIVE_Specification\/latest\/specification\/03_terms_and_definitions\/03_terms_and_definitions.html. Accessed 28 Apr 2025"},{"key":"7_CR2","unstructured":"ASAM e.V.: ASAM OpenDRIVE Version 1.7.0. https:\/\/www.asam.net\/index.php?eID=dumpFile&t=f &f=4422 &token=e590561f3c39aa2260e5442e29e93f6693d1cccd (2021). https:\/\/www.asam.net\/index.php?eID=dumpFile&t=f &f=4422 &token=e590561f3c39aa2260e5442e29e93f6693d1cccd. Accessed 27 May 2025"},{"key":"7_CR3","unstructured":"ASAM e.V.: ASAM Standards (2024). https:\/\/www.asam.net\/. Accessed 28 Apr 2025"},{"key":"7_CR4","unstructured":"ASAM e.V.: OpenDRIVE V1.8.1 (2024). https:\/\/www.asam.net\/standards\/detail\/opendrive. Accessed 28 Apr 2025"},{"key":"7_CR5","unstructured":"ASAM e.V.: OpenDRIVE V1.8.1\/10 Roads\/10.3 Road linkage\/Figure 39 (2024). https:\/\/publications.pages.asam.net\/standards\/ASAM_OpenDRIVE\/ASAM_OpenDRIVE_Specification\/latest\/specification\/10_roads\/10_03_road_linkage.html. Accessed 15 May 2025"},{"key":"7_CR6","unstructured":"ASAM e.V.: QC OpenDRIVE. https:\/\/github.com\/asam-ev\/qc-opendrive (2024), gitHub repository"},{"key":"7_CR7","unstructured":"Austin, J., et\u00a0al.: Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)"},{"key":"7_CR8","doi-asserted-by":"publisher","unstructured":"Becker, D., Ru , F., Geller, C., Eckstein, L.: Generation of complex road networks using a simplified logical description for the validation of automated vehicles. In: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp.\u00a01\u20137 (2020). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294664","DOI":"10.1109\/ITSC45102.2020.9294664"},{"key":"7_CR9","doi-asserted-by":"publisher","unstructured":"Chang, C., Wang, S., Zhang, J., Ge, J., Li, L.: LLMScenario: large language model driven scenario generation. IEEE Trans. Syst. Man Cybern. Syst. (2024). https:\/\/doi.org\/10.1109\/TSMC.2024.3392930","DOI":"10.1109\/TSMC.2024.3392930"},{"key":"7_CR10","unstructured":"Chen, M., et al.: Evaluating large language models trained on code. CoRR abs\/2107.03374 (2021)"},{"key":"7_CR11","unstructured":"Guo, D., et\u00a0al.: DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning (2025). DeepSeek-AI. https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"7_CR12","doi-asserted-by":"publisher","unstructured":"Eisemann, L., Maucher, J.: Automatic odometry-less opendrive generation from sparse point clouds. In: 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp. 681\u2013688. IEEE (2023). https:\/\/doi.org\/10.1109\/itsc57777.2023.10421842","DOI":"10.1109\/itsc57777.2023.10421842"},{"key":"7_CR13","doi-asserted-by":"publisher","unstructured":"Eisemann, L., Maucher, J.: Divide and Conquer: a systematic approach for industrial scale high-definition opendrive generation from sparse point clouds. In: 2024 IEEE Intelligent Vehicles Symposium (IV), pp. 2443\u20132450. IEEE (2024). https:\/\/doi.org\/10.1109\/IV55156.2024.10588602","DOI":"10.1109\/IV55156.2024.10588602"},{"key":"7_CR14","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst. 43(2), 1\u201355 (2025). https:\/\/doi.org\/10.1145\/3703155","DOI":"10.1145\/3703155"},{"key":"7_CR16","unstructured":"Huynh, N., Lin, B.: Large language models for code generation: a comprehensive survey of challenges, techniques, evaluation, and applications (2025). https:\/\/arxiv.org\/abs\/2503.01245"},{"key":"7_CR17","unstructured":"Jiang, J., Wang, F., Shen, J., Kim, S., Kim, S.: A survey on large language models for code generation (2024). https:\/\/arxiv.org\/abs\/2406.00515"},{"key":"7_CR18","unstructured":"Lai, J., Gan, W., Wu, J., Qi, Z., Yu, P.S.: Large language models in law: a survey (2023). https:\/\/arxiv.org\/abs\/2312.03718"},{"key":"7_CR19","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks (2021). https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"7_CR20","unstructured":"Microsoft Corporation: Introducing Copilot Agent Mode (2025). https:\/\/code.visualstudio.com\/blogs\/2025\/02\/24\/introducing-copilot-agent-mode"},{"key":"7_CR21","unstructured":"Pires, R., Junior, R.M., Nogueira, R.: Automatic legal writing evaluation of LLMs (2025). https:\/\/arxiv.org\/abs\/2504.21202"},{"key":"7_CR22","unstructured":"Ruan, B.K., Tsui, H.T., Li, Y.H., Shuai, H.H.: Traffic scene generation from natural language description for autonomous vehicles with large language model (2025). https:\/\/arxiv.org\/abs\/2409.09575"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Scholtes, M., et al.: 6-layer model for a structured description and categorization of urban traffic and environment (2021). https:\/\/arxiv.org\/abs\/2012.06319","DOI":"10.1109\/ACCESS.2021.3072739"},{"key":"7_CR24","doi-asserted-by":"publisher","unstructured":"Schwab, B., Kolbe, T.: Validation of parametric opendrive road space models. Ann. Photogrammetry, Remote Sens. Spatial Inf. Sci. X-4-W2-2022 (2022). https:\/\/doi.org\/10.5194\/isprs-annals-X-4-W2-2022-257-2022","DOI":"10.5194\/isprs-annals-X-4-W2-2022-257-2022"},{"key":"7_CR25","unstructured":"Team, M.A.: Mistral large. https:\/\/mistral.ai\/news\/mistral-large-2407 (2024). https:\/\/mistral.ai\/news\/mistral-large-2407. Accessed 26 May 2025"},{"key":"7_CR26","doi-asserted-by":"publisher","unstructured":"Wachenfeld, W., Winner, H.: The Release of Autonomous Vehicles, pp. 425\u2013449. Springer, Berlin, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-48847-8_21","DOI":"10.1007\/978-3-662-48847-8_21"},{"key":"7_CR27","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models (2023). https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"7_CR28","unstructured":"Williams, S., Huckle, J.: Easy problems that LLMs get wrong (2024). https:\/\/arxiv.org\/abs\/2405.19616"},{"key":"7_CR29","unstructured":"Xiao, Y., Sun, Y., Lin, Y.: ML-SceGen: a multi-level scenario generation framework (2025). https:\/\/arxiv.org\/abs\/2501.10782"},{"key":"7_CR30","unstructured":"Yang, A., et al.: Qwen3 technical report (2025). https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"7_CR31","unstructured":"Yang, J., et al.: Harnessing the power of LLMs in practice: a survey on chatgpt and beyond (2023). https:\/\/arxiv.org\/abs\/2304.13712"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, J., Xu, C., Li, B.: ChatScene: knowledge-enabled safety-critical scenario generation for autonomous vehicles (2024). https:\/\/arxiv.org\/abs\/2405.14062","DOI":"10.1109\/CVPR52733.2024.01464"}],"container-title":["Lecture Notes in Computer Science","Bridging the Gap Between AI and Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07132-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T05:27:52Z","timestamp":1760074072000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07132-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,11]]},"ISBN":["9783032071316","9783032071323"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07132-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,11]]},"assertion":[{"value":"11 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AISoLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Bridging the Gap between AI and Reality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rhodes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aisola2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025-aisola.isola-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}