---
_id: '13120'
abstract:
- lang: eng
  text: 'This paper introduces an approach that leverages large language models (LLMs)
    to convert detailed descriptions of an Operational Design Domain (ODD) into realistic,
    executable simulation scenarios for testing autonomous vehicles. The method combines
    model-based and data-driven techniques to decompose ODDs into three key components:
    environmental, scenery, and dynamic elements. It then applies prompt engineering
    to generate ScenarioRunner scripts compatible with CARLA. The model-based component
    guides the LLM using structured prompts and a “Tree of Thoughts” strategy to outline
    the scenario, while a data-driven refinement process, drawing inspiration from
    red teaming, enhances the accuracy and robustness of the generated scripts over
    time. Experimental results show that while static components, such as weather
    and road layouts, are well captured, dynamic elements like vehicle and pedestrian
    behavior require further refinement. Overall, this approach not only reduces the
    manual effort involved in creating simulation scenarios but also identifies key
    challenges and opportunities for advancing safer and more adaptive autonomous
    driving systems.'
author:
- first_name: Aaron Agyapong
  full_name: Danso, Aaron Agyapong
  id: '84400'
  last_name: Danso
- first_name: Ulrich
  full_name: Büker, Ulrich
  id: '81453'
  last_name: Büker
  orcid: 0000-0002-4403-3889
citation:
  ama: Danso AA, Büker U. Automated Generation of Test Scenarios for Autonomous Driving
    Using LLMs. <i>Electronics</i>. 2025;14(16):3177. doi:<a href="https://doi.org/10.3390/electronics14163177">10.3390/electronics14163177</a>
  apa: Danso, A. A., &#38; Büker, U. (2025). Automated Generation of Test Scenarios
    for Autonomous Driving Using LLMs. <i>Electronics</i>, <i>14</i>(16), 3177. <a
    href="https://doi.org/10.3390/electronics14163177">https://doi.org/10.3390/electronics14163177</a>
  bjps: <b>Danso AA and Büker U</b> (2025) Automated Generation of Test Scenarios
    for Autonomous Driving Using LLMs. <i>Electronics</i> <b>14</b>, 3177.
  chicago: 'Danso, Aaron Agyapong, and Ulrich Büker. “Automated Generation of Test
    Scenarios for Autonomous Driving Using LLMs.” <i>Electronics</i> 14, no. 16 (2025):
    3177. <a href="https://doi.org/10.3390/electronics14163177">https://doi.org/10.3390/electronics14163177</a>.'
  chicago-de: 'Danso, Aaron Agyapong und Ulrich Büker. 2025. Automated Generation
    of Test Scenarios for Autonomous Driving Using LLMs. <i>Electronics</i> 14, Nr.
    16: 3177. doi:<a href="https://doi.org/10.3390/electronics14163177">10.3390/electronics14163177</a>,
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Danso, Aaron Agyapong</span>
    ; <span style="font-variant:small-caps;">Büker, Ulrich</span>: Automated Generation
    of Test Scenarios for Autonomous Driving Using LLMs. In: <i>Electronics</i> Bd.
    14. Basel, MDPI (2025), Nr. 16, S. 3177'
  havard: A.A. Danso, U. Büker, Automated Generation of Test Scenarios for Autonomous
    Driving Using LLMs, Electronics. 14 (2025) 3177.
  ieee: 'A. A. Danso and U. Büker, “Automated Generation of Test Scenarios for Autonomous
    Driving Using LLMs,” <i>Electronics</i>, vol. 14, no. 16, p. 3177, 2025, doi:
    <a href="https://doi.org/10.3390/electronics14163177">10.3390/electronics14163177</a>.'
  mla: Danso, Aaron Agyapong, and Ulrich Büker. “Automated Generation of Test Scenarios
    for Autonomous Driving Using LLMs.” <i>Electronics</i>, vol. 14, no. 16, 2025,
    p. 3177, <a href="https://doi.org/10.3390/electronics14163177">https://doi.org/10.3390/electronics14163177</a>.
  short: A.A. Danso, U. Büker, Electronics 14 (2025) 3177.
  ufg: '<b>Danso, Aaron Agyapong/Büker, Ulrich</b>: Automated Generation of Test Scenarios
    for Autonomous Driving Using LLMs, in: <i>Electronics</i> 14 (2025), H. 16,  S.
    3177.'
  van: Danso AA, Büker U. Automated Generation of Test Scenarios for Autonomous Driving
    Using LLMs. Electronics. 2025;14(16):3177.
date_created: 2025-08-11T15:38:12Z
date_updated: 2025-08-12T07:38:15Z
department:
- _id: DEP5023
- _id: DEP5000
doi: 10.3390/electronics14163177
intvolume: '        14'
issue: '16'
keyword:
- large language models
- generation
- Operational Design Domain
- autonomous vehicles
- simulation
- CARLA
- ScenarioRunner
- prompt-engineering
- fine-tuning
language:
- iso: eng
page: '3177'
place: Basel
publication: Electronics
publication_identifier:
  eissn:
  - '2079-9292 '
publication_status: published
publisher: MDPI
quality_controlled: '1'
status: public
title: Automated Generation of Test Scenarios for Autonomous Driving Using LLMs
type: scientific_journal_article
user_id: '83781'
volume: 14
year: '2025'
...
---
_id: '2071'
abstract:
- lang: eng
  text: In this paper, a fuzzy pattern classification tuning approach is proposed,
    which is based on fusion concept. In this method, tuning parameters are learned
    in a training procedure, enabling system to be capable of managing individual
    classification task. Fuzzy c-means, as a specific instance of Tuning Reference,
    is employed as a tool to offer membership function which is used for making decisions
    and its membership function fuses (tunes) another membership function captured
    from fuzzy pattern classification and then final decisions are made upon fused
    one. Experiments are taken on five benchmark datasets, one of them shows an equal
    performance and the other four present better results than each single classifier.
author:
- first_name: Rui
  full_name: Li, Rui
  id: '2000'
  last_name: Li
- first_name: Volker
  full_name: Lohweg, Volker
  id: '1804'
  last_name: Lohweg
  orcid: 0000-0002-3325-7887
citation:
  ama: 'Li R, Lohweg V. Fuzzy Pattern Classification Tuning by Parameter Learning
    based on Fusion Concept. In: In: The 11th Conference on Information Fusion, June
    30 - July 3, Cologne, Germany; 2008.'
  apa: 'Li, R., &#38; Lohweg, V. (2008). Fuzzy Pattern Classification Tuning by Parameter
    Learning based on Fusion Concept. In: The 11th Conference on Information Fusion,
    June 30 - July 3, Cologne, Germany.'
  bjps: '<b>Li R and Lohweg V</b> (2008) Fuzzy Pattern Classification Tuning by Parameter
    Learning Based on Fusion Concept. In: The 11th Conference on Information Fusion,
    June 30 - July 3, Cologne, Germany.'
  chicago: 'Li, Rui, and Volker Lohweg. “Fuzzy Pattern Classification Tuning by Parameter
    Learning Based on Fusion Concept.” In: The 11th Conference on Information Fusion,
    June 30 - July 3, Cologne, Germany, 2008.'
  chicago-de: 'Li, Rui und Volker Lohweg. 2008. Fuzzy Pattern Classification Tuning
    by Parameter Learning based on Fusion Concept. In: . In: The 11th Conference on
    Information Fusion, June 30 - July 3, Cologne, Germany.'
  din1505-2-1: '<span style="font-variant:small-caps;">Li, Rui</span> ; <span style="font-variant:small-caps;">Lohweg,
    Volker</span>: Fuzzy Pattern Classification Tuning by Parameter Learning based
    on Fusion Concept. In:  : In: The 11th Conference on Information Fusion, June
    30 - July 3, Cologne, Germany, 2008'
  havard: 'R. Li, V. Lohweg, Fuzzy Pattern Classification Tuning by Parameter Learning
    based on Fusion Concept, in: In: The 11th Conference on Information Fusion, June
    30 - July 3, Cologne, Germany, 2008.'
  ieee: R. Li and V. Lohweg, “Fuzzy Pattern Classification Tuning by Parameter Learning
    based on Fusion Concept,” 2008.
  mla: 'Li, Rui, and Volker Lohweg. <i>Fuzzy Pattern Classification Tuning by Parameter
    Learning Based on Fusion Concept</i>. In: The 11th Conference on Information Fusion,
    June 30 - July 3, Cologne, Germany, 2008.'
  short: 'R. Li, V. Lohweg, in: In: The 11th Conference on Information Fusion, June
    30 - July 3, Cologne, Germany, 2008.'
  ufg: '<b>Li, Rui/Lohweg, Volker (2008)</b>: Fuzzy Pattern Classification Tuning
    by Parameter Learning based on Fusion Concept, in: .'
  van: 'Li R, Lohweg V. Fuzzy Pattern Classification Tuning by Parameter Learning
    based on Fusion Concept. In In: The 11th Conference on Information Fusion, June
    30 - July 3, Cologne, Germany; 2008.'
date_created: 2019-11-29T14:09:33Z
date_updated: 2023-03-15T13:49:38Z
department:
- _id: DEP5023
keyword:
- tuning parameter
- information fusion
- fuzzy cmeans
- membership function
- fuzzy pattern classification
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/document/4632223/keywords#full-text-header
publication_identifier:
  isbn:
  - 978-3-8007-3092-6
publication_status: published
publisher: 'In: The 11th Conference on Information Fusion, June 30 - July 3, Cologne,
  Germany'
status: public
title: Fuzzy Pattern Classification Tuning by Parameter Learning based on Fusion Concept
type: conference
user_id: '45673'
year: 2008
...