[{"user_id":"83781","place":"Basel","intvolume":"        14","page":"3177","department":[{"_id":"DEP5023"},{"_id":"DEP5000"}],"status":"public","doi":"10.3390/electronics14163177","citation":{"havard":"A.A. Danso, U. Büker, Automated Generation of Test Scenarios for Autonomous Driving Using LLMs, Electronics. 14 (2025) 3177.","van":"Danso AA, Büker U. Automated Generation of Test Scenarios for Autonomous Driving Using LLMs. Electronics. 2025;14(16):3177.","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.","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>.","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","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>.","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.","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>","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>","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>, .","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>."},"title":"Automated Generation of Test Scenarios for Autonomous Driving Using LLMs","issue":"16","_id":"13120","type":"scientific_journal_article","language":[{"iso":"eng"}],"year":"2025","quality_controlled":"1","volume":14,"keyword":["large language models","generation","Operational Design Domain","autonomous vehicles","simulation","CARLA","ScenarioRunner","prompt-engineering","fine-tuning"],"publication_status":"published","date_created":"2025-08-11T15:38:12Z","author":[{"id":"84400","full_name":"Danso, Aaron Agyapong","first_name":"Aaron Agyapong","last_name":"Danso"},{"orcid":"0000-0002-4403-3889","full_name":"Büker, Ulrich","id":"81453","first_name":"Ulrich","last_name":"Büker"}],"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."}],"publication_identifier":{"eissn":["2079-9292 "]},"date_updated":"2025-08-12T07:38:15Z","publication":"Electronics","publisher":"MDPI"},{"quality_controlled":"1","year":"2024","language":[{"iso":"eng"}],"date_created":"2024-04-12T07:06:41Z","author":[{"last_name":"Meyer","first_name":"Frederic","id":"70963","full_name":"Meyer, Frederic"},{"id":"73431","full_name":"Freitag, Lennart","first_name":"Lennart","last_name":"Freitag"},{"last_name":"Hinrichsen","full_name":"Hinrichsen, Sven","id":"49010","first_name":"Sven"},{"last_name":"Niggemann","id":"10876","full_name":"Niggemann, Oliver","first_name":"Oliver"}],"keyword":["assembly instruction","GPT","large language model","LLM","prompt"],"publication_status":"published","volume":78,"publication_identifier":{"eisbn":["979-8-3503-6122-3"],"isbn":["979-8-3503-6123-0"]},"abstract":[{"text":"With the increasing complexity in manual assembly and a demographic decline in skilled workforce, the importance of well-documented processes through assembly instructions has grown. Creating these instructions is a time-consuming and knowledge-intensive task that typically relies on experienced employees. Although various automation solutions have been proposed to assist in generating assembly instructions, they often fall short in providing detailed textual guidance. With the rise of generative artificial intelligence (AI), new potentials arise in this domain. Therefore, this paper explores these potentials by employing various large language models (LLMs), prompting techniques and input data in an experimental setup for generating detailed assembly instructions, including the planning of assembly sequences as well as textual guidance on tools, assembly activities, and quality assurance measures. The findings reveal promising opportunities in leveraging LLMs but also substantial challenges, particularly in assembly sequence planning. To improve the reliability of generating assembly instructions, we propose a multi-agent concept that decomposes the complex task into simpler subtasks, each managed by specialized agents.","lang":"eng"}],"publisher":"IEEE","date_updated":"2024-10-22T07:28:35Z","publication":"2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)","status":"public","department":[{"_id":"DEP7020"},{"_id":"DEP1305"}],"intvolume":"        78","place":"Piscataway, NJ","user_id":"83781","conference":{"start_date":"2024-09-10","end_date":"2024-09-13","name":"29th International Conference on Emerging Technologies and Factory Automation (ETFA)","location":"Padova, Italy"},"title":"Potentials of Large Language Models for Generating Assembly Instructions","citation":{"ama":"Meyer F, Freitag L, Hinrichsen S, Niggemann O. <i>Potentials of Large Language Models for Generating Assembly Instructions</i>. Vol 78. (IEEE, ed.). IEEE; 2024. doi:<a href=\"https://doi.org/10.1109/ETFA61755.2024.10710806\">https://doi.org/10.1109/ETFA61755.2024.10710806</a>","apa":"Meyer, F., Freitag, L., Hinrichsen, S., &#38; Niggemann, O. (2024). Potentials of Large Language Models for Generating Assembly Instructions. In IEEE (Ed.), <i>2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)</i> (Vol. 78). IEEE. <a href=\"https://doi.org/10.1109/ETFA61755.2024.10710806\">https://doi.org/10.1109/ETFA61755.2024.10710806</a>","ieee":"F. Meyer, L. Freitag, S. Hinrichsen, and O. Niggemann, <i>Potentials of Large Language Models for Generating Assembly Instructions</i>, vol. 78. Piscataway, NJ: IEEE, 2024. doi: <a href=\"https://doi.org/10.1109/ETFA61755.2024.10710806\">https://doi.org/10.1109/ETFA61755.2024.10710806</a>.","mla":"Meyer, Frederic, et al. “Potentials of Large Language Models for Generating Assembly Instructions.” <i>2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)</i>, edited by IEEE, vol. 78, IEEE, 2024, <a href=\"https://doi.org/10.1109/ETFA61755.2024.10710806\">https://doi.org/10.1109/ETFA61755.2024.10710806</a>.","short":"F. Meyer, L. Freitag, S. Hinrichsen, O. Niggemann, Potentials of Large Language Models for Generating Assembly Instructions, IEEE, Piscataway, NJ, 2024.","ufg":"<b>Meyer, Frederic u. a.</b>: Potentials of Large Language Models for Generating Assembly Instructions, Bd. 78, hg. von IEEE, Piscataway, NJ 2024.","chicago":"Meyer, Frederic, Lennart Freitag, Sven Hinrichsen, and Oliver Niggemann. <i>Potentials of Large Language Models for Generating Assembly Instructions</i>. Edited by IEEE. <i>2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)</i>. Vol. 78. Piscataway, NJ: IEEE, 2024. <a href=\"https://doi.org/10.1109/ETFA61755.2024.10710806\">https://doi.org/10.1109/ETFA61755.2024.10710806</a>.","chicago-de":"Meyer, Frederic, Lennart Freitag, Sven Hinrichsen und Oliver Niggemann. 2024. <i>Potentials of Large Language Models for Generating Assembly Instructions</i>. Hg. von IEEE. <i>2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)</i>. Bd. 78. Piscataway, NJ: IEEE. doi:<a href=\"https://doi.org/10.1109/ETFA61755.2024.10710806\">https://doi.org/10.1109/ETFA61755.2024.10710806</a>, .","bjps":"<b>Meyer F <i>et al.</i></b> (2024) <i>Potentials of Large Language Models for Generating Assembly Instructions</i>, IEEE (ed.). Piscataway, NJ: IEEE.","din1505-2-1":"<span style=\"font-variant:small-caps;\">Meyer, Frederic</span> ; <span style=\"font-variant:small-caps;\">Freitag, Lennart</span> ; <span style=\"font-variant:small-caps;\">Hinrichsen, Sven</span> ; <span style=\"font-variant:small-caps;\">Niggemann, Oliver</span> ; <span style=\"font-variant:small-caps;\">IEEE</span> (Hrsg.): <i>Potentials of Large Language Models for Generating Assembly Instructions</i>. Bd. 78. Piscataway, NJ : IEEE, 2024","van":"Meyer F, Freitag L, Hinrichsen S, Niggemann O. Potentials of Large Language Models for Generating Assembly Instructions. IEEE, editor. Vol. 78, 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA). Piscataway, NJ: IEEE; 2024.","havard":"F. Meyer, L. Freitag, S. Hinrichsen, O. Niggemann, Potentials of Large Language Models for Generating Assembly Instructions, IEEE, Piscataway, NJ, 2024."},"doi":"https://doi.org/10.1109/ETFA61755.2024.10710806","corporate_editor":["IEEE"],"type":"conference_editor_article","_id":"11330"},{"type":"scientific_journal_article","_id":"12811","place":"New York, NY","user_id":"83781","department":[{"_id":"DEP5023"}],"page":"1171-1177","intvolume":"        70","status":"public","isi":"1","external_id":{"isi":["001012981300044"]},"doi":"10.1109/tns.2023.3242626","citation":{"chicago":"Shayan, Helmand, Kai Krycki, Marco Doemeland, and Markus Lange-Hegermann. “PGNAA Spectral Classification of Metal With Density Estimations.” <i>IEEE Transactions on Nuclear Science</i> 70, no. 6 (2023): 1171–77. <a href=\"https://doi.org/10.1109/tns.2023.3242626\">https://doi.org/10.1109/tns.2023.3242626</a>.","chicago-de":"Shayan, Helmand, Kai Krycki, Marco Doemeland und Markus Lange-Hegermann. 2023. PGNAA Spectral Classification of Metal With Density Estimations. <i>IEEE Transactions on Nuclear Science</i> 70, Nr. 6: 1171–1177. doi:<a href=\"https://doi.org/10.1109/tns.2023.3242626\">10.1109/tns.2023.3242626</a>, .","bjps":"<b>Shayan H <i>et al.</i></b> (2023) PGNAA Spectral Classification of Metal With Density Estimations. <i>IEEE Transactions on Nuclear Science</i> <b>70</b>, 1171–1177.","din1505-2-1":"<span style=\"font-variant:small-caps;\">Shayan, Helmand</span> ; <span style=\"font-variant:small-caps;\">Krycki, Kai</span> ; <span style=\"font-variant:small-caps;\">Doemeland, Marco</span> ; <span style=\"font-variant:small-caps;\">Lange-Hegermann, Markus</span>: PGNAA Spectral Classification of Metal With Density Estimations. In: <i>IEEE Transactions on Nuclear Science</i> Bd. 70. New York, NY, IEEE (2023), Nr. 6, S. 1171–1177","van":"Shayan H, Krycki K, Doemeland M, Lange-Hegermann M. PGNAA Spectral Classification of Metal With Density Estimations. IEEE Transactions on Nuclear Science. 2023;70(6):1171–7.","havard":"H. Shayan, K. Krycki, M. Doemeland, M. Lange-Hegermann, PGNAA Spectral Classification of Metal With Density Estimations, IEEE Transactions on Nuclear Science. 70 (2023) 1171–1177.","ama":"Shayan H, Krycki K, Doemeland M, Lange-Hegermann M. PGNAA Spectral Classification of Metal With Density Estimations. <i>IEEE Transactions on Nuclear Science</i>. 2023;70(6):1171-1177. doi:<a href=\"https://doi.org/10.1109/tns.2023.3242626\">10.1109/tns.2023.3242626</a>","apa":"Shayan, H., Krycki, K., Doemeland, M., &#38; Lange-Hegermann, M. (2023). PGNAA Spectral Classification of Metal With Density Estimations. <i>IEEE Transactions on Nuclear Science</i>, <i>70</i>(6), 1171–1177. <a href=\"https://doi.org/10.1109/tns.2023.3242626\">https://doi.org/10.1109/tns.2023.3242626</a>","ieee":"H. Shayan, K. Krycki, M. Doemeland, and M. Lange-Hegermann, “PGNAA Spectral Classification of Metal With Density Estimations,” <i>IEEE Transactions on Nuclear Science</i>, vol. 70, no. 6, pp. 1171–1177, 2023, doi: <a href=\"https://doi.org/10.1109/tns.2023.3242626\">10.1109/tns.2023.3242626</a>.","mla":"Shayan, Helmand, et al. “PGNAA Spectral Classification of Metal With Density Estimations.” <i>IEEE Transactions on Nuclear Science</i>, vol. 70, no. 6, 2023, pp. 1171–77, <a href=\"https://doi.org/10.1109/tns.2023.3242626\">https://doi.org/10.1109/tns.2023.3242626</a>.","short":"H. Shayan, K. Krycki, M. Doemeland, M. Lange-Hegermann, IEEE Transactions on Nuclear Science 70 (2023) 1171–1177.","ufg":"<b>Shayan, Helmand u. a.</b>: PGNAA Spectral Classification of Metal With Density Estimations, in: <i>IEEE Transactions on Nuclear Science</i> 70 (2023), H. 6,  S. 1171–1177."},"title":"PGNAA Spectral Classification of Metal With Density Estimations","issue":"6","abstract":[{"lang":"eng","text":"For environmental, sustainable economic and political reasons, recycling processes are becoming increasingly important, aiming at a much higher use of secondary raw materials. Currently, for the copper and aluminum industries, no method for the non-destructive online analysis of heterogeneous materials is available. The prompt gamma neutron activation analysis (PGNAA) has the potential to overcome this challenge. A difficulty when using PGNAA for online classification arises from the small amount of noisy data, due to short-term measurements. In this case, classical evaluation methods using detailed peak by peak analysis fail. Therefore, we propose to view spectral data as probability distributions. Then, we can classify material using maximum log-likelihood with respect to kernel density estimation and use discrete sampling to optimize hyperparameters. For measurements of pure aluminum alloys we achieve near-perfect classification of aluminum alloys under 0.25 s."}],"publication_identifier":{"issn":["0018-9499"],"eissn":["1558-1578"]},"publication":"IEEE Transactions on Nuclear Science","date_updated":"2025-06-26T07:45:59Z","publisher":"IEEE","language":[{"iso":"eng"}],"year":"2023","volume":70,"publication_status":"published","keyword":["Classification of metal","kernel density estimation","maximum log-likelihood","online classification","prompt gamma neutron activation analysis (PGNAA) spectral classification","random sampling"],"date_created":"2025-04-16T12:38:21Z","author":[{"last_name":"Shayan","first_name":"Helmand","id":"79365","full_name":"Shayan, Helmand"},{"last_name":"Krycki","full_name":"Krycki, Kai","first_name":"Kai"},{"last_name":"Doemeland","full_name":"Doemeland, Marco","first_name":"Marco"},{"last_name":"Lange-Hegermann","full_name":"Lange-Hegermann, Markus","id":"71761","first_name":"Markus"}]}]