Wang, ZMa, JLai, EMK2025-01-292025-01-292024-12-23Future Internet, ISSN: 1999-5903 (Print); 1999-5903 (Online), MDPI AG, 16(12), 480-480. doi: 10.3390/fi161204801999-59031999-5903http://hdl.handle.net/10292/18556This survey explores the evolution of test scenario generation for autonomous vehicles (AVs), distinguishing between non-adaptive and adaptive scenario approaches. Non-adaptive scenarios, where dynamic objects follow predetermined scripts, provide repeatable and reliable tests but fail to capture the complexity and unpredictability of real-world traffic interactions. In contrast, adaptive scenarios, which adapt in real time to environmental changes, offer a more realistic simulation of traffic conditions, enabling the assessment of an AV system’s adaptability, safety, and robustness. The shift from non-adaptive to adaptive scenarios is increasingly emphasized in AV research, to better evaluate system performance in complex environments. However, generating adaptive scenario is more complex and faces challenges. These include the limited diversity in behaviors, low model interpretability, and high resource requirements. Future research should focus on enhancing the efficiency of adaptive scenario generation and developing comprehensive evaluation metrics to improve the realism and effectiveness of AV testing.© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).https://creativecommons.org/licenses/by/4.0/46 Information and Computing Sciences46 Information and computing sciencesJournal ArticleOpenAccess10.3390/fi16120480