Guided Latent Spaces for Controllable Multi-Scenario Generation in Autonomous Driving (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41308-41309
DOI: 10.1609/aaai.v40i48.42251 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Manasa Mariam Mammen und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Scenario-based testing is an important approach for the development and validation of autonomous driving systems, as it enables evaluation across different driving situations. Safety-critical scenarios are especially relevant, but they occur rarely in real-world data, which creates the need for generation methods. In this paper, we present a scalable AI-based approach based on a variational autoencoder that unifies the generation of different types of critical scenarios while introducing controllability through a structured latent space. The integration of unified generation and latent space control advances AI-based scenario generation towards practical use, thereby supporting the requirements of industrial validation pipelines.
Zitieren
APA
Mammen, M. M., Kayatas, Z., & Wagner, S. (2026). Guided Latent Spaces for Controllable Multi-Scenario Generation in Autonomous Driving (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41308-41309. https://doi.org/10.1609/aaai.v40i48.42251
Vancouver
Mammen MM, Kayatas Z, Wagner S. Guided Latent Spaces for Controllable Multi-Scenario Generation in Autonomous Driving (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41308-41309. doi:10.1609/aaai.v40i48.42251
BibTeX
@article{Mammen2026,
author = {Mammen, Manasa Mariam and Kayatas, Zafer and Wagner, Stefan},
title = {Guided Latent Spaces for Controllable Multi-Scenario Generation in Autonomous Driving (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41308--41309},
doi = {10.1609/aaai.v40i48.42251}
}
EUVIMED