EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Big Data-Driven Multi-Constraint Learning for Adaptive Safe Driving Control

Yipene Cedric Francois Bassole, Yunsick Sung

Mathematics · 05.08.2026 · 14 (15) · 2810

DOI: 10.3390/math14152810 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 05.08.2026. Verfasst von Yipene Cedric Francois Bassole und 1 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Regional Innovation System & Education (RISE)” through the Seoul RISE Center, Ministry of Education, the Seoul Metropolitan Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

End-to-end autonomous driving systems have demonstrated remarkable potential in navigating complex environments by directly mapping sensory inputs to control actions. However, many existing approaches rely on a single encoder to compress driving big data into a latent vector, which does not explicitly convert driving conditions into internal safety constraints. In addition, some approaches often depend on static, inflexible safety boundaries driven by mathematical equations, and they lack a clear mechanism to adapt control actions under varying conditions. This disconnection between conditions and control actions limits their ability to maintain safe operational controls in diverse kinds of scenarios. To address these limitations, we propose a Big Data-Driven Multi-Constraint Learning framework to generate safe driving action proxies derived from ego motion represented by steering and acceleration. Our architecture uses two encoders in cascade: a Temporal State Encoder that extracts a latent state representation from input driving states using temporal self-attention, and a Latent Constraint Generation Encoder that transforms this latent state into a compact internal constraint vector representing flexible and dynamic safety boundaries instead of static mathematical equations. This constraint vector is fused with the latent state representation to guide a Control Network for action generation, while a Condition Classifier and a Safety Discriminator enforce condition adaptability and safety. We evaluated the framework on the large-scale nuScenes big data repository, and experimental results demonstrated that our deep learning analysis successfully uncovers hidden safety patterns across massive driving logs, yielding stable convergence with low errors, notably a normalized Steering Mean Absolute Error (MAE) of 0.0189, a normalized Acceleration Mean Absolute Error of 0.0387, and strong safety discrimination with a Safety Accuracy of 0.9996, indicating that the learned internal safety constraints effectively modulate control actions under diverse driving states and uncertainties.

Förderung

  • “Regional Innovation System & Education (RISE)” through the Seoul RISE Center
  • Ministry of Education
  • the Seoul Metropolitan Government
  • Institute of Information & communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Deve…
  • Korea government

Zitieren

APA

Bassole, Y. C. F., & Sung, Y. (2026). Big Data-Driven Multi-Constraint Learning for Adaptive Safe Driving Control. Mathematics, 14(15), 2810. https://doi.org/10.3390/math14152810

Vancouver

Bassole YCF, Sung Y. Big Data-Driven Multi-Constraint Learning for Adaptive Safe Driving Control. Mathematics. 2026;14(15):2810. doi:10.3390/math14152810

BibTeX
@article{Bassole2026,
  author = {Bassole, Yipene Cedric Francois and Sung, Yunsick},
  title = {Big Data-Driven Multi-Constraint Learning for Adaptive Safe Driving Control},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {2810},
  doi = {10.3390/math14152810}
}
Kostenlos starten →