EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A ROS-Based Modular End-to-End Architecture: Building and Validating a Safe and Reliable Autonomous Driving Stack

Fabio Sánchez-García iD, Rodrigo Gutiérrez-Moreno iD, Miguel Antunes-García iD, Santiago Montiel-Marín iD, Franck Fierro iD, Elena López-Guillén iD, Rafael Barea iD, Luis M Bergasa iD

Sensors · 04.07.2026 · 26 (13) · 4269

DOI: 10.3390/s26134269 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.07.2026. Verfasst von Fabio Sánchez-García und 7 weiteren Autor:innen. Beteiligte Einrichtung: Electronics Department, University of Alcalá (UAH), 28805 Alcalá de Henares, Spain. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerio de Ciencia, Innovación y Universidades, Comunidad de Madrid.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The implementation of safe and reliable Autonomous Driving Stacks in complex urban environments remains a formidable engineering challenge. While classical modular pipelines provide necessary component-level interpretability, they are inherently rigid, often struggling to adapt to novel environments and failing to provide robust scene interpretation in highly interactive scenarios. In this paper, we present a modular End-to-End ROS-based autonomous driving architecture that upgrades a classical modular baseline by injecting learning-based models into its individual processing layers, integrating GaussianCaR and CLIP for dense semantic BEV perception, expanding the Hierarchical Petri Net state space for safe multi-agent reasoning, refining the planning layer with continuous curve optimization, and replacing the previous reactive controller with an Adaptive Nonlinear Model Predictive Control strategy for superior trajectory tracking. Validated in the CARLA simulator across challenging traffic scenarios and adverse environmental conditions, the proposed architecture raises the Driving Score from 53.81% to 66.46% over the previous baseline, driven by a substantial increase in the Infraction Penalty from 0.59 to 0.79, reflecting a fundamental shift towards safer and more conservative driving behavior at the cost of a moderate reduction in route completion. Against pure End-to-End approaches, our architecture achieves the highest Driving Score at 73.9% and the strongest Infraction Penalty at 0.913, demonstrating that modular interpretability and competitive End-to-End performance are not mutually exclusive. Code will be made publicly available online.

Schlagwörter

Stichwörter der Autor:innen

CARLAROSautonomous drivingholistic validationmodular End-to-Endsimulation

Autor:innen und Institutionen

  • Electronics Department, University of Alcalá (UAH), 28805 Alcalá de Henares, Spain.

ORCID-Profile: Fabio Sánchez-García, Rodrigo Gutiérrez-Moreno, Miguel Antunes-García, Santiago Montiel-Marín, Franck Fierro, Elena López-Guillén, Rafael Barea, Luis M Bergasa

Förderung

  • Ministerio de Ciencia, Innovación y Universidades
  • Comunidad de Madrid

Zitieren

APA

Sánchez-García, F., Gutiérrez-Moreno, R., Antunes-García, M., Montiel-Marín, S., Fierro, F., López-Guillén, E., Barea, R., & Bergasa, L. M. (2026). A ROS-Based Modular End-to-End Architecture: Building and Validating a Safe and Reliable Autonomous Driving Stack. Sensors, 26(13), 4269. https://doi.org/10.3390/s26134269

Vancouver

Sánchez-García F, Gutiérrez-Moreno R, Antunes-García M, Montiel-Marín S, Fierro F, López-Guillén E, et al. A ROS-Based Modular End-to-End Architecture: Building and Validating a Safe and Reliable Autonomous Driving Stack. Sensors. 2026;26(13):4269. doi:10.3390/s26134269

BibTeX
@article{SnchezGarca2026,
  author = {Sánchez-García, Fabio and Gutiérrez-Moreno, Rodrigo and Antunes-García, Miguel and Montiel-Marín, Santiago and Fierro, Franck and López-Guillén, Elena and Barea, Rafael and Bergasa, Luis M},
  title = {A ROS-Based Modular End-to-End Architecture: Building and Validating a Safe and Reliable Autonomous Driving Stack},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4269},
  doi = {10.3390/s26134269}
}
Kostenlos starten →