Hybrid Vision Navigation with Hierarchical VLM–LLM Decision Making
Machines · 14.04.2026 · 14 (4) · 435
DOI: 10.3390/machines14040435 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 14.04.2026. Verfasst von Rihem Farkh und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper presents a hybrid navigation architecture for mapless navigation based on monocular vision. The system combines perception-driven affordance control with event-triggered semantic reasoning within a unified decision framework. Navigation behavior is governed by interpretable perceptual signals and a vision-derived progress proxy that enables self-monitoring. A reactive control regime ensures real-time safety, while a semantic reasoning module is activated only under persistent navigation difficulty to provide structured guidance. Experimental results in simulation and real-world deployment demonstrate improved success rate, safety, and efficiency compared to reactive and continuously active semantic baselines, while maintaining real-time performance on embedded hardware.
Zitieren
APA
Farkh, R., Oudinet, G., Adjou, M., Moussa, A., & Fouad, Y. (2026). Hybrid Vision Navigation with Hierarchical VLM–LLM Decision Making. Machines, 14(4), 435. https://doi.org/10.3390/machines14040435
Vancouver
Farkh R, Oudinet G, Adjou M, Moussa A, Fouad Y. Hybrid Vision Navigation with Hierarchical VLM–LLM Decision Making. Machines. 2026;14(4):435. doi:10.3390/machines14040435
BibTeX
@article{Farkh2026,
author = {Farkh, Rihem and Oudinet, Ghislain and Adjou, Mohamed and Moussa, Alaeddine and Fouad, Yasser},
title = {Hybrid Vision Navigation with Hierarchical VLM–LLM Decision Making},
journal = {Machines},
year = {2026},
volume = {14},
number = {4},
pages = {435},
doi = {10.3390/machines14040435}
}
EUVIMED