Large-Scale Model-Enhanced Vision-Language Navigation: Recent Advances, Practical Applications, and Future Challenges
Sensors · 24.03.2026 · 26 (7) · 2022
DOI: 10.3390/s26072022 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 24.03.2026. Verfasst von Zecheng Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 212 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jiangsu Province.
Abstract (Originalsprache)
The ability to autonomously navigate and explore complex 3D environments in a purposeful manner, while integrating visual perception with natural language interaction in a human-like way, represents a longstanding research objective in Artificial Intelligence (AI) and embodied cognition. Vision-Language Navigation (VLN) has evolved from geometry-driven to semantics-driven and, more recently, knowledge-driven approaches. With the introduction of Large Language Models (LLMs) and Vision-Language Models (VLMs), recent methods have achieved substantial improvements in instruction interpretation, cross-modal alignment, and reasoning-based planning. However, existing surveys primarily focus on traditional VLN settings and offer limited coverage of LLM-based VLN, particularly in relation to Sim2Real transfer and edge-oriented deployment. This paper presents a structured review of LLM-enabled VLN, covering four core components: instruction understanding, environment perception, high-level planning, and low-level control. Edge deployment and implementation requirements, datasets, and evaluation protocols are summarized, along with an analysis of task evolution from path-following to goal-oriented and demand-driven navigation. Key challenges, including reasoning complexity, spatial cognition, real-time efficiency, robustness, and Sim2Real adaptation, are examined. Future research directions, such as knowledge-enhanced navigation, multimodal integration, and world-model-based frameworks, are discussed. Overall, LLM-driven VLN is progressing toward deeper cognitive integration, supporting the development of more explainable, generalizable, and deployable embodied navigation systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China.
- The China-UK Centre on Intelligent Mobility, Southeast University, Nanjing 210096, China.
- State Key Laboratory of Comprehensive PNT Network and Equipment Technology, Nanjing 210096, China.
ORCID-Profile: Xiaolin Meng, Xu He
Förderung
- Natural Science Foundation of Jiangsu Province
Zitieren
APA
Li, Z., Meng, X., He, X., Zhang, Y., & Yin, W. (2026). Large-Scale Model-Enhanced Vision-Language Navigation: Recent Advances, Practical Applications, and Future Challenges. Sensors, 26(7), 2022. https://doi.org/10.3390/s26072022
Vancouver
Li Z, Meng X, He X, Zhang Y, Yin W. Large-Scale Model-Enhanced Vision-Language Navigation: Recent Advances, Practical Applications, and Future Challenges. Sensors. 2026;26(7):2022. doi:10.3390/s26072022
BibTeX
@article{Li2026,
author = {Li, Zecheng and Meng, Xiaolin and He, Xu and Zhang, Youdong and Yin, Wenxuan},
title = {Large-Scale Model-Enhanced Vision-Language Navigation: Recent Advances, Practical Applications, and Future Challenges},
journal = {Sensors},
year = {2026},
volume = {26},
number = {7},
pages = {2022},
doi = {10.3390/s26072022}
}
EUVIMED