Knowledge Graph-Driven Reinforcement Learning for Zero-Shot Vision-Language Navigation
Mathematics · 28.04.2026 · 14 (9) · 1485
DOI: 10.3390/math14091485 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 28.04.2026. Verfasst von Ye Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
To address the limitations of zero-shot generalization in Vision-Language Navigation (VLN), this paper proposes a novel knowledge graph-driven reinforcement learning approach. Our method constructs a hierarchical, dynamically updated knowledge graph online during the agent’s real-time interaction with the environment, seamlessly aligning external semantic priors with continuous visual perception. By leveraging a Chain-of-Thought (CoT) prompting mechanism, the agent performs multi-hop reasoning to precisely locate target objects. Furthermore, we design an end-to-end optimized reinforcement learning framework that fuses multi-modal features and employs a task-oriented composite reward function. Extensive experiments in the AI2-THOR simulation environment demonstrate that the proposed method significantly improves navigation success rates in zero-shot settings. The results validate its robust generalization capabilities, particularly for unseen object categories and complex scene layouts.
Zitieren
APA
Zhang, Y., Zhao, Y., Liu, H., Shi, T., Jia, W., & Li, S. (2026). Knowledge Graph-Driven Reinforcement Learning for Zero-Shot Vision-Language Navigation. Mathematics, 14(9), 1485. https://doi.org/10.3390/math14091485
Vancouver
Zhang Y, Zhao Y, Liu H, Shi T, Jia W, Li S. Knowledge Graph-Driven Reinforcement Learning for Zero-Shot Vision-Language Navigation. Mathematics. 2026;14(9):1485. doi:10.3390/math14091485
BibTeX
@article{Zhang2026,
author = {Zhang, Ye and Zhao, Yandong and Liu, He and Shi, Tengfei and Jia, Weitao and Li, Shenghong},
title = {Knowledge Graph-Driven Reinforcement Learning for Zero-Shot Vision-Language Navigation},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {9},
pages = {1485},
doi = {10.3390/math14091485}
}
EUVIMED