EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PriorNav: Prior Knowledge Enhanced Zero-Shot Goal Navigation via Multi-Step Iterative Reasoning

Wen Liu iD, Xuanshun Zhuang iD, Lei Ma, Zhongliang Deng iD

Sensors · 12.05.2026 · 26 (10) · 3057

DOI: 10.3390/s26103057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.05.2026. Verfasst von Wen Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Zero-shot goal navigation requires an agent to locate targets in unseen environments based on object categories, reference images, or text descriptions, placing high demands on scene understanding and reasoning. Existing methods mainly rely on online observations, modality similarity, or heuristic graph matching, and therefore still struggle with complex target search due to limited use of external knowledge and weak multi-step reasoning. We propose PriorNav, a prior-knowledge-enhanced framework for zero-shot goal navigation. PriorNav learns a unified retrievable knowledge space from semantic, instance, and relational knowledge, maintains a knowledge-enhanced scene graph by fusing retrieved priors with online observations, and performs progressive decision-making through multi-step iterative reasoning across exploration, verification, and approach stages. Experiments on Object-Goal, Image-Instance Goal, and Text-Goal navigation show that PriorNav improves the success rate over the baseline by 3.5%, 13.3%, and 3.5%, respectively, while also outperforming the strongest training-free baselines on all three tasks. Ablation studies further verify the effectiveness of multi-level prior knowledge, scene-graph enhancement, and iterative reasoning. These results show that combining prior knowledge with explicit reasoning is a promising direction for improving zero-shot goal navigation.

Schlagwörter

Stichwörter der Autor:innen

embodied navigationiterative reasoningprior knowledgescene graphzero-shot goal navigation

Autor:innen und Institutionen

  • School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China.

ORCID-Profile: Wen Liu, Xuanshun Zhuang, Zhongliang Deng

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, W., Zhuang, X., Ma, L., & Deng, Z. (2026). PriorNav: Prior Knowledge Enhanced Zero-Shot Goal Navigation via Multi-Step Iterative Reasoning. Sensors, 26(10), 3057. https://doi.org/10.3390/s26103057

Vancouver

Liu W, Zhuang X, Ma L, Deng Z. PriorNav: Prior Knowledge Enhanced Zero-Shot Goal Navigation via Multi-Step Iterative Reasoning. Sensors. 2026;26(10):3057. doi:10.3390/s26103057

BibTeX
@article{Liu2026,
  author = {Liu, Wen and Zhuang, Xuanshun and Ma, Lei and Deng, Zhongliang},
  title = {PriorNav: Prior Knowledge Enhanced Zero-Shot Goal Navigation via Multi-Step Iterative Reasoning},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3057},
  doi = {10.3390/s26103057}
}
Kostenlos starten →