ChatNav: Leveraging LLM to Zero-Shot Semantic Reasoning in Object Navigation
IEEE Transactions on Circuits and Systems for Video Technology · 2025-03 · 35 (3) · 2369-2381
DOI: 10.1109/tcsvt.2024.3485907 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-03. Verfasst von Yong Zhu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Zhejiang Provincial Natural Science Foundation of Major Program.
Abstract (Originalsprache)
In object goal navigation tasks, the robot’s understanding of semantic relationships in the environment is a key factor in its ability to localize target objects. Previously, learning-based methods trained robots using 3D scene datasets to learn semantic relationships. However, these approaches perform poorly in new environments with unfamiliar semantic contexts. In this paper, we propose ChatNav which leverages the powerful knowledge summarizing and reasoning capabilities of a Large Language Model (LLM) for zero-shot inference of explicit semantic relationships. These relationships are further integrated into the navigation system for efficient localization of target objects. ChatNav employs a spatial object clustering algorithm to collect semantic clues and designs common-sense-based prompts for interacting with LLM. It then uses a gravity-repulsion model to convert inference results into heuristic factors for robust navigation decision-making. Our approach requires no additional training and can consistently obtain accurate semantic relationships from LLM, making it well-suited for navigating unknown environments. Experimental results demonstrate the outstanding navigation performance of our proposed method on the Gibson and HM3D datasets, surpassing the current state-of-the-art object goal navigation methods.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Zhejiang Provincial Natural Science Foundation of Major Program
Zitieren
APA
Zhu, Y., Wen, Z., Li, X., Shi, X., Wu, X., Dong, H., & Chen, J. (2025). ChatNav: Leveraging LLM to Zero-Shot Semantic Reasoning in Object Navigation. IEEE Transactions on Circuits and Systems for Video Technology, 35(3), 2369-2381. https://doi.org/10.1109/tcsvt.2024.3485907
Vancouver
Zhu Y, Wen Z, Li X, Shi X, Wu X, Dong H, et al. ChatNav: Leveraging LLM to Zero-Shot Semantic Reasoning in Object Navigation. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(3):2369-2381. doi:10.1109/tcsvt.2024.3485907
BibTeX
@article{Zhu2025,
author = {Zhu, Yong and Wen, Zhenyu and Li, Xiong and Shi, Xiufang and Wu, Xiang and Dong, Hui and Chen, Jiming},
title = {ChatNav: Leveraging LLM to Zero-Shot Semantic Reasoning in Object Navigation},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {3},
pages = {2369--2381},
doi = {10.1109/tcsvt.2024.3485907}
}
EUVIMED