Haotian Pan, Shibo Huang, Jian Yang, Jinpeng Mi, Ke Li, Xiong You, Peidong Liang, Jinbo Yang, Yingjie Liu, Jianfeng Zhang, Muyu Wang, Jie Yang, Xinyu Zhang, Lijun Zhao, Mingsong Chen, Jie Zhou, Xian Wei
Recently, with advances in Large Language Models(LLMs), robot navigation models have demonstrated superior generalization capabilities across environment perception, decision-making, reasoning, planning, instruction understanding, and human-robot interaction. In this article, we systematically review recent LLM-based robot navigation research articles and categorize them into a novel taxonomy comprising perception, planning, control, interaction, and coordination. We also present an overview of the principal datasets, simulations, and metrics used in robot navigation, analyzing the distinctive characteristics of the datasets and the performance of the main LLM-based methods. Furthermore, we discuss the challenges hindering the integration of LLMs into robot navigation and provide opportunities and potential directions for future development.