摘要: Recently, with the advances in Large Language Models (LLMs), robot navigation models have demonstrated superior generalization capabilities, including environment perception, decision-making, reasoning, planning, instruction understanding, and human-robot interaction.In this paper, we systematically review recent LLM-based robot navigation research papers, categorizing existing studies into a novel taxonomy comprising perception, planning, control, interaction, and coordination.We also present an overview of the principal datasets and metrics used in robot navigation, analyzing the distinctive characteristics of the datasets and the performance of the main LLMs-based methods.Furthermore, we discuss the challenges hindering the integration of LLMs into robot navigation and provide opportunities and potential directions for future development.
-
来自:
潘昊天
-
分类:
计算机科学
>>
计算机科学技术其他学科
-
投稿状态:
正在评审中
-
引用:
ChinaXiv:202503.00046
(或此版本
ChinaXiv:202503.00046V1)
DOI:10.12074/202503.00046
CSTR:32003.36.ChinaXiv.202503.00046
-
科创链TXID:
8a92d0b4-4386-406c-a4ac-abfd1703e4b1
- 推荐引用方式:
Haotian Pan,Shibo Huang,Jian Yang,Jinpeng Mi,Ke Li,Xiong You,Xuan Tang,Peidong Liang,Jinbo Yang,Yingjie Liu,Jianfeng Zhang,Muyu Wang,Jie Yang,Xinyu Zhang,Lijun Zhao,Mingsong Chen,Jie Zhou,Xian Wei.Recent Advances in Robotic Navigation via Large Language Models.中国科学院科技论文预发布平台.[DOI:10.12074/202503.00046]
(点此复制)