arXiv preprint / 视觉语言导航

NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models

作者：Gengze Zhou, Yicong Hong, Qi Wu · 单位：The University of Adelaide, The Australian National University · 会议/期刊：arXiv preprint · 分类：视觉语言导航 · 发布日期：2023

具身智能机器人学习导航
新标签打开 AlphaXiv
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models figure
AlphaXiv 中文概览（可滚动查看）