Advances in Embodied Navigation Using Large Language Models: A Survey

TL;DR

This survey reviews how large language models enhance embodied navigation by improving environmental understanding and decision-making, highlighting current models, methodologies, advantages, disadvantages, and future research directions.

Contribution

It provides an exhaustive overview of the integration of LLMs with embodied navigation, summarizing state-of-the-art models, research approaches, and assessing their strengths and weaknesses.

Findings

LLMs significantly improve environmental perception in navigation tasks.

Current models demonstrate robust decision-making capabilities.

Future research will focus on addressing limitations and expanding applications.

Abstract

In recent years, the rapid advancement of Large Language Models (LLMs) such as the Generative Pre-trained Transformer (GPT) has attracted increasing attention due to their potential in a variety of practical applications. The application of LLMs with Embodied Intelligence has emerged as a significant area of focus. Among the myriad applications of LLMs, navigation tasks are particularly noteworthy because they demand a deep understanding of the environment and quick, accurate decision-making. LLMs can augment embodied intelligence systems with sophisticated environmental perception and decision-making support, leveraging their robust language and image-processing capabilities. This article offers an exhaustive summary of the symbiosis between LLMs and embodied intelligence with a focus on navigation. It reviews state-of-the-art models, research methodologies, and assesses the advantages and disadvantages of existing embodied navigation models and datasets. Finally, the article elucidates the role of LLMs in embodied intelligence, based on current research, and forecasts future directions in the field. A comprehensive list of studies in this survey is available at https://github.com/Rongtao-Xu/Awesome-LLM-EN.