Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qiao, Yanyuan, Lyu, Wenqi, Wang, Hui, Wang, Zixu, Li, Zerui, Zhang, Yuan, Tan, Mingkui, Wu, Qi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912227829743616
author Qiao, Yanyuan
Lyu, Wenqi
Wang, Hui
Wang, Zixu
Li, Zerui
Zhang, Yuan
Tan, Mingkui
Wu, Qi
author_facet Qiao, Yanyuan
Lyu, Wenqi
Wang, Hui
Wang, Zixu
Li, Zerui
Zhang, Yuan
Tan, Mingkui
Wu, Qi
contents Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closed-source large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges related to expensive token costs and potential data breaches in real-world applications. In this work, we introduce Open-Nav, a novel study that explores open-source LLMs for zero-shot VLN in the continuous environment. Open-Nav employs a spatial-temporal chain-of-thought (CoT) reasoning approach to break down tasks into instruction comprehension, progress estimation, and decision-making. It enhances scene perceptions with fine-grained object and spatial knowledge to improve LLM's reasoning in navigation. Our extensive experiments in both simulated and real-world environments demonstrate that Open-Nav achieves competitive performance compared to using closed-source LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18794
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs
Qiao, Yanyuan
Lyu, Wenqi
Wang, Hui
Wang, Zixu
Li, Zerui
Zhang, Yuan
Tan, Mingkui
Wu, Qi
Robotics
Computer Vision and Pattern Recognition
Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closed-source large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges related to expensive token costs and potential data breaches in real-world applications. In this work, we introduce Open-Nav, a novel study that explores open-source LLMs for zero-shot VLN in the continuous environment. Open-Nav employs a spatial-temporal chain-of-thought (CoT) reasoning approach to break down tasks into instruction comprehension, progress estimation, and decision-making. It enhances scene perceptions with fine-grained object and spatial knowledge to improve LLM's reasoning in navigation. Our extensive experiments in both simulated and real-world environments demonstrate that Open-Nav achieves competitive performance compared to using closed-source LLMs.
title Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.18794