VLN-Game: Vision-Language Equilibrium Search for Zero-Shot Semantic Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Bangguo, Liu, Yuzhen, Han, Lei, Kasaei, Hamidreza, Li, Tingguang, Cao, Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910703322923008
author Yu, Bangguo
Liu, Yuzhen
Han, Lei
Kasaei, Hamidreza
Li, Tingguang
Cao, Ming
author_facet Yu, Bangguo
Liu, Yuzhen
Han, Lei
Kasaei, Hamidreza
Li, Tingguang
Cao, Ming
contents Following human instructions to explore and search for a specified target in an unfamiliar environment is a crucial skill for mobile service robots. Most of the previous works on object goal navigation have typically focused on a single input modality as the target, which may lead to limited consideration of language descriptions containing detailed attributes and spatial relationships. To address this limitation, we propose VLN-Game, a novel zero-shot framework for visual target navigation that can process object names and descriptive language targets effectively. To be more precise, our approach constructs a 3D object-centric spatial map by integrating pre-trained visual-language features with a 3D reconstruction of the physical environment. Then, the framework identifies the most promising areas to explore in search of potential target candidates. A game-theoretic vision language model is employed to determine which target best matches the given language description. Experiments conducted on the Habitat-Matterport 3D (HM3D) dataset demonstrate that the proposed framework achieves state-of-the-art performance in both object goal navigation and language-based navigation tasks. Moreover, we show that VLN-Game can be easily deployed on real-world robots. The success of VLN-Game highlights the promising potential of using game-theoretic methods with compact vision-language models to advance decision-making capabilities in robotic systems. The supplementary video and code can be accessed via the following link: https://sites.google.com/view/vln-game.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11609
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VLN-Game: Vision-Language Equilibrium Search for Zero-Shot Semantic Navigation
Yu, Bangguo
Liu, Yuzhen
Han, Lei
Kasaei, Hamidreza
Li, Tingguang
Cao, Ming
Robotics
Following human instructions to explore and search for a specified target in an unfamiliar environment is a crucial skill for mobile service robots. Most of the previous works on object goal navigation have typically focused on a single input modality as the target, which may lead to limited consideration of language descriptions containing detailed attributes and spatial relationships. To address this limitation, we propose VLN-Game, a novel zero-shot framework for visual target navigation that can process object names and descriptive language targets effectively. To be more precise, our approach constructs a 3D object-centric spatial map by integrating pre-trained visual-language features with a 3D reconstruction of the physical environment. Then, the framework identifies the most promising areas to explore in search of potential target candidates. A game-theoretic vision language model is employed to determine which target best matches the given language description. Experiments conducted on the Habitat-Matterport 3D (HM3D) dataset demonstrate that the proposed framework achieves state-of-the-art performance in both object goal navigation and language-based navigation tasks. Moreover, we show that VLN-Game can be easily deployed on real-world robots. The success of VLN-Game highlights the promising potential of using game-theoretic methods with compact vision-language models to advance decision-making capabilities in robotic systems. The supplementary video and code can be accessed via the following link: https://sites.google.com/view/vln-game.
title VLN-Game: Vision-Language Equilibrium Search for Zero-Shot Semantic Navigation
topic Robotics
url https://arxiv.org/abs/2411.11609