Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Nuo, Wang, Wen, Yang, Rong, Qin, Mengjie, Lin, Zheyuan, Song, Wei, Zhang, Chunlong, Gu, Jason, Li, Chao
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.18892
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913329663967232
author Xu, Nuo
Wang, Wen
Yang, Rong
Qin, Mengjie
Lin, Zheyuan
Song, Wei
Zhang, Chunlong
Gu, Jason
Li, Chao
author_facet Xu, Nuo
Wang, Wen
Yang, Rong
Qin, Mengjie
Lin, Zheyuan
Song, Wei
Zhang, Chunlong
Gu, Jason
Li, Chao
contents Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18892
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Aligning Knowledge Graph with Visual Perception for Object-goal Navigation
Xu, Nuo
Wang, Wen
Yang, Rong
Qin, Mengjie
Lin, Zheyuan
Song, Wei
Zhang, Chunlong
Gu, Jason
Li, Chao
Computer Vision and Pattern Recognition
Robotics
Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.
title Aligning Knowledge Graph with Visual Perception for Object-goal Navigation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2402.18892