Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yaoxian, Song, Penglei, Sun, Haoyu, Liu, Zhixu, Li, Wei, Song, Yanghua, Xiao, Xiaofang, Zhou
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913347515973632
author Yaoxian, Song
Penglei, Sun
Haoyu, Liu
Zhixu, Li
Wei, Song
Yanghua, Xiao
Xiaofang, Zhou
author_facet Yaoxian, Song
Penglei, Sun
Haoyu, Liu
Zhixu, Li
Wei, Song
Yanghua, Xiao
Xiaofang, Zhou
contents Embodied AI is one of the most popular studies in artificial intelligence and robotics, which can effectively improve the intelligence of real-world agents (i.e. robots) serving human beings. Scene knowledge is important for an agent to understand the surroundings and make correct decisions in the varied open world. Currently, knowledge base for embodied tasks is missing and most existing work use general knowledge base or pre-trained models to enhance the intelligence of an agent. For conventional knowledge base, it is sparse, insufficient in capacity and cost in data collection. For pre-trained models, they face the uncertainty of knowledge and hard maintenance. To overcome the challenges of scene knowledge, we propose a scene-driven multimodal knowledge graph (Scene-MMKG) construction method combining conventional knowledge engineering and large language models. A unified scene knowledge injection framework is introduced for knowledge representation. To evaluate the advantages of our proposed method, we instantiate Scene-MMKG considering typical indoor robotic functionalities (Manipulation and Mobility), named ManipMob-MMKG. Comparisons in characteristics indicate our instantiated ManipMob-MMKG has broad superiority in data-collection efficiency and knowledge quality. Experimental results on typical embodied tasks show that knowledge-enhanced methods using our instantiated ManipMob-MMKG can improve the performance obviously without re-designing model structures complexly. Our project can be found at https://sites.google.com/view/manipmob-mmkg
format Preprint
id arxiv_https___arxiv_org_abs_2311_03783
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI
Yaoxian, Song
Penglei, Sun
Haoyu, Liu
Zhixu, Li
Wei, Song
Yanghua, Xiao
Xiaofang, Zhou
Artificial Intelligence
Robotics
Symbolic Computation
Embodied AI is one of the most popular studies in artificial intelligence and robotics, which can effectively improve the intelligence of real-world agents (i.e. robots) serving human beings. Scene knowledge is important for an agent to understand the surroundings and make correct decisions in the varied open world. Currently, knowledge base for embodied tasks is missing and most existing work use general knowledge base or pre-trained models to enhance the intelligence of an agent. For conventional knowledge base, it is sparse, insufficient in capacity and cost in data collection. For pre-trained models, they face the uncertainty of knowledge and hard maintenance. To overcome the challenges of scene knowledge, we propose a scene-driven multimodal knowledge graph (Scene-MMKG) construction method combining conventional knowledge engineering and large language models. A unified scene knowledge injection framework is introduced for knowledge representation. To evaluate the advantages of our proposed method, we instantiate Scene-MMKG considering typical indoor robotic functionalities (Manipulation and Mobility), named ManipMob-MMKG. Comparisons in characteristics indicate our instantiated ManipMob-MMKG has broad superiority in data-collection efficiency and knowledge quality. Experimental results on typical embodied tasks show that knowledge-enhanced methods using our instantiated ManipMob-MMKG can improve the performance obviously without re-designing model structures complexly. Our project can be found at https://sites.google.com/view/manipmob-mmkg
title Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI
topic Artificial Intelligence
Robotics
Symbolic Computation
url https://arxiv.org/abs/2311.03783