中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
HOZ plus plus : Versatile Hierarchical Object-to-Zone Graph for Object Navigation

文献类型：期刊论文

作者Zhang, Sixian1,2; Song, Xinhang1,2; Yu, Xinyao1,2; Bai, Yubing1,2; Guo, Xinlong1,2; Li, Weijie1,2; Jiang, Shuqiang1,2
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2025-07-01
卷号47期号:7页码:5958-5975
关键词Navigation Training Visualization Layout Artificial intelligence Semantics Planning Periodic structures Location awareness Three-dimensional displays Embodied AI visual navigation object goal navigation hierarchical knowledge graph
ISSN号0162-8828
DOI10.1109/TPAMI.2025.3552987
英文摘要The goal of object navigation task is to reach the expected objects using visual information in unseen environments. Previous works typically implement deep models as agents that are trained to predict actions based on visual observations. Despite extensive training, agents often fail to make wise decisions when navigating in unseen environments toward invisible targets. In contrast, humans demonstrate a remarkable talent to navigate toward targets even in unseen environments. This superior capability is attributed to the cognitive map in the hippocampus, which enables humans to recall past experiences in similar situations and anticipate future occurrences during navigation. It is also dynamically updated with new observations from unseen environments. The cognitive map equips humans with a wealth of prior knowledge, significantly enhancing their navigation capabilities. Inspired by human navigation mechanisms, we propose the Hierarchical Object-to-Zone (HOZ++) graph, which encapsulates the regularities among objects, zones, and scenes. The HOZ++ graph helps the agent to identify the current zone and the target zone, and computes an optimal path between them, then selects the next zone along the path as the guidance for the agent. Moreover, the HOZ++ graph continuously updates based on real-time observations in new environments, thereby enhancing its adaptability to new environments. Our HOZ++ graph is versatile and can be integrated into existing methods, including end-to-end RL and modular methods. Our method is evaluated across four simulators, including AI2-THOR, RoboTHOR, Gibson, and Matterport 3D. Additionally, we build a realistic environment to evaluate our method in the real world. Experimental results demonstrate the effectiveness and efficiency of our proposed method.
资助项目National Natural Science Foundation of China[62125207] ; National Natural Science Foundation of China[62032022] ; National Natural Science Foundation of China[62272443] ; National Natural Science Foundation of China[U23B2012] ; Beijing Natural Science Foundation[JQ22012] ; Beijing Natural Science Foundation[L242020]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001504146900038
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/42343]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Jiang, Shuqiang
作者单位1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Sixian,Song, Xinhang,Yu, Xinyao,et al. HOZ plus plus : Versatile Hierarchical Object-to-Zone Graph for Object Navigation[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2025,47(7):5958-5975.
APA Zhang, Sixian.,Song, Xinhang.,Yu, Xinyao.,Bai, Yubing.,Guo, Xinlong.,...&Jiang, Shuqiang.(2025).HOZ plus plus : Versatile Hierarchical Object-to-Zone Graph for Object Navigation.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,47(7),5958-5975.
MLA Zhang, Sixian,et al."HOZ plus plus : Versatile Hierarchical Object-to-Zone Graph for Object Navigation".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 47.7(2025):5958-5975.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。