Multi-Object Navigation Using Potential Target Position Policy Function

doi:10.1109/TIP.2023.3263110

	Multi-Object Navigation Using Potential Target Position Policy Function
	Zeng, Haitao; Song, Xinhang; Jiang, Shuqiang
	2023
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	32 页码:2608-2619
摘要	Visual object navigation is an essential task of embodied AI, which is letting the agent navigate to the goal object under the user's demand. Previous methods often focus on single-object navigation. However, in real life, human demands are generally continuous and multiple, requiring the agent to implement multiple tasks in sequence. These demands can be addressed by repeatedly performing previous single task methods. However, by dividing multiple tasks into several independent tasks to perform, without the global optimization between different tasks, the agents' trajectories may overlap, reducing the efficiency of navigation. In this paper, we propose an efficient reinforcement learning framework with a hybrid policy for multi-object navigation, aiming to maximally eliminate noneffective actions. First, the visual observations are embedded to detect the semantic entities (such as objects). And the detected objects are memorized and projected into semantic maps, which can also be regarded as a long-term memory of the observed environment. Then a hybrid policy consisting of exploration and long-term planning strategies is proposed to predict the potential target position. In particular, when the target is directly oriented, the policy function makes long-term planning for the target based on the semantic map, which is implemented by a sequence of motion actions. In the alternative, when the target is not oriented, the policy function estimates an object's potential position toward exploring the most possible objects (positions) that have close relations to the target. The relation between different objects is obtained with prior knowledge, which is used to predict the potential target position by integrating with the memorized semantic map. And then a path to the potential target is planned by the policy function. We evaluate our proposed method on two large-scale 3D realistic environment datasets, Gibson and Matterport3D, and the experimental results demonstrate the effectiveness and generalization of the proposed method.
关键词	Navigation Task analysis Semantics Visualization Reinforcement learning Trajectory Three-dimensional displays Multi-object navigation object navigation embodied AI
DOI	10.1109/TIP.2023.3263110
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Project of New Generation Artificial Intelligence of China[2018AAA0102500] ; 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[U1936203] ; Beijing Natural Science Foundation[Z190020] ; Beijing Natural Science Foundation[JQ22012] ; National Postdoctoral Program for Innovative Talents[BX201700255]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000982402100010
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21416
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	Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Haitao,Song, Xinhang,Jiang, Shuqiang. Multi-Object Navigation Using Potential Target Position Policy Function[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2023,32:2608-2619.
APA	Zeng, Haitao,Song, Xinhang,&Jiang, Shuqiang.(2023).Multi-Object Navigation Using Potential Target Position Policy Function.IEEE TRANSACTIONS ON IMAGE PROCESSING,32,2608-2619.
MLA	Zeng, Haitao,et al."Multi-Object Navigation Using Potential Target Position Policy Function".IEEE TRANSACTIONS ON IMAGE PROCESSING 32(2023):2608-2619.