Covariance Estimation for Pose Graph Optimization in Visual-Inertial Navigation Systems

doi:10.1109/TIV.2023.3263837

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Covariance Estimation for Pose Graph Optimization in Visual-Inertial Navigation Systems
	Shi, Pengcheng 1,2; Zhu, Zhikai 4; Sun, Shiying 1; Rong, Zheng 3; Zhao, Xiaoguang 1; Tan, Min 1,2
刊名	IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
	2023-06-01
卷号	8 期号:6 页码:3657-3667
关键词	Covariance estimation loop closing pose graph optimization visual-inertial odometry
ISSN号	2379-8858
DOI	10.1109/TIV.2023.3263837
通讯作者	Sun, Shiying(sunshiying2013@ia.ac.cn)
英文摘要	Pose graph optimization helps reduce drift accumulated in pure odometry of visual simultaneous localization and mapping (SLAM) systems by solving a nonlinear least square problem, including both sequential constraints and loop-closing constraints. However, the covariances of all constraints are set to constant matrices or by manual setting. In this paper, we propose a novel approach to approximate covariances of constraints in pose graph optimization to better represent the true uncertainty of the underlying visual-inertial navigation system (VINS) that fuses inertial measurements and visual observations. Specifically, for sequential constraints, we propose to utilize nonlinear factor recovery to optimally extract covariance matrices from the accumulated visual-inertial odometry (VIO). For loop-closing constraints, we propose a dynamic scale estimation method to approximate the scales of the information matrices. To evaluate the effectiveness and robustness of the proposed method, we conduct extensive experiments on public and self-collected datasets in various environments. Results show that our proposed method achieves higher accuracy compared with naively-formulated pose graph optimization adopted by several state-of-the-art visual-inertial navigation systems.
资助项目	Independent Research Project of Medical Engineering Laboratory of Chinese PLA General Hospital[2022SYSZZKY12] ; National Natural Science Foundation of China[62203438] ; National Natural Science Foundation of China[62103410] ; Science and Technology Project of Beijing[Z221100000222015]
WOS关键词	ROBUST ; LOCALIZATION ; VERSATILE ; ODOMETRY ; FILTER ; SLAM
WOS研究方向	Computer Science ; Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001033547600014
资助机构	Independent Research Project of Medical Engineering Laboratory of Chinese PLA General Hospital ; National Natural Science Foundation of China ; Science and Technology Project of Beijing
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53921]
专题	多模态人工智能系统全国重点实验室
通讯作者	Sun, Shiying
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.NIO Inc, Shanghai 201804, Peoples R China
推荐引用方式 GB/T 7714	Shi, Pengcheng,Zhu, Zhikai,Sun, Shiying,et al. Covariance Estimation for Pose Graph Optimization in Visual-Inertial Navigation Systems[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2023,8(6):3657-3667.
APA	Shi, Pengcheng,Zhu, Zhikai,Sun, Shiying,Rong, Zheng,Zhao, Xiaoguang,&Tan, Min.(2023).Covariance Estimation for Pose Graph Optimization in Visual-Inertial Navigation Systems.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,8(6),3657-3667.
MLA	Shi, Pengcheng,et al."Covariance Estimation for Pose Graph Optimization in Visual-Inertial Navigation Systems".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 8.6(2023):3657-3667.