Scale Jump-Aware Pose Graph Relaxation for Monocular SLAM with Re-Initializations

doi:10.1109/IROS55552.2023.10341995

	Scale Jump-Aware Pose Graph Relaxation for Monocular SLAM with Re-Initializations
	Yuan, Runze1 ; Cheng, Ran 2; Liu, Lige 2; Sun, Tao 2; Kneipl, Laurent1
	2023-10-05
会议录名称	2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
ISSN	2153-0858
页码	3445-3452
发表状态	已发表
DOI	10.1109/IROS55552.2023.10341995
摘要	Pose graph relaxation has become an indispensable addition to SLAM enabling efficient global registration of sensor reference frames under the objective of satisfying pair-wise relative transformation constraints. The latter may be given by incremental motion estimation or global place recognition. While the latter case enables loop closures and drift compensation, care has to be taken in the monocular case in which local estimates of structure and displacements can differ from reality not just in terms of noise, but also in terms of a scale factor. Owing to the accumulation of scale propagation errors, this scale factor is drifting over time, hence scale-drift aware pose graph relaxation has been introduced. We extend this idea to cases in which the relative scale between subsequent sensor frames is unknown, a situation that can easily occur if monocular SLAM enters re-initialization and no reliable overlap between successive local maps can be identified. The approach is realized by a hybrid pose graph formulation that combines the regular similarity consistency terms with novel, scale-blind constraints. We apply the technique to the practically relevant case of small indoor service robots capable of effectuating purely rotational displacements, a condition that can easily cause tracking failures. We demonstrate that globally consistent trajectories can be recovered even if multiple re-initializations occur along the loop, and present an in-depth study of success and failure cases. © 2023 IEEE.
关键词	Simultaneous localization and mapping Service robots Motion estimation Optimization methods Cameras Land vehicles Trajectory
会议名称	2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
会议地点	Detroit, MI, USA
会议日期	1-5 Oct. 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20240315412743
EI主题词	Motion estimation
EISSN	2153-0866
EI分类号	731.5 Robotics
原始文献类型	Conference article (CA)
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/349511
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_Laurent Kneip组
作者单位	1.ShanghaiTech University, Mobile Percention Lab, China 2.Midea Robozone, China
第一作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Yuan, Runze,Cheng, Ran,Liu, Lige,et al. Scale Jump-Aware Pose Graph Relaxation for Monocular SLAM with Re-Initializations[C]:Institute of Electrical and Electronics Engineers Inc.,2023:3445-3452.