Switch-SLAM: Switching-Based LiDAR-Inertial-Visual SLAM for Degenerate Environments

被引:16
作者
Lee, Junwoon [1 ]
Komatsu, Ren [2 ]
Shinozaki, Mitsuru [3 ,4 ]
Kitajima, Toshihiro [4 ]
Asama, Hajime [2 ]
An, Qi [1 ]
Yamashita, Atsushi [1 ]
机构
[1] Univ Tokyo, Grad Sch Fron tier Sci, Dept Human & Engn Environm Studies, Chiba 2778563, Japan
[2] Univ Tokyo, Grad Sch Engn, Dept Precis Engn, Tokyo 1138656, Japan
[3] KUBOTA Corp, Technol Innovat R&D Dept 2, Res & Dev Headquarters, Osaka 5900908, Japan
[4] KUBOTA Corp, Technol Innovat R&D Dept, Res & Dev Headquarters, Osaka 5900908, Japan
关键词
Laser radar; Switches; Odometry; Simultaneous localization and mapping; Visualization; Visual odometry; Optimization; SLAM; sensor fusion; localization; LiDAR degeneracy; harsh environment; REAL-TIME; ROBUST; VERSATILE; ODOMETRY;
D O I
10.1109/LRA.2024.3421792
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
This letter presents Switch-SLAM, switching-based LiDAR-inertial-visual SLAM for degenerate environments, designed to tackle the challenges in degenerate environments for LiDAR and visual SLAM. Switch-SLAM achieves high robustness and accuracy by utilizing a switching structure that transitions from LiDAR to visual odometry when degeneration of LiDAR odometry is detected. To efficiently detect degeneration, Switch-SLAM incorporates a non-heuristic degeneracy detection method that does not require heuristic tuning and demonstrates generalizability across various environments. Switch-SLAM is evaluated on diverse datasets containing both LiDAR and visual odometry degeneracy scenarios. The experimental results highlight the accurate and robust localization by the proposed method in multiple challenging environments with either LiDAR or visual SLAM degeneracy.
引用
收藏
页码:7270 / 7277
页数:8
相关论文
共 33 条
[1]  
[Anonymous], 1900, Mag. J. Sci., V50, P157
[2]  
Benaych-Georges F, 2018, Arxiv, DOI arXiv:1601.04055
[3]   A METHOD FOR REGISTRATION OF 3-D SHAPES [J].
BESL, PJ ;
MCKAY, ND .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) :239-256
[4]   Square Root Marginalization for Sliding-Window Bundle Adjustment [J].
Demmel, Nikolaus ;
Schubert, David ;
Sommer, Christiane ;
Cremers, Daniel ;
Usenko, Vladyslav .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :13240-13248
[5]   LSD-SLAM: Large-Scale Direct Monocular SLAM [J].
Engel, Jakob ;
Schoeps, Thomas ;
Cremers, Daniel .
COMPUTER VISION - ECCV 2014, PT II, 2014, 8690 :834-849
[6]   On-Manifold Preintegration for Real-Time Visual-Inertial Odometry [J].
Forster, Christian ;
Carlone, Luca ;
Dellaert, Frank ;
Scaramuzza, Davide .
IEEE TRANSACTIONS ON ROBOTICS, 2017, 33 (01) :1-21
[7]   Geometrically stable sampling for the ICP algorithm [J].
Gelfand, N ;
Ikemoto, L ;
Rusinkiewicz, S ;
Levoy, M .
FOURTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, 2003, :260-267
[8]   Integrating generic sensor fusion algorithms with sound state representations through encapsulation of manifolds [J].
Hertzberg, Christoph ;
Wagner, Rene ;
Frese, Udo ;
Schroeder, Lutz .
INFORMATION FUSION, 2013, 14 (01) :57-77
[9]   iSAM2: Incremental smoothing and mapping using the Bayes tree [J].
Kaess, Michael ;
Johannsson, Hordur ;
Roberts, Richard ;
Ila, Viorela ;
Leonard, John J. ;
Dellaert, Frank .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2012, 31 (02) :216-235
[10]  
Kim G, 2018, IEEE INT C INT ROBOT, P4802, DOI 10.1109/IROS.2018.8593953