Asynchronous State Estimation of Simultaneous Ego-motion Estimation and Multiple Object Tracking for LiDAR-Inertial Odometry

被引:12
作者
Lin, Yu-Kai [1 ]
Lin, Wen-Chieh [1 ]
Wang, Chieh-Chih [2 ,3 ]
机构
[1] Natl Yang Ming Chiao Tung Univ, Inst Multimedia Engn, Hsinchu, Taiwan
[2] Natl Yang Ming Chiao Tung Univ, Dept Elect & Comp Engn, Hsinchu, Taiwan
[3] Ind Technol Res Inst, Mech & Mechatron Syst Res Labs, Hsinchu, Taiwan
来源
2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023) | 2023年
关键词
Autonomous driving; SLAM; odometry; multiple object tracking; SIMULTANEOUS LOCALIZATION; ROBUST;
D O I
10.1109/ICRA48891.2023.10161269
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We propose LiDAR-Inertial Odometry via Simultaneous EGo-motion estimation and Multiple Object Tracking (LIO-SEGMOT), an optimization-based odometry approach targeted for dynamic environments. LIO-SEGMOT is formulated as a state estimation approach with asynchronous state update of the odometry and the object tracking. That is, LIO-SEGMOT can provide continuous object tracking results while preserving the keyframe selection mechanism in the odometry system. Meanwhile, a hierarchical criterion is designed to properly couple odometry and object tracking, preventing system instability due to poor detections. We compare LIO-SEGMOT against the baseline model LIO-SAM, a state-of-the-art LIO approach, under dynamic environments of the KITTI raw dataset and the self-collected Hsinchu dataset. The former experiment shows that LIO-SEGMOT obtains an average improvement 1.61% and 5.41% of odometry accuracy in terms of absolute translational and rotational trajectory errors. The latter experiment also indicates that LIO-SEGMOT obtains an average improvement 6.97% and 4.21% of odometry accuracy.
引用
收藏
页码:10616 / 10622
页数:7
相关论文
共 36 条
[1]  
[Anonymous], 2019, I SYMP CONSUM ELECTR, DOI [DOI 10.1109/TCYB.2019.2906497, DOI 10.1109/icce.2019.8662071]
[2]   DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM [J].
Bescos, Berta ;
Campos, Carlos ;
Tardos, Juan D. ;
Neira, Jose .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03) :5191-5198
[3]   Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age [J].
Cadena, Cesar ;
Carlone, Luca ;
Carrillo, Henry ;
Latif, Yasir ;
Scaramuzza, Davide ;
Neira, Jose ;
Reid, Ian ;
Leonard, John J. .
IEEE TRANSACTIONS ON ROBOTICS, 2016, 32 (06) :1309-1332
[4]  
Forster C., 2015, Robotics: Science and Systems, V11
[5]  
Geiger A., 2012, 2012 IEEE C COMP VIS
[6]   Dynamic SLAM: The Need For Speed [J].
Henein, Mina ;
Zhang, Jun ;
Mahony, Robert ;
Ila, Viorela .
2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, :2123-2129
[7]  
Hsiao M, 2019, IEEE INT CONF ROBOT, P1274, DOI [10.1109/icra.2019.8793854, 10.1109/ICRA.2019.8793854]
[8]   ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings [J].
Huang, Jiahui ;
Yang, Sheng ;
Mu, Tai-Jiang ;
Hu, Shi-Min .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :2165-2174
[9]   ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation [J].
Huang, Jiahui ;
Yang, Sheng ;
Zhao, Zishuo ;
Lai, Yu-Kun ;
Hu, Shi-Min .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :5874-5883
[10]  
Judd KM, 2018, IEEE INT C INT ROBOT, P3949, DOI 10.1109/IROS.2018.8594213