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

研究成果: Conference contribution同行評審

3 引文 斯高帕斯(Scopus)

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.

原文English
主出版物標題Proceedings - ICRA 2023
主出版物子標題IEEE International Conference on Robotics and Automation
發行者Institute of Electrical and Electronics Engineers Inc.
頁面10616-10622
頁數7
ISBN(電子)9798350323658
DOIs
出版狀態Published - 2023
事件2023 IEEE International Conference on Robotics and Automation, ICRA 2023 - London, United Kingdom
持續時間: 29 5月 20232 6月 2023

出版系列

名字Proceedings - IEEE International Conference on Robotics and Automation
2023-May
ISSN(列印)1050-4729

Conference

Conference2023 IEEE International Conference on Robotics and Automation, ICRA 2023
國家/地區United Kingdom
城市London
期間29/05/232/06/23

指紋

深入研究「Asynchronous State Estimation of Simultaneous Ego-motion Estimation and Multiple Object Tracking for LiDAR-Inertial Odometry」主題。共同形成了獨特的指紋。

引用此