Feature Scan Context aided Lidar-IMU Simultaneously Localization and Mapping

Yan Wen, Lijin Han, Ying Li, Sihao Lin, Shida Nie, Xiaohui Jiang

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Precise simultaneously localization and mapping is necessary to self-driving cars. In this paper, we present a SLAM system fusing with lidar and IMU data. Considering that pose initial value is a key problem for point cloud ICP alignment, we propose a method using the Extended Kalman Filter to combine initial yaw value obtained by feature scan context with the preintegrated IMU estimation value, aiming to improve the initial yaw value of the vehicle. In addition, we adopt the feature scan context to the loop closure, which is beneficial to the whole SLAM system to reduce the accumulative errors. Sufficient experiments are carried out in outdoor environment. The results show that our method acquires significant superior performance comparing with other two main current lidar SLAM systems-LIO-SAM and LeGo-Loam.

源语言英语
主期刊名Proceedings of the 2023 7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9798350340488
DOI
出版状态已出版 - 2023
活动7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023 - Changsha, 中国
期限: 27 10月 202329 10月 2023

出版系列

姓名Proceedings of the 2023 7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023

会议

会议7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023
国家/地区中国
Changsha
时期27/10/2329/10/23

指纹

探究 'Feature Scan Context aided Lidar-IMU Simultaneously Localization and Mapping' 的科研主题。它们共同构成独一无二的指纹。

引用此