Lidar odometry and mapping method based on multi-structure semantic features

被引：0
|
作者：
Lyu P. [1 ]
Wang Y. [1 ]
Fang W. [1 ]
Lai J. [1 ]
Yu W. [1 ]
机构：
[1] Navigation Research Center, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing
来源：
Zhongguo Guanxing Jishu Xuebao/Journal of Chinese Inertial Technology | 2023年 / 31卷 / 12期
关键词：
feature matching; lidar; map update; structural semantic feature;
D O I：
10.13695/j.cnki.12-1222/o3.2023.12.007
中图分类号：
学科分类号：
摘要：
At present, point, line, surface features or single structural semantic features are usually used in lidar odometry algorithms, and the matching accuracy is susceptible to be interfered in scenes with sparse features. To solve this problem, a lidar odometry and mapping method based on multi-structure semantic features is proposed. Firstly, a grid-based multi-structure semantic feature extraction method is proposed to effectively extract the cylinder, ground and plane features. Secondly, the matching cost functions are constructed for the three types of semantic features to realize the joint matching of multi-semantic features. Thirdly, the parametric description models of the three types of semantic features are established, and incremental map storage and update methods are designed. Finally, indoor and outdoor experiments are carried out and compared with A-LOAM, LEGO-LOAM, LIO-SAM, FAST-LIO, SLOAM and other algorithms. The experimental results show that compared with the above algorithms, the positioning accuracy of the proposed algorithm is improved by more than 15% and 5% in outdoor and indoor environment, respectively. © 2023 Editorial Department of Journal of Chinese Inertial Technology. All rights reserved.
引用
收藏
页码：1210 / 1219
页数：9
相关论文
共 20 条
  • [1] Zhang J, Singh S., LOAM: Lidar odometry and mapping in real-time, Robotics: Science and Systems, pp. 1-9, (2014)
  • [2] Shan T, Englot B., Lego-LOAM: Lightweight and ground-optimized lidar odometry and mapping on variable terrain, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4758-4765, (2018)
  • [3] Shan T, Englot B, Meyers D, Et al., LIO-SAM: Tightly-coupled lidar inertial odometry via smoothing and mapping, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5135-5142, (2020)
  • [4] Xu W, Zhang F., FAST-LIO: A fast, robust lidar-inertial odometry package by tightly-coupled iterated Kalman filter, IEEE Robotics and Automation Letters, 6, 2, pp. 3317-3324, (2021)
  • [5] Wang Z, Li S, Cao M, Et al., Pole-like objects mapping and long-term robot localization in dynamic urban scenarios, 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 998-1003, (2021)
  • [6] Zhou L, Huang G, Mao Y, Et al., PLC-LiSLAM: LiDAR SLAM with planes, lines, and cylinders, IEEE Robotics and Automation Letters, 7, 3, pp. 7163-7170, (2022)
  • [7] Proenca P F, Gao Y., Fast cylinder and plane extraction from depth cameras for visual odometry, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6813-6820, (2018)
  • [8] Chen S W, Nardari G V, Lee E S, Et al., SLOAM: Semantic lidar odometry and mapping for forest inventory, IEEE Robotics and Automation Letters, 5, 2, pp. 612-619, (2020)
  • [9] Zheng B, Liu Q, Zhao F, Et al., Loop detection and semantic mapping algorithm fused with semantic information, Journal of Chinese Inertial Technology, 28, pp. 629-637, (2020)
  • [10] Wang Y, Jin Y, Zhang Y, Et al., Structured road obstacle detection method based on lidar, Journal of Chinese Inertial Technology, 31, pp. 593-601, (2023)
12