Design and Implementation of Efficient SLAM System Based on Multi-Sensor Fusion

Shaohui Wang; Fei Li

doi:10.54097/hbb73g96

Authors

Shaohui Wang
Fei Li

DOI:

https://doi.org/10.54097/hbb73g96

Keywords:

Multi-sensor fusion, SLAM technology, ICP algorithm, Mobile robot, Stereo camera, LiDAR

Abstract

In Simultaneous Localization and Mapping (SLAM) algorithms, the robustness of single sensors is relatively poor. To address this issue, this study develops a multi-sensor fusion platform that integrates data from LiDAR, stereo cameras, and IMUs, and employs advanced algorithms such as ORB-SLAM2 and Cartographer for efficient data processing and map construction. For point cloud data, we apply the Iterative Closest Point (ICP) algorithm for point-to-point optimization, effectively solving the issue of large map accumulation errors in traditional LiDAR-based SLAM algorithms, which rely solely on odometry for estimating the robot's pose. By using publicly available datasets and conducting multiple map construction experiments in a real campus environment, the proposed method's effectiveness and feasibility are validated, significantly reducing error accumulation and producing more accurate localization and map construction results.

Downloads

Download data is not yet available.

References

[1] Tian Y, Chen H W, Wang F S, et al. A Survey of SLAM Algorithms for Indoor Mobile Robots [J]. Computer Science, 2021, 48 (9): 223-234.

[2] YU Yang, Research on indoor localization and autonomous navigation method of mobile Robot based on laser radar [D]. Harbin: Harbin University of Commerce, 2023.

[3] SHEN Sijie, Tian Xin, WEI Guoliang, et al. Review of SLAM algorithm based on 2D lidar [J]. Computer Technology and Development, 2012, 32 (1): 13-18+46.

[4] Mur-Artal, R., & Tardós, J. D. (2017). ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras. IEEE Transactions on Robotics, 33(5), 1255-1262.

[5] Saldaña, M., et al. (2018). Industrial mobile robot navigation using SLAM-based localization and mapping techniques. Industrial Robot: An International Journal, 45(1), 76-87.

[6] Engel, J., Schöps, T., & Cremers, D. (2014). LSD-SLAM: Large-Scale Direct Monocular SLAM. European Conference on Computer Vision (ECCV), 834-849.

[7] LIU Mingqin, ZHANG Xiaoguang, XU Guiyun, et al. Review on the development of single-robot SLAM technology and related mainstream technologies U]. Computer Engineering and Application, 2020, 56 (18): 25-35.

[8] WANG Xia, ZUO Yifan, Research progress of Visual SLAM [U]. Journal of Intelligent Systems, 2020, 15 (5): 825-834.

[9] Zhang Z K. Design and research of indoor 3D reconstruction and SLAM system based on binocular vision [D]. Guangdong University of Technology, 2020

[10] Kümmerle, R., & Grisetti, G. (2013). A consistent multi-sensor fusion approach for large-scale SLAM. International Journal of Robotics Research, 32(4), 432-451.

[11] Peng Zhen, SAN Hongjun, Li Chunlei, et al. Indoor SLAM based on multi-sensor fusion [J]. Computer Engineering and Design, 2024, 45 (10): 3136-3142.

[12] Zhao Jinjian, Liu Beilei, Zhao Yong. Research on image recognition and target detection based on multi-sensor fusion [J]. Wireless Internet Technology, 2024, 21 (18): 31-34.

[13] Chen Xiangyuan. Research on 3D Mapping of complex roadway Topography based on multi-sensor Information Fusion [J]. Chinese Journal of Construction Machinery, 2024, 22 (5): 673-674.

[14] Zhang Yu, Tan Zu-Bing, CAO Dong-pu, et al. Summary of Research on Key Closing Technology of Range Meter Based on Vision and Inertial Measurement Unit [J]. Chinese Journal of Mechanical Engineering, 2024, 60 (10): 3-21. ZHANG Y, TAN Z B, CAO D P, et al. Survey on key techniquesfor visual and inertial based odomety [J]. Journal of MechanicalEngineering, 2024, 60(10): 3-21.

[15] ENGEL J, SCHOPS T, CREMERS D. LSD-SLAM: Large-scale direct monocular SLAM[C]//European Conference onComputer Vision. Cham, Switzerland: Springer, 2014: 834-849.

[16] Li B. GP-SLAM: a new simultaneous localization and mapping algorithm based on lidar [D]. Zhejiang University, 2020.

[17] He J, LIU X Y. Ground obstacle detection technology based on RGB-D and inertial sensor fusion [J]. Journal of Computer Aided Design and Computer Graphics, 2022, 34(2): 254-263.

[18] YUN S, TING W, SHILIANG S, et al. GR-LOAM:LiDAR-based sensor fusion SLAM for ground robots on complex terrain [J]. Robotics and Autonomous Systems, 2021, 140(5):103759.

[19] CHEN Mingyou, TANG Yunchao, ZOU Xiangjun, et al. 3D global mapping of large-scale unstructured orchard integrating eye in-hand stereo vision and SLAM [J]. Computers and Electronics in Agriculture, 2021, 187:106237.

[20] QIN T, LI P L, SHEN S J. VINS-Mono: A robust and versatilemonocular visual-inertial state estimator [J]. IEEE Transactionson Robotics, 2018, 34(4): 1004-1020.

[21] LIU Zhenyang, LIU Pei, LI Yuwen, et al. 3D mapping algorithm of indoor environment based on 2D laser and TOF camera [J]. Industrial Control Computer, 2022, 35 (9): 24-26

[22] Research on Indoor Robot Mapping and Navigation Based on Multi-sensor Fusion in High School [D]. Yinchuan: Ningxia University, 2021.

[23] Li Jiao. Research on Spatio-temporal Registration and Performance Evaluation of Multi-platform Multi-sensor Multi-source Information Fusion System [D]. Northwestern Polytechnical University, 2003.

[24] Dissanayake, G., Nikolic, S., & Durrant-Whyte, H. (2001). A solution to the simultaneous localization and map building (SLAM) problem. IEEE Transactions on Robotics and Automation, 17(3), 229-241.

[25] Mur-Artal, R., & Tardós, J. D. (2017). ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras. IEEE Transactions on Robotics, 33(5), 1255-1262.

[26] Zhang, W., & Liu, M. (2018). Adaptive sensor fusion for mobile robot localization. International Journal of Robotics Research, 37(10), 1249-1265.

[27] Zeng Xianglei. Research on 3D Point Cloud Registration Algorithm Based on Geometric Features [D]. Jinan: Shandong University, 2020.