SIMULTANEOUS LOCALIZATION AND MAPPING METHOD OF DYNAMIC ENVIRONMENT FOR UNMANNED SYSTEMS

DOI: 10.31673/2786-8362.2025.013241

Abstract

This paper is devoted to the study of simultaneous localization and mapping (SLAM)
methods for unmanned systems operating in complex and dynamic environments. The paper considers the
challenges associated with the need to adapt to environmental changes. The use of the Kalman filter and its
extended versions is proposed, in particular with optimization using nonlinear programming methods. The
obtained scientific results include the optimization of the Kalman filter taking into account nonlinearities
using nonlinear programming methods, as well as the integration of classical computer vision algorithms
(ORB) with convolutional neural networks. To achieve these results, the tasks of analyzing existing SLAM
methods, developing new adaptive localization algorithms, and their experimental verification on existing
datasets were solved. The results obtained can be recommended for use in projects on autonomous
navigation of unmanned ground and air platforms, especially in conditions of limited environmental
predictability, such as rescue operations, military missions, automated manufacturing and transportation
systems.
Keywords: SLAM, Kalman filter, dynamic environment, localization, unmanned systems,
convolutional neural networks

References
1. Bailey T., Durrant-Whyte H. Simultaneous localization and mapping (SLAM): part II. IEEE
Robotics & Automation Magazine. 2006. Vol. 13, no. 3. P. 108–117. URL:
https://doi.org/10.1109/mra.2006.1678144.
2. Yarovoi A., Cho Y. K. Review of simultaneous localization and mapping (SLAM) for
construction robotics applications. Automation in Construction. 2024. Vol. 162. P. 105344. URL:
https://doi.org/10.1016/j.autcon.2024.105344.
3. VDO-SLAM: A Visual Dynamic Object-aware SLAM System / J. Zhang et al. URL:
https://arxiv.org/abs/2005.11052.
4. Visual SLAM in dynamic environments based on object detection / Y.-b. Ai et al. Defence
Technology. 2020. URL: https://doi.org/10.1016/j.dt.2020.09.012.
5. Liu Y., Miura J. RDS-SLAM: Real-Time Dynamic SLAM Using Semantic Segmentation
Methods. IEEE Access. 2021. Vol. 9. P. 23772–23785. URL:
https://doi.org/10.1109/access.2021.3050617.
6. Wadud, R. A., & Sun, W. (2022). DyOb-SLAM: Dynamic Object Tracking SLAM System.
arXiv. URL: https://doi.org/10.48550/arXiv.2211.01941.
7. Kim, A., Osep, A., & Leal-Taixe, L. (2021). EagerMOT: 3D Multi-Object Tracking via
Sensor Fusion.
8. Mur-Artal R., Montiel J. M. M., Tardos J. D. ORB-SLAM: A Versatile and Accurate
Monocular SLAM System. IEEE Transactions on Robotics. 2015. Vol. 31, no. 5. P. 1147–1163. URL:
https://doi.org/10.1109/tro.2015.2463671.
9. Applying SLAM Algorithm Based on Nonlinear Optimized Monocular Vision and IMU in
the Positioning Method of Power Inspection Robot in Complex Environment / C. Wang et al.
Mathematical Problems in Engineering. 2022. Vol. 2022. P. 1–14. URL:
https://doi.org/10.1155/2022/3378163.
10. Choi K.-S., Lee S.-G. Enhanced SLAM for a mobile robot using extended Kalman Filter
and neural networks. International Journal of Precision Engineering and Manufacturing. 2010. Vol.
11, no. 2. P. 255–264. URL: https://doi.org/10.1007/s12541-010-0029-9.
11. Liu H. Identifying and updating local optimization methods in extended Kalman filter
SLAM. Applied and Computational Engineering. 2023. Vol. 4, no. 1. P. 569–573. URL:
https://doi.org/10.54254/2755-2721/4/2023325.