Artificial intelligence

Scientific journal

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Search by:

Year of publication
Author name
Paper title

Algorithms for UAV localization with Scene Matching

Melnyk Y.1, Lukatskyi Y.1
1 State University of Information and Communication Technologies
melnik_yur@ukr.net; evgeniy.lukatsky@gmail.com
https://orcid.org/0000-0002-5028-8749https://orcid.org/0000-0003-3352-3230

Full text (PDF)

UDC: 004.89 + 623.4
Publication Language: Ukrainian
Stuc. intelekt. 2024; 29(4):173-183

Abstract: This article addresses the issue of unmanned aerial vehicle (UAV) navigation and the application of artificial intelligence (AI) to overcome current challenges. It reviews the historical use of control systems for ballistic and cruise missiles dating back to the 1940s. The shortcomings of existing control systems that rely on inertial systems and the challenges faced in aerial conflict scenarios are identified. The main stages of the navigation process, particularly through image comparison, are outlined. An analysis of existing image comparison methods for navigation purposes using various systems is presented, detailing their advantages and disadvantages and examining the mathematical models underlying these processes. The paper proposes solutions to the challenges faced by existing UAV control methods, specifically by utilizing a sliding window approach to reduce required resources and shorten decision-making time for real-time flight navigation through AI integration.

Keywords: Unmanned aerial vehicles, navigation, control systems, inertial navigation system, dataset, system training, artificial intelligence

References:

  1. Wrigley, W. History of Inertial Navigation. Navigation vol 24, issue 1 Available: URL:https://doi.org/10.1002/j.2161-4296.1977.tb01262.x.
  2. Riedel, F. W., Hall, S. M., Barton, J. D., та ін. (2010). Guidance and Navigation in the Global Engagement Department, Johns Hopkins APL Technical Digest, 29(2), 118–132.
  3. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110.
  4. Bay, H., Tuytelaars, T., & Van Gool, L. (2006). SURF: Speeded up robust features. In European Conference on Computer Vision (pp. 404–417). Springer.
  5. Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011). ORB: An efficient alternative to SIFT or SURF. In 2011 International Conference on Computer Vision (pp. 2564–2571). IEEE.
  6. Lukatskyi, Ye. Vykhidnyi kod prohramy doslidzhennia metodiv vydilennia oznak SIFT, SURF, ORB. Available: https://github.com/Zhekar1998/Article_scene_matching_app.git.

View full text (PDF)