Article

Download article

Algorithms for laying of the route of unmanned aerial vehicles based on Hopfield neural networks

M. Musiyenko, Iryna Zhuravska

Abstract

The models, methods and algorithms for laying of the route of unmanned aerial vehicles (UAV) are considered in the paper. Mathematical tools of Hopfield neural networks (HNN) are offered to use for the defined task. A modeling of UAV behavior in MATLAB r2009b environment is carried out. A modified model of the HNN structure (due to the adding of additional module for geographical coordinates analysis) and a mathematical model of laying the optimal route for UAV according to Sudoku principle (by adding additional constraints) are developed. The experiments have proved the adequacy and efficiency of the offered method and developed models for laying of UAV routes

Keywords:

UAV, laying of route, Hopfield neural network, mathematical modeling, MATLAB

Retrieved from Volume 21, No. 1, 2016

Pages 20-27

References Suggested citation

References

  1. Bortoff, S.A. (2000). Path planning for UAVs. In Proceedings of the 2000 American Control Conference (Vol. 1, pp. 364–368).
  2. European Aviation Safety Agency. (2015). Proposal to create common rules for operating drones in Europe, September. Retrieved from https://www.easa.europa.eu/system/files/dfu/205933-01-EASA_Summary%20of%20the%20ANPA.pdf
  3. Federal Aviation Administration Office of the Chief Counsel. (2015). State and local regulation of unmanned aircraft systems (UAS) fact sheet, December 17. Retrieved from https://www.faa.gov/uas/regulations_policies/media/UAS_Fact_Sheet_Final.pdf
  4. Goldman, J. (2016). Drones hit new heights at CES 2016. CNET, Gadgets, January 10. Retrieved from http://www.cnet.com/news/drones-ces-2016/
  5. Guang, Y., & Vikram, K. (2002). Optimal path planning for unmanned air vehicles with kinematic and tactical constraints. In Proceedings of the 41st IEEE Conference on Decision and Control (Vol. 2, pp. 1301–1306).
  6. Hopfield, J.J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79, 2554–2558.
  7. Kojic, N., Reljin, I., & Reljin, B. (2013). Route selection problem based on Hopfield neural network. Radioengineering, 22(4), 1182–1193.
  8. Musiyenko, M.P., Zhuravska, I.M., Kulakovska, I.V., & Kulakovska, A.O. (2016). Simulation of the behavior of robot subswarm in spatial corridors. In Proceedings of the 36th International Conference on Electronics and Nanotechnology (ELNANO-2016), Kyiv.
  9. Pashkevich, A., & Kazheunikau, M. (2005). Neural network approach to trajectory synthesis for robotic manipulators. Journal of Intelligent Manufacturing, 16, 173–187.
  10. Rana, A.S., & Zalzala, A.M.S. (1997). A neural networks based collision detection engine for multi-arm robotic systems. In Proceedings of the 5th International Conference on Artificial Neural Networks, 140–145.
  11. Yan, M. (2016). Dijkstra’s Algorithm (Presentation). Massachusetts Institute of Technology, Department of Mathematics. Retrieved from http://math.mit.edu/~rothvoss/18.304.3PM/Presentations/1-Melissa.pdf

Suggested citation

Musiyenko, M., & Zhuravska, I. (2016). Algorithms for laying of the route of unmanned aerial vehicles based on Hopfield neural networks. Bulletin of Cherkasy State Technological University, 21(1), 20-27.