Motion control along a program trajectory using a neural network

The paper examines the creation of a hardware and software prototype of an unmanned vehicle and testing its hardware and software architecture in an attempt to create a universal standard solution for this type of device. The problem of controlling a drone is considered in such a way that it is possible to flexibly switch the sources of control commands and control algorithms. For this purpose, the subsystems for generating and executing control commands are proposed to be connected via a message queue. It is makes possible to combine autonomous and manual controlled modes of operation of the drone. A method for generating control commands when an object follows a program trajectory, based on a neural network, is proposed. The input data of the network are the coordinates of the program trajectory and the current state of the object, and the output data are control actions. The paper describes the hardware and software components of an automobile-type device, the architecture of its control system, the architecture of a neural network, and possible approaches to its training. The creation of a training set using both simulated and real traffic data is discussed, which allows the self-driving device to “learn” different driving styles. The results of experiments with various training samples are presented, which demonstrate the practical applicability of the proposed control method. Attention is paid to aspects of the neural network structure, including the choice of the number of layers and neurons. The possibility of using “intermediate” points of the program trajectory to improve the properties of the object’s movement is indicated. In general, it is concluded that the use of neural networks is promising in the control of drones, in cases where combining and flexible switching of control algorithms is required.

1. Korobeev A.I., Chuchaev A.I. Unmanned vehicles: new challenges to public security. Lex Russica (Russkii zakon). 2019;(2):9–28. DOI: 10.17803/1729-5920.2019.147.2.009-028. (In Russ.).

2. Kulyagina E.A., Skoropupova A.V. Digital logistics: prospects and development problems in Russia. Ustoichivoe ekonomicheskoe razvitie: problemy i perspektivy. 2022:140–144. (In Russ.).

3. Pokusaev O.N., Kupriyanovskii V.P., Kattsyn D.V., Namiot D.E. On ontology and security of autonomous (driverless) cars. International Journal of Open Information Technologies. 2019;7(2):81–93. (In Russ.).

4. Gusev S.I., Epifanov V.V. Problems of introduction of unmanned vehicles in the economic environment. Vestnik Ul'yanovskogo gosudarstvennogo tekhnicheskogo universiteta = Bulletin of the Ulyanovsk State Technical University. 2021;(1):44–49. (In Russ.).

5. Kisulenko B.V. Safety of automated/autonomous vehicles and its assessment before permission for operation. Avtomobil'naya promyshlennost'. 2022;(2):7–13. (In Russ.).

6. Bondarev A.N., Kirichek R.V. Overview of unmanned aerial apparatus for general use and regulation of air UAV movement in different countries. Informatsionnye tekhnologii i telekommunikatsii = Telecom IT. 2016;4(4):13–23. (In Russ.).

7. Afonin I.L, Ievlev K.V., Atyashkin D.V. Identification system of civil unmanned aerial vehicles. Sovremennye problemy radioelektroniki i telekommunikatsii. 2019;(2):41. (In Russ.).

8. Merkulov G.A., Pavlova N.V. Program-algorithmic security of the board computer complex of below flight vehicle civilian appointment appointment. Avtomatizatsiya i IT v energetike. 2017;(8):26–33. (In Russ.).

9. Matyukha S.V. Analysis of the prospects for the use of unmanned aerial vehicles in air transportation. Transportnoe delo Rossii = Transport business of Russia. 2021;(3):26–27. DOI: 10.52375/20728689_2021_3_26. (In Russ.).

10. Popov A.S., Usmonov E.M., Sukhachev N.V. Method of navigation of unmanned aerial vehicles based on technical vision system. Transport: nauka, tekhnika, upravlenie. Nauchnyi informatsionnyi sbornik = Transport: science, equipment, management. Scientific Information Collection. 2022;(2):11–19. DOI: 10.36535/0236-1914-2022-02-2. (In Russ.).

11. Kirillova M.A., Rozhko A.I. Prospects of development of unmanned ships in Russian Federation. Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Morskaya tekhnika i tekhnologiya. 2020;(3):16–22. DOI: 10.24143/2073-1574-2020-3-16-22. (In Russ.).

12. Epikhin A.I., Ignatenko A.V., Studenikin D.E., Khekert E.V. Trends, prospects and technologies for modern and cutting-edge power plants within maritime industry incorporating aspects of autonomous shipping. Ekspluatatsiya morskogo transporta. 2021;(1):88–96. DOI: 10.34046/aumsuomt98/14. (In Russ.).

13. Ardel'yanov N.P. Intermediate results of the e-navigation concept. Vestnik gosudarstvennogo morskogo universiteta imeni admirala F.F. Ushakova. 2022;(2):8–11. (In Russ.).

14. Rivkin B.S. E-navigation: 5 years later. Giroskopiya i navigatsiya = Gyroscopy and Navigation. 2020;28(1):101–120. DOI: 10.17285/0869-7035.0026. (In Russ.).

15. Korenev A.S., Khabarov S.P., Shpektorov A.G. A route calculation for unmanned vessel. Morskie intellektual'nye tekhnologii = Marine intelligent technologies. 2021;(4-1):158–165. DOI: 10.37220/MIT.2021.54.4.047. (In Russ.).

16. Dyda A.A., Pushkarev I.I., Chumakova K.N. Static obstacles avoidance algorithm for unmanned ship. Vestnik gosudarstvennogo universiteta morskogo i rechnogo flota im. admirala S.O. Makarova. 2021;13(3):307–315. DOI: 10.21821/2309-5180-2021-13-3-307-315. (In Russ.).

17. Thomas A.J., Petridis M., Walters S.D., Gheytassi S.M., Morgan R.E. Two Hidden Layers are Usually Better than One. Engineering Applications of Neural Networks. Communications in Computer and Information Science. 2017;744;279-290. DOI: 10.1007/978-3-319-65172-9_24. (In Eng.).

18. Chu Y., Fei J., Hou S. Adaptive Global Sliding-Mode Control for Dynamic Systems Using Double Hidden Layer Recurrent Neural Network Structure. IEEE Transactions on Neural Networks and Learning Systems. 2020;31(4);1297–1309. DOI: 10.1109/TNNLS.2019.2919676. (In Eng.).

19. Jia C., Kong D., Du L. Recursive Terminal Sliding-Mode Control Method for Nonlinear System Based on Double Hidden Layer Fuzzy Emotional Recurrent Neural Network. IEEE Access. 2022;10;118012–118023. DOI: 10.1109/ACCESS.2022.3220800. (In Eng.).

20. Grinyak V.M., Devyatisil'nyi A.S., Lyul'ko V.I., Tsybanov P.A. Indoor positioning system based on bluetooth beacons. Modelirovanie, optimizatsiya i informatsionnye tekhnologii = Modeling, optimization and information technology. 2018;6(2):132–143. URL: https://moit.vivt.ru/wp-content/uploads/2018/04/GrinyakSoavtori_2_18_1.pdf. (In Russ.).

21. Dyda A.A., Nguen V.T., Os'kin D.A. Ship course control system with compensation of external disturbance on steering gear. Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Morskaya tekhnika i tekhnologiya. 2021;(4):34–42. DOI: 10.24143/2073-1574-2021-4-34-42. (In Russ.).