Artifi cial Intelligence Technologies in the Autonomous Underwater Vehicle Control Systems

The purpose of the paper is to present the experience of developing algorithms implemented in the AUV control system using artificial intelligence (AI) technologies. The author’s view on the content of the concept of AI in relation to the creation of complex technical systems is presented. Two of the most promising, according to the author, AI technologies are identified: 1) development of the basic algorithm and its improvement based on the results of comprehensive modeling in various operating conditions; 2) creation of a problem-oriented artificial neural network and its deep learning using a large amount of experimentally obtained training material. It is stated that both technologies are quite time-consuming and require a long time to implement. But if the completeness and adequacy of modeling of the conditions in which the system being created is supposed to function plays a key role in modeling technology, then in machine learning technology, the availability of a sufficient amount of training material comes to the fore (in the case of developing vision systems — images of recognizable objects, the number of which can number many thousands).The paper presents the structure of the multi-agent control system of AUV, focuses on the complexity of the tasks it solves and the need to use AI technologies in its creation. It is shown that of all the tasks solved by the AUV control system, AI methods are most in demand for solving two categories of tasks: 1) recognition of the current situation and making an adequate decision in this situation in the interests of completing the route task; 2) search for the designated bottom object among many other bottom objects of natural and artificial origin. The use of AI technologies is demonstrated by the example of the development using a specially created simulation stand of the AUV control algorithm when bypassing an extended. It is proposed to solve the problem of detecting and recognizing a designated bottom object using deep learning technology of a problem-oriented artificial neural network with the peculiarity that the training material is formed programmatically in the form of digital images of the desired bottom object at the output of hydroacoustic, optical and electromagnetic means of monitoring the bottom in various conditions of their observation.

1. Inzartsev A. V., Kiselev L. V., Kostenko V. V., Matvienko Yu. V., Pa-vin A. M., Shcherbatyuk A. F. Underwater robotic complexes: systems, technologies, applications, Vladivostok, Dalnauka, 2018, 368 p. (in Russian).

2. Inzartsev A. V. et al. Application of an autonomous uninhabited underwater vehicle for scientific research in the Arctic, Underwater research and robotics, 2007, no. 2(4), pp. 5—14 (in Russian).

3. Millar G., Mackay L., Maneuvering Under the Ice, Sea Technology, 2015, vol. 56, no. 4, pp. 35—38.

4. Apollonov E. M., Bachurin A. A., Gorokhov I., Ponomarev L. O. On the possibility and necessity of creating an ultralarge uninhabited underwater vehicle, Collection of materials of the XIII All-Russian Scientific and Practical Conference "Perspective systems and management tasks", Rostov-on-Don — Taganrog, SFU, 2018, pp. 34—42 (in Russian).

5. Wong K. ed. Jane’s unmanned maritime vehicle, 20192020, IHS Markit, Coulsdon, Surrey, UK, 2020.

6. Illarionov G. Yu., Si denko K. S., Bocharov L. Yu. Threat from the depths: XXI century, Khabarovsk, KGUP "Khabarovsk Regional Printing House", 201 1, 304 p. (in Russian).

7. Kuzmitsky M. A., Gizitdinova M. R. Mobile underwater robots in solving Navy tasks: Modern technologies and prospects, Fundamental and applied hydrophysics, 2011, vol. 4, no. 3, pp. 37—48 (in Russian).

8. Cebrowski A. K., Garstka J. J. Network-centric warfare: its origins and future, U. S. Naval Institute Proceedings, 1998, no. 1.

9. Baulin V., Kondratiev A. Implementation of the concept of "network-centric war" in the US Navy, Foreign Military Review, 2009, no. 6, pp. 61—67 (in Russian).

10. Turing A. Can machines think? Moscow State publishing of physics.-mat. literature, 1960 (in Russian).

11. Turing A. Computing Machinery and Intelligence, Mind, 1950, V. LIX, no. 236. pp. 433—460.

12. What is Artificial Intelligence?, available at: http://wwwformal.stanford.edu/jmc/whatisai/whatisai.html).

13. Artificial intelligence in the USSR, available at: http://ainews.ru/2017/10/iskusstvennyj_intellekt_v_sssr.html) (in Russian).

14. Goodfellow Ya., Benjio I., Courville A. Deep learning, Moscow, DMK Press, 2017, 652 p. (in Russian).

15. Nikolenko S., Kadurin A., Arkhangelskaya E. Deep learning, St. Petersburg, Peter, 2018, 480 p. (in Russian).

16. National strategy for the development of artificial intelligence for the period up to 2030. Approved by Decree of the President of the Russian Federation No. 490, 17 dated October 10, 2019 (in Russian).

17. The concept of development of regulation of relations in the field of artificial intelligence and robotics technologies until 2024. Approved by the Decree of the Government of the Russian Federation dated August 19, 2020, No. 2129-p. (in Russian).

18. Artificial Intelligence Journey, available at: https:// aijourney.ru

19. Newborn M. Deep Blue: An artificial intelligence milestone, Springer, 2003, 346 p.

20. Gorodetsky V. I., Grushin M. S., Khabalov A. V. Multiagent system (review), News of artificial intelligence, 1998, no. 2, pp. 64—116 (in Russian).

21. Rzhevsky G. A., Skobelev P. O. How to manage complex systems? Multi-agent technologies for the creation of intelligent enterprise management systems, Samara, Etching, 2015, 290 p. (in Russian).

22. Innocenti B. A multi-agent distributed coordination with architecture for an Autonomous robot. Ph.D. dissertation, Universitat de Girona, 2009.

23. Boreyko A. A., Inzartsev A. V., Mashoshin A. I., Pavin A. M., Pashkevich I. V. Control system of large-scale autonomous autonomous vehicle based on a multi-agent approach, Underwater research and robotics, 2019, no. 2 (28), pp. 23—31 (in Russian).

24. Laptev K. Z., Illarionov G. Yu. What can hinder the underwater navigation of an autonomous uninhabited underwater vehicle, Collection of materials of the XIII All-Russian Scientific and Practical Conference "Perspective systems and management tasks", Rostov-on-Don, Southern Federal University, 2017, pp. 138—146 (in Russian).

25. Inzartsev A. V., Bagnitsky A. V. Algorithms for circumventing local bottom objects for an autonomous underwater robot, Sixth All-Russian Scientific.- tech. conf. "Technical problems of the development of the world ocean" (TPOMO-6), Vladivostok, 2015, pp. 450—454 (in Russian).

26. Tuseeva I. B., Tuseeva D. B., Kim Yun-gi. Dynamic window algorithm for navigation of autonomous underwater vehicles, Artificial intelligence and decision-making, 2013, no. 3, pp. 67—77 (in Russian).

27. Galarza C., Masmitja I., Prat J., Gomariz S. Design of obstacle detection and avoidance system for Guanay II AUV, Appl. Sci., 2020, vol. 10, pp. 32—37.

28. Lin C., Wang H., Yuan J., Yu D., Li C. An improved recurrent neural network for unmanned underwater vehicle online obstacle avoidance, IEEEJ.Ocean. Eng., 2019, vol. 44, pp. 120—133.

29. Bykova V. S., Mashoshin A. I., Pashkevich I. V. Safe Navigation Algorithm for Autonomous Underwater Vehicles, Gyroscopy and Navigation, 2021, vol.12, no.1, pp. 86—95 (in Russian).

30. Inzartsev A. V., Panin M. A., Bobkov V. A., Morozov M. A. Model solution of the problem of inspection of industrial equipment facilities with the help of ANPA based on the method of video recognition of characteristic points, Underwater research and robotics, 2021, no. 3 (37), pp. 23—35 (in Russian).

31. Bykova V. S., Mashoshin A. I., Smirnov A. S. One approach to the recognition of bottom objects using monitoring systems installed on an autonomous underwater vehicle, Proc. RusAutoCon-2022 (in press).