A possible approach to the creation of self-learning control systems for autonomous robots

A possible approach to the creation of self-learning control systems for autonomous robots

Ivan l. Ermolov
Doctor of Technical Science, Professor, Ishlinsky Institute for Problems in Mechanics of the Russian Academy of Sciences (IPMech RAS), Deputy Director, 101-1, pr. Vernadskogo, Moscow, 119526, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., ORCID: 0000-0002-8458-7982

Sergey P. Khripunov
Doctor of Technical Science, Professor, V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences, Leading Research Scientist, 65, Profsoyuznaya ul., Moscow, 117997, Russia,  This email address is being protected from spambots. You need JavaScript enabled to view it.

Received November 15, 2022

Abstract
Unmanned systems often function in new, non-predetermined environment. This demands flexible and simultaneously stable function of these systems. This can be implemented by their adaptation and, as a final goal, self-learning or self-organization in control systems. Autonomous functioning in extreme environment requires self-learning drastically. Such environment can be hostile towards unmanned systems, it may contain sophisticated communication conditions. All these are deteriorated by poor on-board control algorithms. In some of such cases unmanned systems may become inefficient or, even more, useless in some cases. This brings to front necessity to create adaptive self-learning control systems for robots. These should be capable to generate efficient, or even optimal decisions in extreme environment. This paper presents on of possible approaches to create self-learning control systems based on so called decision along analogues.

Key words
Unmanned system, robots' autonomy, self-learning.

Acknowledgements
The present work was partially supported by the Ministry of Science and Higher Education within the framework of the Russian State Assignment under contract No.АААА-А20-120011690138-6).

DOI
10.31776/RTCJ.11106

Bibliographic description
Ermolov, I.I. and Khripunov, S.P. (2023). A possible approach to the creation of self-learning control systems for autonomous robots. Robotics and Technical Cybernetics, 11(1), pp.45-50.

UDC identifier:
004.896:007.52

References

  1. Khripunov, S.P. (1995). Osnovy Situatsionnogo Modelirovaniya Zadach Prinyatiya Resheniy pri Boyevom Primenenii Aviatsionnykh Pritsel'no-navigatsionnykh Sistem. Uchebnoye Posobiye [Fundamentals of Situational Modeling of Decision-making Problems in the Combat Use of Aviation Sighting and Navigation Systems. Textbook]. Moscow: VVIA im. prof. N.E. Zhukovsky Publ.
  2. Ermolov, I.L. (2017). Robototekhnika: Avtonomnost' Robotov. Seriya: Itogi Nauki i Tekhniki. Roboty i Robototekhnicheskiye Ustroystva [Robotics: Autonomy of Robots. Series: Results of Science and Technology. Robots and Robotic Devices]. Moscow: VINITI Publ.
  3. Ermolov, I.L. and Khripunov, S.P. (2018). Problems of group application of robotic systems and ways to solve them. Extreme Robotics, 1, pp.164–165. (in Russian).