Solving the Problem of the Optimal Control System General Synthesis Based on Approximation of a Set of Extremals using the Symbol Regression Method

A new approach is considered to solving the problem of synthesizing an optimal control system based on the extremals' set approximation. At the first stage, the optimal control problem for various initial states out of a given domain is being numerically sold. Evolutionary algorithms are used to solve the optimal control problem numerically. At the second stage, the problem of approximating the found set of extremals by the method of symbolic regression is solved. Approach considered in the work makes it possible to eliminate the main drawback of the known approach to solving the control synthesis problem using the symbolic regression method, which consists in the fact that the genetic algorithm used in solving the synthesis problem does not provide information about proximity of the found solution to the optimal one. Here, control function is built on the basis of a set of extremals; therefore, any particular solution should be close to the optimal trajectory. Computational experiment is presented for solving the applied problem of synthesizing the four-wheel robot optimal control system in the presence of phase constraints. It is experimentally demonstrated that the synthesized control function makes it possible for any initial state from a given domain to obtain trajectories close to optimal in the quality functional. Initial states were considered during the experiment, both included in the approximating set of optimal trajectories and others from the same given domain. Approximation of the extremals set was carried out by the network operator method

The study was partially supported by the RFBR project no. 18-29-03061-mk

Литература

[1] Boltyanskiy V.G. Matematicheskie metody optimal’nogo upravleniya [Mathematical methods of optimum control]. Moscow, Nauka Publ., 1969.

[2] Arutyunov A.V., Magaril-Il’yaev G.G., Tikhomirov V.M. Printsip maksimuma Pontryagina. Dokazatel’stvo i prilozheniya [Pontryagin maximum principle. Proof and applications]. Moscow, Faktorial Press Publ., 2006.

[3] Diveev A.I. Priblizhennye metody resheniya zadachi sinteza optimal’nogo upravleniya [Approximate methods for solving the optimal control synthesis problem]. Moscow, VTs RAN Publ., 2015.

[4] Pshikhopov V.Kh., Medvedev M.Yu. Synthesis of control systems for underwater vehicles with nonlinear actuators. Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2011, no. 3, pp. 147--156 (in Russ.).

[5] Kolesnikov A.A. Sinergeticheskie metody upravleniya slozhnymi sistemami: teoriya sistemnogo sinteza [Synergetic control methods for complex systems: theory of system synthesis]. Moscow, Librokom Publ., 2012.

[6] Kolesnikov A.A., Kolesnikov A.A., Kuz'menko A.A. The ADAR method and theory of optimal control in the problems of synthesis of nonlinear control systems. Mekhatronika, avtomatizatsiya, upravlenie, 2016, no. 10, pp. 657--669 (in Russ.). DOI: https://doi.org/10.17587/mau.17.657-669

[7] Shushlyapin E.A., Bezuglaya A.E. Analytical synthesis of regulators for nonlinear systems with a terminal state method on examples of motion control of a wheeled robot and a vessel. J. Appl. Math., 2018, vol. 2018, art. 4868791. DOI: https://doi.org/10.1155/2018/4868791

[8] Diveev A.I. Chislennye metody resheniya zadachi sinteza upravleniya [Numerical methods for solving control synthesis problem]. Moscow, RUDN Publ., 2019.

[9] Diveev A.I. Metod setevogo operatora [Network operator method]. Moscow, VTs RAN Publ., 2010.

[10] Koza J.R., Keane M.A., Streeter M.J., et al. Genetic programming IV. Routine human-competitive machine intelligence. Springer, 2003.

[11] Ryan C., O’Neill M., Collins J.J. Handbook of grammatical evolution. Springer, 2018.

[12] Kojecky L., Zelinka I. CUDA-based analytic programming by means of SOMA algorithm. Advances in Intelligent Systems and Computing --- Mendel. Springer, 2015, pp. 171--180. DOI: https://doi.org/10.1007/978-3-319-19824-8_14

[13] Diveev A.I. A numerical method for network operator for synthesis of a control system with uncertain initial values. J. Comput. Syst. Sc. Int., 2012, vol. 51, no. 2, pp. 228--243. DOI: https://doi.org/10.1134/S1064230712010066

[14] Pesterev A.V. A linearizing feedback for stabilizing a car-like robot following a curvilinear path. J. Comput. Syst. Sc. Int., 2013, vol. 52, no. 5, pp. 819--830. DOI: https://doi.org/10.1134/S1064230713050109

[15] Pham D.T., Castellani M. A comparative study of the Bees Algorithm as a tool for function optimization. Cogent Eng., 2015, vol. 2 no. 1, pp. 1--28. DOI: https://doi.org/10.1080/23311916.2015.1091540

[16] Grishin A.A., Karpenko A.P. Efficiency investigation of the bees algorithm into global optimization problem. Nauka i obrazovanie: nauchnoe izdanie MGTU im. N.E. Baumana [Science and Education: Scientific Publication], 2010, no. 8 (in Russ.). DOI: https://doi.org/10.7463/0810.0154050

[17] Diveev A.I., Konstantinov S.V. Study of the practical convergence of evolutionary algorithms for the optimal program control of a wheeled robot. J. Comput. Syst. Sc. Int., 2018, vol. 57, no. 4, pp. 561--580. DOI: https://doi.org/10.1134/S106423071804007X

[18] Konstantinov S.V., Diveev A.I., Balandina G.I., et al. Comparative research of random search algorithms and evolutionary algorithms for the optimal control problem of the mobile robot. Procedia Comput. Sc., 2019, vol. 150, pp. 462--470. DOI: https://doi.org/10.1016/j.procs.2019.02.080

[19] Sofronova E.A., Belyakov A.A., Khamadiyarov D.B. Optimal control for traffic flows in the urban road networks and its solution by variational genetic algorithm. Procedia Comput. Sc., 2019, vol. 150, pp. 302--308. DOI: https://doi.org/10.1016/j.procs.2019.02.056