Sergey Konstantinov

Mr. Sergey Konstantinov

RUDN University
+1

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2018 in Journal of Computer and Systems Sciences International
Verified
Journal Article
Closed access
PDF file
Askhat DiveevAskhat Diveev
Askhat Diveev
SKSergey Konstantinov
Sergey Konstantinov
Evolutionary algorithms for solving the problem of the optimal program control are considered. The most popular evolutionary algorithms, the genetic algorithm (GA), the differential evolution (DE)...

29 January 2021 in Mathematics
Verified
Journal Article
Open access
PDF file
Askhat DiveevAskhat Diveev
Askhat Diveev
SKSergey Konstantinov
Sergey Konstantinov
ESElizaveta Shmalko
Elizaveta Shmalko
GDGe DONG
Ge DONG
The paper is devoted to an emerging trend in control—a machine learning control. Despite the popularity of the idea of machine learning, there are various interpretations of this concept, and there is an urgent need for its strict mathematical formalization. An attempt to formalize the concept of machine learning is presented in this paper. The concepts of an unknown function, work area, training set are introduced, and a mathematical formulation of the machine learning problem is presented. Based on the presented formulation, the concept of machine learning control is considered. One of the problems of machine learning control is the general synthesis of control. It implies finding a control function that depends on the state of the object, which ensures the achievement of the control goal with the optimal value of the quality criterion from any initial state of some admissible region. Supervised and unsupervised approaches to solving a problem based on symbolic regression methods are considered. As a computational example, a problem of general synthesis of optimal control for a spacecraft landing on the surface of the Moon is considered as supervised machine learning control with a training set.

31 July 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Askhat DiveevAskhat Diveev
Askhat Diveev
Elena SofronovaElena Sofronova
Elena Sofronova
SKSergey Konstantinov
Sergey Konstantinov
Two approaches to the numerical solution of the optimal control problem are studied. The direct approach is based on the reduction of the optimal control problem to a nonlinear programming problem. Another approach is so-called synthesized optimal control, and it includes the solution of the control synthesis problem and stabilization at some point in the state space, followed by the search of stabilization points and movement of the control object along these points. The comparison of these two approaches was carried out as the solution of the optimal control problem as a time function cannot be directly used in the control system, although the obtained discretized control can be embedded. The control object was a group of interacting mobile robots. Dynamic and static constraints were included in the quality criterion. Implemented methods were evolutionary algorithms and a random parameter search of piecewise linear approximation and coordinates of stabilization points, along with a multilayer network operator for control synthesis.

1 April 2018
Verified
Conference Paper
Closed access
ADA.I. Diveev
A.I. Diveev
SKSergey Konstantinov
Sergey Konstantinov
ESE.A. Sofronova
E.A. Sofronova
An experimental comparison of evolutionary algorithms and gradient-based methods for the optimal control problem is carried out. The problem is solved separately by Particle swarm optimization, Grey wolf optimizer, Fast gradient descent method, Marquardt method and Adam method. The simulation is performed on a jet aircraft model. The results of each algorithm performance are compared according to the best found value of the fitness function, the mean value and the standard deviation.

1 July 2017
Verified
Conference Paper
Closed access
ADA.I. Diveev
A.I. Diveev
GBG.I. Balandina
G.I. Balandina
SKSergey Konstantinov
Sergey Konstantinov
The paper describes a novel numerical symbolic regression method. It's called complete binary variational genetic programming. We use it for synthesis of optimal control. This method performs better than genetic programming at crossover, reduces the search area and speeds up search algorithm by using small variations. The efficiency of the new method is proven on the given example of control system synthesis for mobile robot.

1 January 2017 in Procedia Computer Science
Verified
Journal Article
Open access
SKSergey Konstantinov
Sergey Konstantinov
ABA.A. Baryshnikov
A.A. Baryshnikov
Six modern and promising evolutionary algorithms are described: genetic algorithm, differential evolution method, variational genetic algorithm, particle swarm optimization algorithm, bat-inspired method and firefly algorithm. For all algorithms brief description and main steps of receiving solution are given. In the experimental part all algorithms are compared by the effectiveness of solving the parametric optimization problem for PID controllers.