Alexander Gorobtsov

Dr. Alexander Gorobtsov


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
12 May 2023 in Algorithms
Verified
Journal Article
Open access
PDF file
YOYulia Orlova
Yulia Orlova
AGAlexander Gorobtsov
Alexander Gorobtsov
OSOleg Sychev
Oleg Sychev
VRVladimir Rozaliev
Vladimir Rozaliev
AZAlexander Zubkov
Alexander Zubkov
ADAnastasia Romanovna Donsckaia
Anastasia Romanovna Donsckaia
Since the COVID-19 pandemic, the demand for respiratory rehabilitation has significantly increased. This makes developing home (remote) rehabilitation methods using modern technology essential. New techniques and tools, including wireless sensors and motion capture systems, have been developed to implement remote respiratory rehabilitation. Significant attention during respiratory rehabilitation is paid to the type of human breathing. Remote rehabilitation requires the development of automated methods of breath analysis. Most currently developed methods for analyzing breathing do not work with different types of breathing. These methods are either designed for one type (for example, diaphragmatic) or simply analyze the lungs’ condition. Developing methods of determining the types of human breathing is necessary for conducting remote respiratory rehabilitation efficiently. We propose a method of determining the type of breathing using wireless sensors with the motion capture system. To develop that method, spectral analysis and machine learning methods were used to detect the prevailing spectrum, the marker coordinates, and the prevailing frequency for different types of breathing. An algorithm for determining the type of human breathing is described. It is based on approximating the shape of graphs of distances between markers using sinusoidal waves. Based on the features of the resulting waves, we trained machine learning models to determine the types of breathing. After the first stage of training, we found that the maximum accuracy of machine learning models was below 0.63, which was too low to be reliably used in respiratory rehabilitation. Based on the analysis of the obtained accuracy, the training and running time of the models, and the error function, we choose the strategy of achieving higher accuracy by increasing the training and running time of the model and using a two-stage method, composed of two machine learning models, trained separately. The first model determines whether the breath is of the mixed type; if it does not predict the mixed type of breathing, the second model determines whether breathing is thoracic or abdominal. The highest accuracy achieved by the composite model was 0.81, which surpasses single models and is high enough for use in respiratory rehabilitation. Therefore, using three wireless sensors placed on the patient’s body and a two-stage algorithm using machine learning models, it was possible to determine the type of human breathing with high enough precision to conduct remote respiratory rehabilitation. The developed algorithm can be used in building rehabilitation applications.


18 November 2022 in Sensors
Verified
Journal Article
Open access
PDF file
AGAlexander Gorobtsov
Alexander Gorobtsov
OSOleg Sychev
Oleg Sychev
YOYulia Orlova
Yulia Orlova
ESEvgeniy Smirnov
Evgeniy Smirnov
OGOlga Grigoreva
Olga Grigoreva
MAMarina Andreeva
Marina Andreeva
We consider the problem of dimensionality reduction of state space in the variational approach to the optimal control problem, in particular, in the reinforcement learning method. The control problem is described by differential algebraic equations consisting of nonlinear differential equations and algebraic constraint equations interconnected with Lagrange multipliers. The proposed method is based on changing the Lagrange multipliers of one subset based on the Lagrange multipliers of another subset. We present examples of the application of the proposed method in robotics and vibration isolation in transport vehicles. The method is implemented in FRUND—a multibody system dynamics software package.

1 December 2006 in Computational Mathematics and Mathematical Physics
Verified
Journal Article
Closed access
PDF file
LBL. Ya. Banakh
L. Ya. Banakh
AGAlexander Gorobtsov
Alexander Gorobtsov
OCO. K. Chesnokov
O. K. Chesnokov
Systems of differential algebraic equations are examined. A method is proposed for transforming the rectangular matrix of algebraic equations to block diagonal form. This method ensures the prescribed accuracy of the solution with respect to the original system of equations.

3 July 2026 in Informatics and Automation
Verified
Journal Article
Open access
PDF file
AGAlexander Gorobtsov
Alexander Gorobtsov
KKKonstantin Klimov
Konstantin Klimov
VDVladimir Danilov
Vladimir Danilov
The purpose of the work is to create methods for controlling real-time walking robots for a wide range of motion modes. A modification of the inverse dynamics method is considered, using a universal adaptive gait generator that implements the six-dimensional motion of the robot's body. This method has been implemented in software, with the addition of regularization methods for numerically integrating equations with a singular matrix. The results of theoretical and experimental research on the motion of a dog robot in various modes over micro and macro irregularities are presented. There is a low level of dynamic parameters of the robot's motion, in particular, high vibration, which corresponds to the literature data for a similar kinematic scheme of dog robots, the control of which is synthesized by machine learning methods and inverse dynamics. The reason for the low quality of control is the phases of motion in which the system becomes uncontrollable. Possible modifications of the robot's kinematic scheme are considered to ensure the unconditional controllability of the system. These modifications can be achieved by introducing redundant controllable degrees of freedom, such as a tail, paws, etc. New theoretical methods for controlling systems with redundant degrees of freedom are proposed based on the generalized dynamic balancing problem. The effectiveness of these methods is confirmed through simulations of the controlled movement of a dog robot with a tail and paws. For a common kinematic scheme of a dog robot with three drives per leg and point contact in the foot, a rational solution is to use a single wheel for moving over micro-irregularities and walking propulsors for overcoming macro-irregularities and escaping from emergency situations, such as tipping over. The episodic use of walking propulsors allows for simplified control modes, which are effectively implemented within the proposed modification of the inverse dynamics method. The concept has been confirmed by numerical and field experiments. In this case, the locomotion control system can be implemented on an inexpensive hardware basis, including the use of proven instrumentation for widespread robots, such as quadrocopters. A distinctive feature of robots based on the proposed control principles is their modular design, which allows for modifications in a wide range of technical characteristics through various module configurations. Such highly mobile robots can become a cheap and safe platform for refinement of navigation systems, unmanned control, etc. in real-world conditions in various fields of application.

30 June 2024 in Robotics and Technical Cybernetics
Verified
Journal Article
Closed access
AGAlexander Gorobtsov
Alexander Gorobtsov
VUVolgograd State Technical University
Volgograd State Technical University
SKSergey Kartsov
Sergey Kartsov
YPYuriy Polyakov
Yuriy Polyakov
ADAnton Dianskiy
Anton Dianskiy
M«Moscow State University of Technology «STANKIN»
Moscow State University of Technology «STANKIN»
A mathematical model for analyzing the power, consumed by the robot-android drives in rectilinear motion with a uniformly increasing speed, is considered. The mathematical model is compiled using the methods of multibody systems dynamics. Solving problems using the model is performed by numerical integration methods. The time dependences of the rotation angles drives and their angular velocities have been constructed. The dependences of the moments in drives in an unsteady mode of motion with increasing speed were also obtained. The drives with maximum energy consumption have been identified. It is shown, that the required power in the drives in-creases significantly with increasing speed of the robot. The nature of the power consumption in the drives has a pulsed form, with sections of positive and negative power, which indicates the possibility of significantly reducing energy consumption in the drives due to recuperation. The peak power in the most loaded lower limb drives can reach 0.7 kW. The total algebraic sum of power consumption in all drives is also approximately 0.7 kW. In this case, the total power absolute value of all drives reaches 2 kW. The maximum values of power consumption occur at high speeds – up to 0.9 m/s. At speeds up to 0.2 m/s, the total power does not exceed 150 – 200 W.