Персона: Чепин, Евгений Валентинович
Загружается...
Email Address
Birth Date
Научные группы
Организационные подразделения
Организационная единица
Институт интеллектуальных кибернетических систем
Цель ИИКС и стратегия развития - это подготовка кадров, способных противостоять современным угрозам и вызовам, обладающих знаниями и компетенциями в области кибернетики, информационной и финансовой безопасности для решения задач разработки базового программного обеспечения, повышения защищенности критически важных информационных систем и противодействия отмыванию денег, полученных преступным путем, и финансированию терроризма.
Статус
Фамилия
Чепин
Имя
Евгений Валентинович
Имя
14 results
Результаты поиска
Теперь показываю 1 - 10 из 14
- ПубликацияОткрытый доступUsing Environmental Objects as Visual Stimuli in BCI-based Interaction System: Theoretical Approach(2021) Petrova, A.; Chepin, E.; Voznenko, T.; Петрова, Анжелика Анатольевна; Чепин, Евгений Валентинович; Возненко, Тимофей Игоревич© 2020 Elsevier B.V.. All rights reserved.In this study, we consider a novel approach of using subconscious brain activity, presented by evoked potentials (EP), in a BCI-based interaction system. The main idea of the proposed approach is using objects of everyday life as "integrated" stimuli. We investigate different methodologies of operating with visual stimuli in traditional EP-based systems and their applicability of using with environmental objects. The proposed architecture of a novel EP-based interaction system includes a conjunction of BCI and eye tracker (ETI) channels to select and recognize surrounding objects to directly interact with them further.
- ПубликацияОткрытый доступThe Influence of Using Different Mental Images as BCI Commands on the Quality of Control(2020) Petrova, A.; Voznenko, T.; Dyumin, A.; Chepin, E.; Cherepanova, A.; Петрова, Алёна Игоревна; Возненко, Тимофей Игоревич; Дюмин, Александр Александрович; Чепин, Евгений Валентинович© 2020 The Authors. Published by Elsevier B.V.Brain-Computer Interface (BCI) is a modern and progressive technology for controlling robotic devices. They are broadly applicable in various fields of robotics and information technologies, where alternative methods of controlling electronic devices are used (for example, medical robotics, development of virtual reality applications, game industry, etc.). The most common ways to implement BCI control commands are mental images, evoked potentials, and facial expressions. Compared to other methods, mental images are difficult to perform because of the need to perform an intensified mental activity and concentrate strongly on their execution. At the same time, mental images provide the operator with a promising opportunity to control the robot without performing any physical movements (compared to facial expressions usage) and without using additional equipment for stimuli representation (as is the case of evoked potentials). Therefore, it is necessary to conduct research on various aspects of working with mental images, such as the use of various types of mental images, the impact on the work of distractions, the operator's preliminary training technique, etc., to improve the user experience of using them and the quality of device control via such way of control. In this paper, we consider use mental images of different types as BCI control commands-visual, sound, kinesthetic. Performing of these commands is involving various parts of the brain. The quality of the operator's work with these types of mental images is evaluated, including the quality of mental images recognition by the BCI, as well as the time spent by the operator on their execution.
- ПубликацияТолько метаданныеDeveloping a Voice Control System for a Wheeled Robot(2024) Chepin, E.; Gridnev, A.; Erlou, M.; Чепин, Евгений Валентинович; Гриднев, Александр Александрович
- ПубликацияОткрытый доступThe Command Interpretation in Decomposition Method of Multi-Channel Control for a Robotic Device(2020) Voznenko, T. I.; Gridnev, A. A.; Chepin, E. V.; Kudryavtsev, K. Y.; Возненко, Тимофей Игоревич; Гриднев, Александр Александрович; Чепин, Евгений Валентинович; Кудрявцев, Константин Яковлевич© 2020 The Authors. Published by Elsevier B.V.Multi-channel control is a way of control using a few different channels simultaneously. The example of the multi-channel system is the extended brain-computer interface (extended-BCI) where voice, gesture and BCI control channels are used at the same time. However, this way of control is redundant: One command can be executed using different control channels. Because of each channel have errors of both types the control using few channels simultaneously can increase unwanted influence on robotic device control. One way to decrease this effect is to decompose the multi-channel control method into one composite channel. That composed channel should be defined based on some parameter and the best way of control. In this article, we consider MTnP parameter. During decomposition of the multi-channel system, command information not in composed channel is usually ignored. In this article, we propose a way of this information interpretation to improve the multi-channel control decomposition method for a robotic wheelchair using the extended-BCI.
- ПубликацияТолько метаданныеThe Impact of Artifacts on the BCI Control Channel for a Robotic Wheelchair(2020) Petrova, A. I.; Voznenko, T. I.; Chepin, E. V.; Петрова, Алёна Игоревна; Возненко, Тимофей Игоревич; Чепин, Евгений Валентинович© 2020, Springer Nature Switzerland AG.There are many ways to control robotic devices. The modern and actual technology of brain-computer interfaces (BCI) is one of the ways to implement a control channel. This way provides additional control options for the operator, such as using facial expressions, mental activity and head movements. However, BCI is far from being used in everyday life conditions in part because of the influence of various noises that provoke changes in the EEG signal, called artifacts. Therefore, it is necessary to evaluate the impact of these noises on control commands executed using BCI and take this impact into account during the control commands design. This is especially true when several commands, that require various types of movements (facial expressions, head movements), are used in a single control configuration, since these commands themselves provoke such noises and guarantee their occurrence in the control process. In this paper, we considered a set of BCI commands for control a robotic wheelchair and propose a system of metrics for assessing the impact of artifacts on these commands. The system of metrics was used to assess the mutual impact of commands to each other and avoid conflicts of commands arising from the occurrence of artifacts.
- ПубликацияТолько метаданныеStudy on the Possibility of Detecting Objects in Real Time on a Mobile Robot(2020) Verbitsky, N. S.; Chepin, E. V.; Gridnev, A. A.; Чепин, Евгений Валентинович; Гриднев, Александр Александрович© 2020, Springer Nature Switzerland AG.Today, a task of current interest in the field of artificial intelligence in digital image processing is the detection of objects using a convolutional neural network. The purpose of this work is to study the processing of video stream in real-time with the help of a modified tracking module on the client-server system used in robotic complexes. The modified tracking module proposed in this paper, which is a combination of the KCF and SORT algorithms, eliminates object detection duplicates and levels the low speed of the convolutional neural network. By measuring the operating time of each module in the system, was obtained the frame rate of each module. The obtained time characteristics of the client-server system modules confirm the effectiveness of the proposed modified tracking module. The practical significance of the work consists of the hypothesis confirmation is about reducing the impact of the object detection rate on the overall performance of the system when using the tracking module.
- ПубликацияТолько метаданныеReconfigurable Locomotion of Hexapod Robot Based on Inverse Kinematics(2020) Gumeniuk, V. A.; Chepin, E. V.; Voznenko, T. I.; Gridnev, A. A.; Чепин, Евгений Валентинович; Возненко, Тимофей Игоревич; Гриднев, Александр Александрович© 2020, Springer Nature Switzerland AG.In our days, robotics development grow and became fast changing industry, robots spread over the world far more than any time before. Most of all, robots have presented by manufacturing robots, but robots capable to move can be more flexible to give a solution to even new kinds of problems. Hexapods are one of those kind of robots. Today they are widely known, but they are not widespread, despite their advantages, and most frequently using in research purposes. One of the main problem is that locomotion can be done by many different gaits. At the same time, hexapods have six legs, that leads to complexity of control algorithm, which must provide correct positioning for all legs at any moment in time. But to simplicity, often only one specific gait is using. In this paper, we propose system that is able to work with multiple gaits simultaneously. This system allows robot to use different methods of locomotion which are more efficient in specific situations. As a proof of concept was implemented control software. It respond for locomotion, saving different gaits and their switching, even in movement. The result of the paper is an automated robot locomotion system.
- ПубликацияТолько метаданныеThe Decomposition Method of Multi-channel Control System Based on Extended BCI for a Robotic Wheelchair(2020) Voznenko, T. I.; Gridnev, A. A.; Kudryavtsev, K. Y.; Chepin, E. V.; Возненко, Тимофей Игоревич; Гриднев, Александр Александрович; Кудрявцев, Константин Яковлевич; Чепин, Евгений Валентинович© 2020, Springer Nature Switzerland AG.There are a number of ways to control a mobile robotic device, in particular robotic wheelchair. One of this ways is an extended brain-computer interface (extended BCI) – robotic control system with simultaneous independent alternative control channels (BCI, voice and gesture control channels). Because of each channel has advantages and disadvantages the combination of some channels (multi-channel control) can be used. However, when commands are executed from several control channels, various conflicts may arise: for example, one command comes from one control channel, and some opposite commands (which cannot be executed simultaneously) that come from the other channels. To resolve such conflicts, two methods can be used: coordinated control and decomposition. Both of these methods are based on a quality evaluation of each control channel. To evaluate the quality of those control channels the different parameters can be used. This paper proposes a decomposition method of multi-channel control system based on proposed parameter. This technique allows to choose the best channel-command combinations based on type I and type II errors.
- ПубликацияТолько метаданныеGesture recognition system based on Convolutional neural networks(2019) Chistyakov, I. S.; Chepin, E. V.; Чепин, Евгений Валентинович© 2019 Published under licence by IOP Publishing Ltd. This article tells about gesture recognition system based on Convolutional neural nets. System consists of two parts: the tracking and detection subsystem and gesture recognition subsystem.
- ПубликацияТолько метаданныеThe Method of Statistical Estimation of the Minimum Number of Tests for Reliable Evaluation of the Robotic Multi-channel Control Systems Quality(2019) Kudryavtsev, K. Y.; Cherepanov, A. V.; Voznenko, T. I.; Dyumin, A. A.; Gridnev, A. A.; Chepin, E. V.; Кудрявцев, Константин Яковлевич; Возненко, Тимофей Игоревич; Дюмин, Александр Александрович; Гриднев, Александр Александрович; Чепин, Евгений Валентинович© 2019, Springer Nature Switzerland AG. There is a growth in adoption of multi-channel (tactile, voice, gesture, brain-computer interface, etc.) control systems for mobile robots that help to improve its reliability. But, a complex control system requires a large number of tests to determine the quality of operation. Hence, multi-channel control systems are subjects of rigorous testing process for estimation of the number of successful command recognitions and the number of errors. The more tests will be conducted, the more accurate evaluation of the control channel quality will be. However, in most cases, carrying out the tests is expensive and time-consuming. Therefore, it is necessary to determine the minimum number of tests required to evaluate channel control quality with a given significance level. In this paper we propose a technique for determining the minimum required number of tests. Experimental results of evaluating the multichannel control system of the mobile robotic wheelchair using this technique are presented.