Solution of the dynamics inverse problem with the copying control of an anthropomorphic manipulator based on the predictive estimate of the operator’s hand movement using the updated Brown method

Петренко, В. И.; Тебуева, Фариза; Gurchinsky, M. M.; Antonov, V. O.; Shutova, J. A.

doi:10.1088/1757-899x/450/4/042013

Cited by 9 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of this work is to develop a method for controlling the movement of an anthropomorphic manipulator in the working area with a dynamic obstacle based on deep training with reinforcement. Known methods for planning the path of an anthropomorphic manipulator in the working area with an obstacle, based on solving problems of kinematics and dynamics [8][9][10], based on an analytical approach. However, the most promising are methods for solving these problems using such an artificial intelligence method as deep learning, due to the following advantages:…”

Section: Introductionmentioning

confidence: 99%

Method of Controlling the Movement of an Anthropomorphic Manipulator in the Working Area With Dynamic Obstacle

Петренко¹,

Gurchinsky²,

Тебуева³

et al. 2020

Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020)

View full text Add to dashboard Cite

Currently, the rapidly developing direction of anthropomorphic robotics attracts great interest of developers. This is due to the need to perform routine, harmful and hazardous types of work without direct human intervention, which is the key to ensuring the safety of the tasks performed. The article discusses the issue of optimizing the trajectory of the manipulator when performing operations in the working area with an obstacle. To achieve this goal, an algorithm for controlling the movement of an anthropomorphic manipulator in a working area with dynamic obstacles is proposed using deep learning technology with amplification of a convolutional artificial neural network based on the DQN learning algorithm. This algorithm is more scalable than peers because it can be used for a wide variety of path planning problems in both deterministic and non-deterministic environments. The results of modeling the operation of a manipulator with seven rotational degrees of mobility in the working area with a typical obstacle in the form of a sphere are presented. The presented simulation results demonstrate the effectiveness of the proposed method and the need for its further development.

show abstract

Section: Introductionmentioning

confidence: 99%

Method of Controlling the Movement of an Anthropomorphic Manipulator in the Working Area With Dynamic Obstacle

Петренко¹,

Gurchinsky²,

Тебуева³

et al. 2020

Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020)

View full text Add to dashboard Cite

show abstract

“…To register positions and anthropomorphic manipulator control developed device uses the method of solving the kinematics problem [15]: direct kinematics problem through the representation of Denavit-Hartenberg to determine the Cartesian coordinates of the shoulder joint, anthropomorphic manipulator wrist and the operator's hand and the inverse problem of kinematics to determine the Cartesian coordinates of the anthropomorphic manipulator elbow. To solve the problem of dynamics, the article [16] describes a method of predicting the operator's hand movements to form the laws of motion of the anthropomorphic manipulator nodes.…”

Section: Introductionmentioning

confidence: 99%

Exoskeleton for Operator's Motion Сapture With Master-Slave Control

Petrenko¹,

Тебуева²,

Gurchinsky³

et al. 2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

The study is devoted to the development of the structure of the upper-limb exoskeleton for operator's motion capture with master-slave control. The objective of the study is to develop design solutions in the field of registration of the current position of the operator's hand parts during the technological operations of the control commands formation for their accurate reproduction by the movements of the anthropomorphic manipulator links in real time. For the developed structure of the upper-limb exoskeleton, the division of the product scheme is described, the rationale for the design, the layout of kinematic pairs equipped with angular rotation sensors, and the design of the lever system that duplicates the operator's hand with its metric parameters is given. To check the efficiency of the exoskeleton design, a simulation program was used. The accuracy of the rotation angle of the exoskeleton elbow joint in the simulation model does not exceed 3.4%, shoulder joint-5.2%. The presented structure of the exoskeleton will allow to register the current positions of the operator's hand parts when performing technological operations and to form control commands for their accurate reproduction by the links of the manipulator.

show abstract

“…• a method for the dynamics problem solving by predicting the movements of the operator's hand to form the laws of motion of the anthropomorphic manipulator nodes [2].…”

Section: Introductionmentioning

confidence: 99%

The Study of the Problems of the Master-Slave Teleoperation Control Anthropomorphic Manipulator

Петренко¹,

Тебуева²,

Gurchinsky³

et al. 2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

This article describes the problems of anthropomorphic manipulators (AM) master-slave teleoperation control. The aim of the work is to study the problems of the teleoperation control accuracy. The scheme of copying control system is considered in the article. The most characteristic problems for this control method are allocated. The discretization and restoring of the signal examples describing the rotation angle dependence of the manipulator joint on time are made. Real-time smoothing methods based on the calculation of the speed and acceleration of the signal change, as well as smoothing by piecewise linear interpolation with a delay of one discrete time tick are applied to the restored signal. For the restored signals with smoothing and without smoothing, the root mean square of deviation from the initial signal is estimated.

show abstract

Solution of the dynamics inverse problem with the copying control of an anthropomorphic manipulator based on the predictive estimate of the operator’s hand movement using the updated Brown method

Cited by 9 publications

References 2 publications

Method of Controlling the Movement of an Anthropomorphic Manipulator in the Working Area With Dynamic Obstacle

Method of Controlling the Movement of an Anthropomorphic Manipulator in the Working Area With Dynamic Obstacle

Exoskeleton for Operator's Motion Сapture With Master-Slave Control

The Study of the Problems of the Master-Slave Teleoperation Control Anthropomorphic Manipulator

Contact Info

Product

Resources

About