Deep regression of convolutional neural network applied to resolved acceleration control for a robot manipulator

2021 ◽  
pp. 014233122110027
Author(s):  
Yong-Lin Kuo ◽  
Shih-Chien Tang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Robot Manipulator ◽  
Parallel Robot ◽  
Real Time Control ◽  
End Effector ◽  
Time Control ◽  
Control Scheme ◽  
Resolved Acceleration Control ◽  
Position And Orientation

This paper presents a modified resolved acceleration control scheme based on deep regression of the convolutional neural network. The resolved acceleration control scheme can achieve precise motion control of robot manipulators by regulating the accelerations of the end-effector, and the conventional scheme needs the position and orientation of the end-effector, which are obtained through the direct kinematics of the robot manipulator. This scheme increases the computational loads and might obtain inaccurate position and orientation due to mechanical errors. To overcome the drawbacks, a camera is used to capture the images of the robot manipulator, and then a deep regression of convolutional neural network is imposed into the resolved acceleration control to obtain the position and orientation of the end-effector. The proposed approach aims to enhance the positioning accuracy, to reduce the computational loads, and to facilitate the deep regression in real-time control. In this study, the proposed approach is applied to a 3-DOF planar parallel robot manipulator, and the results are compared with those by the conventional resolved acceleration control and a visual servo-based control. The results show that those objectives are achieved. Furthermore, the robustness of the proposed approach is tested through only the partial image of the end-effector available, and the proposed approach still works functionally and effectively.

Finding Features of Positioning Error for Large Industrial Robots Based on Convolutional Neural Network

2021 ◽  
Author(s):  
Daiki Kato ◽  
Kenya Yoshitugu ◽  
Naoki Maeda ◽  
Toshiki Hirogaki ◽  
Eiichi Aoyama ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Production Systems ◽  
Industrial Robot ◽  
Three Dimensional ◽  
Industrial Robots ◽  
Numerical Control ◽  
Robot Motion ◽  
Positioning Error ◽  
End Effector

Abstract Most industrial robots are taught using the teaching playback method; therefore, they are unsuitable for use in variable production systems. Although offline teaching methods have been developed, they have not been practiced because of the low accuracy of the position and posture of the end-effector. Therefore, many studies have attempted to calibrate the position and posture but have not reached a practical level, as such methods consider the joint angle when the robot is stationary rather than the features during robot motion. Currently, it is easy to obtain servo information under numerical control operations owing to the Internet of Things technologies. In this study, we propose a method for obtaining servo information during robot motion and converting it into images to find features using a convolutional neural network (CNN). Herein, a large industrial robot was used. The three-dimensional coordinates of the end-effector were obtained using a laser tracker. The positioning error of the robot was accurately learned by the CNN. We extracted the features of the points where the positioning error was extremely large. By extracting the features of the X-axis positioning error using the CNN, the joint 1 current is a feature. This indicates that the vibration current in joint 1 is a factor in the X-axis positioning error.

scholarly journals A Novel Kinematically Redundant Planar Parallel Robot Manipulator With Full Rotatability

2018 ◽  
Vol 11 (1) ◽  
Author(s):  
Nicholas Baron ◽  
Andrew Philippides ◽  
Nicolas Rojas
Keyword(s):  
Potential Application ◽  
Robot Manipulator ◽  
Video Recording ◽  
Parallel Robot ◽  
Singularity Analysis ◽  
Geometric Method ◽  
Forward Kinematics ◽  
Online Video ◽  
End Effector ◽  
Moving Platform

This paper presents a novel kinematically redundant planar parallel robot manipulator, which has full rotatability. The proposed robot manipulator has an architecture that corresponds to a fundamental truss, meaning that it does not contain internal rigid structures when the actuators are locked. This also implies that its rigidity is not inherited from more general architectures or resulting from the combination of other fundamental structures. The introduced topology is a departure from the standard 3-RPR (or 3-RRR) mechanism on which most kinematically redundant planar parallel robot manipulators are based. The robot manipulator consists of a moving platform that is connected to the base via two RRR legs and connected to a ternary link, which is joined to the base by a passive revolute joint, via two other RRR legs. The resulting robot mechanism is kinematically redundant, being able to avoid the production of singularities and having unlimited rotational capability. The inverse and forward kinematics analyses of this novel robot manipulator are derived using distance-based techniques, and the singularity analysis is performed using a geometric method based on the properties of instantaneous centers of rotation. An example robot mechanism is analyzed numerically and physically tested; and a test trajectory where the end effector completes a full cycle rotation is reported. A link to an online video recording of such a capability, along with the avoidance of singularities and a potential application, is also provided.

scholarly journals A New Approach to the Solution of Robot Kinematics Based on Relative Transformation Matrices

2016 ◽  
Vol 5 (3) ◽  
pp. 213
Author(s):  
Mohammad Reza Elhami ◽  
Iman Dashti
Keyword(s):  
Robot Manipulator ◽  
Robot Kinematics ◽  
Coordinate Frame ◽  
End Effector ◽  
New Approach ◽  
Transformation Matrices ◽  
The World ◽  
Convenient Approach ◽  
Position And Orientation ◽  
Relative Transformation

In analyzing robot manipulator kinematics, we need to describe relative movement of adjacent linkages or joints in order to obtain the pose of end effector (both position and orientation) in reference coordinate frame. Denavit-Hartenberg established a method based on a 4×4 homogenous matrix so called “A” matrix. This method used by most of the authors for kinematics and dynamic analysis of the robot manipulators. Although it has many advantages, however, finding the elements of this matrix and link/joint’s parameters is sometimes complicated and confusing. By considering these difficulties, the authors proposed a new approach called ‘convenient approach’ that is developed based on “Relative Transformations Principle”. It provides a very simple and convenient way for the solution of robot kinematics compared to the conventional D-H representation. In order to clarify this point, the kinematics of the world known Stanford manipulator has been solved through D-H representation as well as convenient approach and the results are compared.

Dynamic modeling, system identification and comparative study of various control strategies for a spatial parallel manipulator

2021 ◽  
pp. 095965182110320
Author(s):  
Mervin Joe Thomas ◽  
Shoby George ◽  
Deepak Sreedharan ◽  
ML Joy ◽  
AP Sudheer
Keyword(s):  
Real Time ◽  
Parallel Manipulator ◽  
Control Strategies ◽  
Proportional Integral Derivative ◽  
Real Time Control ◽  
Model Predictive Controller ◽  
End Effector ◽  
Proportional Integral ◽  
Time Control ◽  
Predictive Controller

The significant challenges seen with the mathematical modeling and control of spatial parallel manipulators are its difficulty in the kinematic formulation and the inability to real-time control. The analytical approaches for the determination of the kinematic solutions are computationally expensive. This is due to the passive joints, solvability issues with non-linear equations, and inherent kinematic constraints within the manipulator architecture. Therefore, this article concentrates on an artificial neural network–based system identification approach to resolve the complexities of mathematical formulations. Moreover, the low computation time with neural networks adds up to its advantage of real-time control. Besides, this article compares the performance of a constant gain proportional–integral–derivative (PID), variable gain proportional–integral–derivative, model predictive controller, and a cascade controller with combined variable proportional–integral–derivative and model predictive controller for real-time tracking of the end-effector. The control strategies are simulated on the Simulink model of a 6-degree-of-freedom 3-PPSS (P—prismatic; S—spherical) parallel manipulator. The simulation and real-time experiments performed on the fabricated manipulator prototype indicate that the proposed cascade controller with position and velocity compensation is an appropriate method for accurate tracking along the desired path. Also, training the network using the experimentally generated data set incorporates the mechanical joint approximations and link deformities present in the fabricated model into the predicted results. In addition, this article showcases the application of Euler–Lagrangian formalism on the 3-PPSS parallel manipulator for its dynamic model incorporating the system constraints. The Lagrangian multipliers include the influence of the constraint forces acting on the manipulator platform. For completeness, the analytical model results have been verified using ADAMS for a pre-defined end-effector trajectory.

A hybrid impedance control scheme for underwater welding robots with a passive foundation in the controller domain

SIMULATION ◽  
2017 ◽  
Vol 93 (7) ◽  
pp. 619-630 ◽  
Author(s):  
Sunil Kumar ◽  
Vikas Rastogi ◽  
Pardeep Gupta
Keyword(s):  
Minimum Distance ◽  
Position Control ◽  
Robot Manipulator ◽  
Impedance Control ◽  
Graph Model ◽  
Proportional Integral Derivative ◽  
End Effector ◽  
Flexible Arm ◽  
Control Scheme ◽  
Effective Stability

A hybrid impedance control scheme for the force and position control of an end-effector is presented in this paper. The interaction of the end-effector is controlled using a passive foundation with compensation gain. For obtaining the steady state, a proportional–integral–derivative controller is tuned with an impedance controller. The hybrid impedance controller is implemented on a terrestrial (ground) single-arm robot manipulator. The modeling is done by creating a bond graph model and efficacy is substantiated through simulation results. Further, the hybrid impedance control scheme is applied on a two-link flexible arm underwater robot manipulator for welding applications. Underwater conditions, such as hydrodynamic forces, buoyancy forces, and other disturbances, are considered in the modeling. During interaction, the minimum distance from the virtual wall is maintained. A simulation study is carried out, which reveals some effective stability of the system.

Sign in / Sign up

Export Citation Format

Share Document