Control Design of Robotic Manipulator Based on Quantum Neural Network

2017 ◽  
Vol 140 (6) ◽  
Author(s):  
Hayder Mahdi Abdulridha ◽  
Zainab Abdullah Hassoun
Keyword(s):  
Neural Network ◽  
Dynamic Model ◽  
Pid Controller ◽  
Inverse Kinematics ◽  
Robot Manipulator ◽  
System Response ◽  
Proportional Integral Derivative ◽  
Dynamics Model ◽  
Lagrange Method ◽  
Quantum Neural Network

In this study, a control system was designed to control the robot's movement (The Mitsubishi RM-501 robot manipulator) based on the quantum neural network (QNN). A proposed method was used to solve the inverse kinematics in order to determine the angles values for the arm's joints when it follows through any path. The suggested method is the QNN algorithm. The forward kinematics was derived according to Devavit–Hartenberg representation. The dynamics model for the arm was modeled based on Lagrange method. The dynamic model is considered to be a very important step in the world of robots. In this study, two methods were used to improve the system response. In the first method, the dynamic model was used with the traditional proportional–integral–derivative (PID) controller to find its parameters (Kp, Ki, Kd) by using Ziegler Nichols method. In the second method, the PID parameters were selected depending on QNN without the need to a mathematical model of the robot manipulator. The results show a better response to the system when replacing the traditional PID controller with the suggested controller.

Establishment and comparison of a spatial dynamics model for virtual track train with different steering modes

2021 ◽  
pp. 146441932110240
Author(s):  
Zhonghui Yin ◽  
Jiye Zhang ◽  
Haiying Lu
Keyword(s):  
Pid Controller ◽  
Dynamic Performance ◽  
Spatial Dynamics ◽  
Steering System ◽  
Front Wheel ◽  
Proportional Integral Derivative ◽  
Dynamics Model ◽  
Proposed Model ◽  
Suspension Control ◽  
Curved Section

To solve the urbanization and the economic challenges, a virtual track train (VTT) transportation system has been proposed in China. To evaluate the dynamic behavior of the VTT, a spatial dynamics model has been developed that considers the suspension system and the steering system. Additionally, the model takes into account road irregularity to make simulations more realistic. Based on the newly proposed dynamic model and a designed proportional–integral–derivative (PID) controller, simulation frames of the vehicle and of the VTT are established with the path-tracking performance. The results show that the vehicle and the VTT can run along a desired lane with allowable errors, verifying the proposed model. The vehicle and VTT with the four-wheel steering system show a better dynamic performance than the models with the front-wheel steering system in the curved section. Moreover, the simulation frame can be further applied to dynamics-related assessments, parameter optimization and active suspension control strategy.

scholarly journals Inverse Kinematic Solution of 5R Manipulator using ANN and ANFIS

2015 ◽  
Vol 4 (2) ◽  
pp. 109
Author(s):  
Panchand Jha
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Inference System ◽  
Inverse Kinematics ◽  
Fuzzy Inference ◽  
Robot Manipulator ◽  
Ann Model ◽  
Inference System ◽  
Artificial Neural ◽  
Neural Fuzzy

<span>Inverse kinematics of manipulator comprises the computation required to find the joint angles for a given Cartesian position and orientation of the end effector. There is no unique solution for the inverse kinematics thus necessitating application of appropriate predictive models from the soft computing domain. Artificial neural network and adaptive neural fuzzy inference system techniques can be gainfully used to yield the desired results. This paper proposes structured artificial neural network (ANN) model and adaptive neural fuzzy inference system (ANFIS) to find the inverse kinematics solution of robot manipulator. The ANN model used is a multi-layered perceptron Neural Network (MLPNN). Wherein, gradient descent type of learning rules is applied. An attempt has been made to find the best ANN configuration for the problem. It is found that ANFIS gives better result and minimum error as compared to ANN.</span>

Study and Realization of a Prototype Octocopter System with PID Controller

2018 ◽  
Vol 10 (4) ◽  
Author(s):  
Saidi Hemza ◽  
Djebri Boualem
Keyword(s):  
Dynamic Model ◽  
Pid Controller ◽  
External Environment ◽  
Lagrangian Model ◽  
System Dynamic Model ◽  
Proportional Integral Derivative ◽  
Proportional Integral Derivative Controller ◽  
Proportional Integral ◽  
Euler Model ◽  
Electrical Components

In this work, the mechanical and electrical components are designed and realised for an octocopter. The designed system dynamic model is supported with Euler-Lagrangian model and Newton-Euler model respectively for the rotational and transnational movements of the drone. The prototype octocopter is also equipped with a proportional integral derivative controller to feedback both location and respond to the external environment.

Force Control of Robot Manipulator by Neural Network Model - Experiment and Evaluation of One-Degree-of-Freedom Manipulator -

1990 ◽  
Vol 2 (4) ◽  
pp. 273-281 ◽  
Author(s):  
Masatoshi Tokita ◽  
◽  
Toyokazu Mitsuoka ◽  
Toshio Fukuda ◽  
Takashi Kurihara ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Force Control ◽  
Pid Controller ◽  
Robot Manipulator ◽  
Force Sensor ◽  
Robotic Manipulator ◽  
The Neural Network ◽  
The Stability

In this paper, a force control of a robotic manipulator based on a neural network model is proposed with consideration of the dynamics of both the force sensor and objects. This proposed system consists of the standard PID controller, the gains of which are augmented and adjusted depending on objects through a process of learning. The authors proposed a similar method previously for the force control of the robotic manipulator with consideration of dynamics of objects, but without consideration of dynamics of the force sensor, showing only simulation results. This paper shows the similar structure of the controller via the neural network model applicable to the cases with consideration of both effects and demonstrates that the proposed method shows the better performance than the conventional PID type of controller, yielding to the wider range of applications, consequently. Therefore, this method can be applied to the force/compliance control problems. The effects of the number of neurons and hidden layers of the neural network model are also discussed through the simulation and experimental results as well as the stability of the control system.

Velocity and Force Observers for the Control of Robot Manipulators

2013 ◽  
Vol 135 (6) ◽  
Author(s):  
Marco A. Arteaga–Pérez ◽  
Juan C. Rivera–Dueñas ◽  
Alejandro Gutiérrez–Giles
Keyword(s):  
Dynamic Model ◽  
Tracking Control ◽  
Inverse Kinematics ◽  
Robot Manipulator ◽  
Robot Manipulators ◽  
Asymptotical Stability ◽  
Joint Angles ◽  
Force Tracking

In this paper, position/force tracking control for rigid robot manipulators interacting with its environment is considered. It is assumed that only joint angles are available for feedback, so that velocity and force observers are designed. The principle of orthogonalization is employed for this particular purpose and some of its main properties are fully exploited to guarantee local asymptotical stability. Only the force observer requires the dynamic model of the robot manipulator for implementation, and the scheme is developed directly in workspace coordinates, so that no inverse kinematics is required. The proposed approach is tested experimentally and compared with a well–known algorithm.

Obstacle avoidance inverse kinematics solution of redundant robots by neural networks

Robotica ◽  
1997 ◽  
Vol 15 (1) ◽  
pp. 3-10 ◽  
Author(s):  
Ziqiang Mao ◽  
T. C. Hsia
Keyword(s):  
Neural Network ◽  
Obstacle Avoidance ◽  
Inverse Kinematics ◽  
Robot Manipulator ◽  
Solution Technique ◽  
Training Algorithms ◽  
Neural Network Approach ◽  
Work Space ◽  
The Neural Network ◽  
Free Case

This paper investigates the neural network approach to solve the inverse kinematics problem of redundant robot manipulators in an environment with obstacles. The solution technique proposed requires only the knowledge of the robot forward kinematics functions and the neural network is trained in the inverse modeling manner. Training algorithms for both the obstacle free case and the obstacle avoidance case are developed. For the obstacle free case, sample points can be selected in the work space as training patterns for the neural network. For the obstacle avoidance case, the training algorithm is augmented with a distance penalty function. A ball-covering object modeling technique is employed to calculate the distances between the robot links and the objects in the work space. It is shown that this technique is very computationally efficient. Extensive simulation results are presented to illustrate the success of the proposed solution schemes. Experimental results performed on a PUMA 560 robot manipulator is also presented.

DESIGN, DYNAMIC MODELING AND CONTROL OF WEARABLE FINGER ORTHOSIS

2021 ◽  
pp. 2150006
Author(s):  
BEYDA TAŞAR ◽  
AHMET BURAK TATAR ◽  
ALPER KADIR TANYıLDıZı ◽  
OGUZ YAKUT
Keyword(s):  
Neurological Disorders ◽  
Pid Controller ◽  
Hand Function ◽  
Energy Costs ◽  
Proportional Integral Derivative ◽  
Lagrange Method ◽  
Modeling And Control ◽  
The World ◽  
Robotic Orthosis ◽  
And Control

Human hands and fingers are of significant importance in people’s capacity to perform daily tasks (touching, feeling, holding, gripping, writing). However, about 1.5 million people around the world are suffering from injuries, muscle and neurological disorders, a loss of hand function, or a few fingers due to stroke. This paper focuses on newly developed finger orthotics, which is thin, adaptable to the length of each finger and low energy costs. The aim of the study is to design and control a new robotic orthosis using for daily rehabilitation therapy. Kinematic and dynamic analysis of orthosis was calculated and the joint regulation of orthosis was obtained. The Lagrange method was used to obtain dynamics, and the Denavit–Hartenberg (D–H) method was used for kinematic analysis of hand. In order to understand its behavior, the robotic finger orthotics model was simulated in MatLab/Simulink. The simulation results show that the efficiency and robustness of proportional integral derivative (PID) controller are appropriate for the use of robotic finger orthotics.

scholarly journals PD-SVM Integrated Controller for Robotic Manipulator Tracking Control

2014 ◽  
Vol 2014 ◽  
pp. 1-6
Author(s):  
Neha Kapoor ◽  
Jyoti Ohri
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
System Performance ◽  
Tracking Control ◽  
Pid Controller ◽  
Robotic Manipulator ◽  
Support Vector ◽  
Proportional Integral Derivative ◽  
Proportional Integral ◽  
Noise Disturbances

Highly precise tracking of a robotic manipulator in presence of uncertainties like noise, disturbances, and friction has been addressed in this particular paper. An integrated proportional derivative and support vector machine (SVMPD) controller has been proposed for manipulator tracking. To illustrate the efficiency of the proposed controller, simulations have been done on a 2-DOF manipulator system. Performance of the proposed controller has been checked and verified with respect to to a simple PID controller and the radial bias neural network proportional integral derivative (RBNNPD) controller. It has been proved that the proposed controller can achieve better tracking performance as compared to other controllers as the range of errors is less and the time taken by the controller has reduced up to 14 times as compared to RBNN.

Sign in / Sign up

Export Citation Format

Share Document