Learning of inverse-dynamics and inverse-kinematics for two-link SCARA robot using neural networks

2007 ◽  
Author(s):  
Ken Onozato ◽  
Yutaka Maeda
Keyword(s):  
Neural Networks ◽  
Inverse Kinematics ◽  
Inverse Dynamics ◽  
Scara Robot

Effects of Dynamic Model Errors in Task-Priority Operational Space Control

Robotica ◽  
2021 ◽  
pp. 1-12
Author(s):  
Paolo Di Lillo ◽  
Gianluca Antonelli ◽  
Ciro Natale
Keyword(s):  
Inverse Kinematics ◽  
Degrees Of Freedom ◽  
Inverse Dynamics ◽  
Null Space ◽  
Control Algorithms ◽  
Model Errors ◽  
Operational Space ◽  
Dynamic Level ◽  
Concurrent Tasks ◽  
Modeling Errors

SUMMARY Control algorithms of many Degrees-of-Freedom (DOFs) systems based on Inverse Kinematics (IK) or Inverse Dynamics (ID) approaches are two well-known topics of research in robotics. The large number of DOFs allows the design of many concurrent tasks arranged in priorities, that can be solved either at kinematic or dynamic level. This paper investigates the effects of modeling errors in operational space control algorithms with respect to uncertainties affecting knowledge of the dynamic parameters. The effects on the null-space projections and the sources of steady-state errors are investigated. Numerical simulations with on-purpose injected errors are used to validate the thoughts.

Decentralized adaptive tracking control for high-order interconnected stochastic nonlinear time-varying delay systems with stochastic input-to-state stable inverse dynamics by neural networks

2019 ◽  
Vol 41 (13) ◽  
pp. 3612-3625 ◽  
Author(s):  
Wang Qian ◽  
Wang Qiangde ◽  
Wei Chunling ◽  
Zhang Zhengqiang
Keyword(s):  
Neural Networks ◽  
Tracking Control ◽  
Large Scale ◽  
Inverse Dynamics ◽  
Small Neighborhood ◽  
High Order ◽  
Interconnected Systems ◽  
Delay Systems ◽  
Rbf Neural Networks ◽  
Stochastic Input

The paper solves the problem of a decentralized adaptive state-feedback neural tracking control for a class of stochastic nonlinear high-order interconnected systems. Under the assumptions that the inverse dynamics of the subsystems are stochastic input-to-state stable (SISS) and for the controller design, Radial basis function (RBF) neural networks (NN) are used to cope with the packaged unknown system dynamics and stochastic uncertainties. Besides, the appropriate Lyapunov-Krosovskii functions and parameters are constructed for a class of large-scale high-order stochastic nonlinear strong interconnected systems with inverse dynamics. It has been proved that the actual controller can be designed so as to guarantee that all the signals in the closed-loop systems remain semi-globally uniformly ultimately bounded, and the tracking errors eventually converge in the small neighborhood of origin. Simulation example has been proposed to show the effectiveness of our results.

Kinematics and Dynamics of a Parallel Manipulator With Woven Joints

1993 ◽  
Author(s):  
Hyunsok Pang
Keyword(s):  
Lagrange Multipliers ◽  
Kinematic Analysis ◽  
Inverse Kinematics ◽  
Parallel Manipulator ◽  
Inverse Dynamics ◽  
Numerical Technique ◽  
Vector Analysis ◽  
Kinematics And Dynamics ◽  
Governing Equations ◽  
Numerical Examples

Abstract Presented is an analysis of the kinematics and the inverse dynamics of a proposed three DOF parallel manipulator resembling the Stewart platform in a general form. In the kinematic analysis, the inverse kinematics, velocity and acceleration analyses are performed, respectively, using vector analysis and general homogeneous transformations. An algorithm to solve the inverse dynamics of the proposed parallel manipulator is then presented using a Lagrangin technique. In this case, it is found that one should introduce and subsequently eliminate Lagrange multipliers in order to arrive at the governing equations. Numerical examples are finally carried out to examine the validity of the approach and the accuracy of the numerical technique employed. The trajectory of motion of the manipulator is also performed using a cubic spline.

Inverse kinematics and inverse dynamics for control of a biped walking machine

1993 ◽  
Vol 10 (4) ◽  
pp. 531-555 ◽  
Author(s):  
Ching-Long Shih ◽  
William A. Gruver ◽  
Tsu-Tian Lee
Keyword(s):  
Inverse Kinematics ◽  
Inverse Dynamics ◽  
Biped Walking ◽  
Walking Machine

DELTA: a simple and efficient parallel robot

Robotica ◽  
1990 ◽  
Vol 8 (2) ◽  
pp. 105-109 ◽  
Author(s):  
F. Pierrot ◽  
C. Reynaud ◽  
A. Fournier
Keyword(s):  
Inverse Kinematics ◽  
Research Team ◽  
Dynamic Models ◽  
Inverse Dynamics ◽  
Parallel Robot ◽  
Parallel Robots ◽  
Kinematic Parameters ◽  
Mechanical Structure ◽  
Serial Robots ◽  
École Polytechnique

SummaryThe DELTA parallel robot, designed by an EPFL (Ecole Polytechnique Fédérale de Lausanne) research team, is a mechanical structure which has the advantage of parallel robots and ease of serial robots modeling. This paper presents solutions for a complete modeling of the DELTA parallel robot (direct and inverse kinematics, inverse statics, inverse dynamics), with few arithmetic and trigonometric operations. Our method is based on a satisfactory choice of kinematic parameters and on a few restricting hypotheses for the static and dynamic models. We give some details of each model, we present some computation results and we put the emphasis on some particular points, showing the capabilities of this mechanical structure.

Optimisation of Engineering Systems With the Bees Algorithm

2018 ◽  
Vol 8 (1) ◽  
pp. 1-15 ◽  
Author(s):  
Duc T Pham ◽  
Luca Baronti ◽  
Biao Zhang ◽  
Marco Castellani
Keyword(s):  
Neural Networks ◽  
Inverse Kinematics ◽  
State Of The Art ◽  
Bees Algorithm ◽  
Engineering Systems ◽  
Standard Formulation ◽  
First Case ◽  
Engineering Problems ◽  
Hydraulic Load ◽  
Optimisation Technique

This article describes the Bees Algorithm in standard formulation and presents two applications to real-world continuous optimisation engineering problems. In the first case, the Bees Algorithm is employed to train three artificial neural networks (ANNs) to model the inverse kinematics of the joints of a three-link manipulator. In the second case, the Bees Algorithm is used to optimise the parameters of a linear model used to approximate the torque output for an electro-hydraulic load system. In both cases, the Bees Algorithm outperformed the state-of-the-art in the literature, proving to be an effective optimisation technique for engineering systems.

An investigation into the use of neural networks for the semi-active control of a magnetorheologically damped vehicle suspension

2010 ◽  
Vol 224 (7) ◽  
pp. 829-848 ◽  
Author(s):  
H Metered ◽  
P Bonello ◽  
S O Oyadiji
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Inverse Dynamics ◽  
Ride Comfort ◽  
Mr Damper ◽  
Performance Criteria ◽  
Vehicle Suspension ◽  
Neural Network Controller ◽  
Road Disturbance ◽  
Continuous State

Neural networks are highly useful for the modelling and control of magnetorheological (MR) dampers. A damper controller based on a recurrent neural network (RNN) of the inverse dynamics of an MR damper potentially offers significant advantages over conventional controllers in terms of reliability and cost through the minimal use of sensors. This paper introduces a neural-network-based MR damper controller for use in conjunction with the system controller of a semi-active vehicle suspension. A mathematical model of a semi-active quarter-vehicle suspension using an MR damper is derived. Control performance criteria are evaluated in the time and frequency domains in order to quantify the suspension effectiveness under bump and random road disturbance. Studies using the modified Bouc—Wen model for the MR damper as well as an actual damper fitted in a hardware-in-the-loop simulation (HILS) both showed that the inverse RNN damper controller potentially offers a significantly superior ride comfort and vehicle stability over a conventional MR damper controller based on continuous-state control. The neural network controller produces a smoother and lower input voltage to the MR damper coil, ensuring extended damper life and lower power requirement respectively. Further studies performed using an RNN model of the forward dynamics of the MR damper showed that it is a reliable substitute for HILS for validating multi-damper control applications.

Adaptive control of a robot using neural networks

Robotica ◽  
1994 ◽  
Vol 12 (6) ◽  
pp. 553-561 ◽  
Author(s):  
D. T. Pham ◽  
S. J. Oh
Keyword(s):  
Neural Networks ◽  
Adaptive Control ◽  
Control System ◽  
Inverse Dynamics ◽  
Dynamic Interaction ◽  
Variable Load ◽  
Time Varying ◽  
Adaptive Control System ◽  
The Third ◽  
Articulated Robot

SummaryThis paper describes an adaptive control system for an articulated robot with n joints carrying a variable load. The robot is a complex nonlinear time-varying MIMO plant with dynamic interaction between its inputs and outputs. However, the design of the control system is relatively straightforward and does not require any prior knowledge about the plant. This is because the control system is based on using neural networks which can capture the dynamic characteristics of the plant automatically. Three neural networks are employed in total, the first to learn the dynamics of the robot, the second to model its inverse dynamics and the third, a copy of the second neural network, to control the robot.

Sign in / Sign up

Export Citation Format

Share Document