Decentralized neural network control for guaranteed tracking error constraint of a robot manipulator

Han, Seong-Ik; Lee, Jang-Myung

doi:10.1007/s12555-014-0132-2

Cited by 21 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…synthesis together with an adaptive fuzzy algorithm is incorporated in the conventional CTC to compensate uncertainties and approximate the errors. New control techniques such as neural network (Jolliffe 2002;Han and Lee 2015;Jin et al 2018;He et al 2017), intelligent systems (Song et al 2005;Dogan et al 2017), fuzzy adaptive control (Yang et al 2016), robust control (Jiang et al 2020;Rigatos et al 2017), and robust adaptive control (Chen et al 2016;Wu et al 2013;Dou and Wang 2013;Song et al 2005;Ahmadi and Fateh 2018;Dumlu 2018) have been also researched in the field of robot control with different strategies.…”

Section: Introductionmentioning

confidence: 99%

Manipulator Dynamic Nonlinearity Approximation Based on Polytopic LPV Modeling for Robot Tracking Control Problem

Fazli

Kazemi

2022

Iran J Sci Technol Trans Electr Eng

View full text Add to dashboard Cite

This article proposes a novel robot control strategy to compensate the robotic manipulator nonlinearity effects by applying the linear parameter-varying (LPV) modeling technique. A polytopic LPV description of the robot is created by the usual Lagrangian linearizing about an arbitrary complex full-scope trajectory. The principal component analysis is implemented for the parameter set mapping and generating a reduced polytopic LPV model to decrease the implementation complexity. An estimation of the required torque is calculated based on the constructed polytopic model to neutralize the nonlinear terms of the robot dynamics. The control gain matrix is involved in a set of linear matrix inequalities to sufficiently decrease the time derivative of a Lyapunov function. A sufficient condition ensures that the proposed controller stabilizes the polytopic LPV system against the torque estimation error. Finally, the proposed scheme is applied to the six-degree-offreedom PUMA560 manipulator for the tracking control problem.

show abstract

Section: Introductionmentioning

confidence: 99%

Manipulator Dynamic Nonlinearity Approximation Based on Polytopic LPV Modeling for Robot Tracking Control Problem

Fazli

Kazemi

2022

Iran J Sci Technol Trans Electr Eng

View full text Add to dashboard Cite

show abstract

“…It can find the local minimum fast enough, which is suitable for real-time approaches. RBFNN has also been developed to work with SMC controllers and implemented in many real applications [20][21][22]. RBFNN only contains three layers, one input layer, one hidden layer, and one output layer.…”

Section: Introductionmentioning

confidence: 99%

“…For the manipulator dynamics (2), if the sliding surface is chosen as(25), the controller(14, 34,36 ) ensures the closed-loop system asymptotically stable. Proof: We assume the perturbation estimation error of the SPO for the j-th joint as22…”

mentioning

confidence: 99%

Fast Fractional-Order Terminal Sliding Mode Control With RBFNN Based Sliding Perturbation Observer for 7-DOF Robot Manipulator

et al. 2021

View full text Add to dashboard Cite

A new perturbation estimator, using radial basis function (RBF) neural networks (RBFNN) to modify the sliding perturbation observer (SPO), is proposed with the fast fractional-order terminal sliding mode control (FFOTSMC). It aims to control a seven-degree-of-freedom (7-DOF) robot manipulator. The new perturbation estimator applies the data-driven method RBFNN to compensate for the estimation error in the conventional SPO for the first time. The modified SPO estimates the perturbation, which contains the disturbance, dynamic uncertainties, and modeling errors. The estimated perturbation is used to design with the FFOTSMC, which improves the tracking accuracy and reduces the chattering. The FFOTSMC was designed using the fractional-order derivative to design the sliding surface and the reaching/law for reaching the sliding surface. In experiments on the robot, the proposed estimation method has been evaluated by comparing with the conventional SPO or only RBFNN with the same controller, FFOTSMC. The asymptotic stability of the controller with the new estimator is proved using Lyapunov functions for fractional-order systems.

show abstract

“…For teleoperation systems with error constrained, Yang et al investigated the control strategy by transforming synchronization errors to a new form and then using a terminal sliding‐mode–based finite‐time control method to ensure finite‐time convergence for the synchronization errors. Based on a new constrained error variable and RBFNN, Han and Lee put forward a position tracking protocol, by which the transient and steady‐state performances of the systems were improved.…”

Section: Introductionmentioning

confidence: 99%

Distributed finite‐time containment control for multiple Euler‐Lagrange systems with communication delays

Chen

Sun

et al. 2018

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

Summary In this paper, distributed finite‐time containment control for multiple Euler‐Lagrange systems with communication delays and general disturbances is investigated under directed topology by using sliding‐mode control technique. We consider that the information of dynamic leaders can be obtained by only a portion of the followers. Firstly, a nonsingular fast terminal sliding surface is selected to achieve the finite‐time convergence for the error variables. Then, a distributed finite‐time containment control algorithm is proposed where the neural network is utilized to approximate the model uncertainties and external disturbances of the systems. Furthermore, considering that error constraint method can improve the performance of the systems, a distributed finite‐time containment control algorithm is developed by transforming the error variable into another form. It is demonstrated that the containment errors are bounded in finite time by using Lyapunov theory, graph theory, and finite‐time stability theory. Numerical simulations are provided to show the effectiveness of the proposed methods.

show abstract

Decentralized neural network control for guaranteed tracking error constraint of a robot manipulator

Cited by 21 publications

References 16 publications

Manipulator Dynamic Nonlinearity Approximation Based on Polytopic LPV Modeling for Robot Tracking Control Problem

Manipulator Dynamic Nonlinearity Approximation Based on Polytopic LPV Modeling for Robot Tracking Control Problem

Fast Fractional-Order Terminal Sliding Mode Control With RBFNN Based Sliding Perturbation Observer for 7-DOF Robot Manipulator

Distributed finite‐time containment control for multiple Euler‐Lagrange systems with communication delays

Contact Info

Product

Resources

About