Online RBF and fuzzy based sliding mode control of robot manipulator (original) (raw)
Related papers
ROBOT TRAJECTORY TRACKING WITH ADAPTIVE RBFNN-based FUZZY SLIDING MODE CONTROL
Due to computational burden and dynamic uncertainty, the classical model-based control approaches are hard to be implemented in the multivariable robotic systems. In this paper, a model-free fuzzy sliding mode control based on neural network is proposed. In classical sliding mode controllers, system dynamics and system parameters is required to compute the equivalent control. In Radial Basis Function Neural Network (RBFNN) based fuzzy sliding mode control, a RBFNN is developed to mimic the equivalent control law in the Sliding Mode Control (SMC). The weights of the RBFNN are changed for the system state to hit the sliding surface and slide along it with an adaptive algorithm. The initial weights of the RBFNN are set to zero and then tuned online, no supervised learning procedures are needed. In proposed method, by introducing the fuzzy concept to the sliding mode and fuzzifying the sliding surface, the chattering can be alleviated. The proposed method is implemented on industrial robot (Manutec-r15) and compared with a PID controller. Experimental studies carried out have shown that this approach is a good candidate for trajectory tracking applications of industrial robot.
Sliding mode control of nonlinear systems using Gaussian radial basis function neural network
IEEE Conference, 2001
In this paper, a novel method for driving the dynamics of a nonlinear system to a sliding mode is discussed. The approach is based on a sliding mode control methodology, i.e., the system under control is driven towards a sliding mode by tuning the parameters of the controller. In this loop, the parameters of the controller are adjusted such that a zero learning error level is reached in one dimensional phase space defined on the output of the controller. A Gaussian radial basis function neural network is used as the controller.
Sliding mode control of nonlinear systems using Gaussian radial basis function neural networks
2001
In this paper, a novel method for driving the dynamics of a nonlinear system to a sliding mode is discussed. The approach is based on a sliding mode control methodology, i.e., the system under control is driven towards a sliding mode by tuning the parameters of the controller. In this loop, the parameters of the controller are adjusted such that a zero learning error level is reached in one dimensional phase space defined on the output of the controller. A Gaussian radial basis function neural network is used as the controller.
Sequential Adaptive RBF-Fuzzy Variable Structure Control Applied to Robotics Systems
International Journal of Intelligent Systems and Applications, 2014
In this paper, we present a combination of sequential trained radial basis function networks and fuzzy techniques to enhance the variable structure controllers dedicated to robotics systems. In this aim, four RBFs networks were used to estimate the model based part parameters (Inertia, Centrifugal and Coriolis, Gravity and Friction matrices) of a variable structure controller so to respond to model variation and disturbances, a sequential online training algorithm based on Growing-Pruning "GAP" strategy and Kalman filter was implemented. To eliminate the chattering effect, the corrective control of the VS control was computed by a fuzzy controller. Simulations are carried out to control three degrees of freedom SCARA robot manipulator where the obtained results show good disturbance rejection and chattering elimination.
Neural Computing and Applications, 2016
Radial basis function network (RBFN) is used in this paper for predefined trajectory control of both one-link and two-link robotic manipulators. The updating equations for the RBFN parameters were derived using the gradient descent principle. The other advantage of using this principle is that it shows the clustering effect in distributing the radial centres. To increase the complexity, the dynamics of robotic manipulator is assumed to be unknown, and hence, simultaneous control and identification steps were performed using the RBFNs. The performance of the RBFN is compared with the multilayer feed-forward neural network (MLFFNN) in terms of mean square error, tolerance to disturbance and parameter variations in the system. The efficacy of RBFN as a controller and identification tool is verified by performing the simulation study, and the results obtained reveal the superior performance of RBFN over MLFFNN in both identification and control aspects for one-link and two-link robotic manipulators. Keywords Radial basis function networks Á One-link and two-link robotic manipulators Á Identification and adaptive control Á Multi layer feed-forward neural network Á Robustness
International Journal of Engineering and Advanced Technology, 2021
This paper briefly discusses about the Robust Controller based on Adaptive Sliding Mode Technique with RBF Neural Network (ASMCNN) for Robotic Manipulator tracking control in presence of uncertainities and disturbances. The aim is to design an effective trajectory tracking controller without any modelling information. The ASMCNN is designed to have robust trajectory tracking of Robot Manipulator, which combines Neural Network Estimation with Adaptive Sliding Mode Control. The RBF model is utilised to construct a Lyapunov function-based adaptive control approach. Simulation of the tracking control of a 2dof Robotic Manipulator in the presence of unpredictability and external disruption demonstrates the usefulness of the planned ASMCNN.
The neural network sliding mode controller based on multiple model for Robotic Manipulators
A Multi-model neural network sliding mode controller (MNNSMC) is proposed for robotic manipulator in this paper. The proposed MNNSMC scheme combining the SMC (sliding mode control) and neural network technique. The multi-model ensures that when the working environments of robotic manipulator are changeful, we can choose the proper model to get better control indicators. The controller applies the SMC to obtain high response and invariability to uncertainties and adopts neural network to estimate the switch gain in order to weaken the sliding mode chattering. The neural network is trained extensively with the state estimation error backpropagation learning algorithm. It consists of an input layer, hidden layer and output layer. Input layer of vector are errors and velocity errors and output layer of vector means to estimate the switch gain. In order to ensure the rationality of the switch, a new switching index is proposed which is a PID type with forgetting factor. The simulation results demonstrate the effectiveness and feasibility of the proposed control strategy.
International Journal of Advanced Robotic Systems, 2012
In the few last years, investigations in neural networks, fuzzy systems and their combinations become attractive research areas for modeling and controlling of uncertain systems. In this paper, we propose a new robust controller based on the integration of a Radial Base Function Neural Network (RBFNN) and an Interval Type-2 Fuzzy Logic (IT2FLC) for robot manipulator actuated by pneumatic artificial muscles (PAM). The proposed approach was synthesized for each joint using Sliding Mode Control (SMC) and named Radial Base Function Neural Network Type-2 Fuzzy Sliding Mode Control (RBFT2FSMC). Several objectives can be accomplished using this control scheme such as: avoiding difficult modeling, attenuating the chattering effect of the SMC, reducing the rules number of the fuzzy control, guaranteeing the stability and the robustness of the system, and finally handling the uncertainties of the system. The proposed control approach is synthesized and the stability of the robot using this controller was analyzed using Lyapunov theory. In order to demonstrate the efficiency of the RBFT2FSMC compared to other control technique, simulations experiments were performed using linear model with parameters uncertainties obtained after identification stage. Results show the superiority of the proposed approach compared to RBFNN Type-1 Fuzzy SMC. Finally, an experimental study of the proposed approach was presented using 2-DOF robot.
Adaptive Fuzzy-Neural Control Utilizing Sliding Mode Based Learning Algorithm for Robot Manipulator
This paper introduces an adaptive fuzzy-neural control (AFNC) utilizing sliding mode-based learning algorithm (SMBLA) for robot manipulator to track the desired trajectory. A traditional sliding mode controller is applied to ensure the asymptotic stability of the system, and the fuzzy rule-based wavelet neural networks (FWNNs) are employed as the feedback controllers. Additionally, a novel adaptation of the FWNNs parameters is derived from the SMBLA in the Lyapunov stability theorem. Hence, the AFNC approximates parameter variation, unmodeled dynamics, and unknown disturbances without the detailed knowledge of robot manipulator, while resulting in an improved tracking performance. Lastly, in order to validate the effectiveness of the proposed approach, the comparative simulation results of two-degrees of freedom robot manipulator are presented. Keywords – traditional sliding mode control (TSMC), adaptive fuzzy neural control (AFNC), fuzzy rule-based wavelet neural network (FWNN), sliding mode-based learning algorithm (SMBLA), degrees of freedom robot manipulator (DOFRM)