Vikas Panwar

Neural network-based nonlinear tracking control of kinematically redundant robot manipulators

In this paper, neural network-based nonlinear dynamical control of kinematically redundant robot manipulators is considered. The neural network-based controller achieves end-effector trajectory tracking as well as subtask tracking effectively. A feedforward neural network is employed to learn the parametric uncertainties, existing in the dynamical model of the robot manipulator. The whole system is shown to be stable in the sense of Lyapunov. Numerical simulation studies are carried out for a 3R planar robot manipulator to show the effectiveness of the control scheme.

Adaptive neuro fuzzy based hybrid force/position control for an industrial robot manipulator

In this paper an ANFIS-PD+I (AFSPD+I) based hybrid force/position controller has been proposed which works effectively with unspecified robot dynamics in the presence of external disturbances. A constraint is put to limit the movement of manipulator in XY Cartesian coordinates. The validity of the proposed controller has been tested using a 6-degree of freedom PUMA robot manipulator. The performance comparison have been done with the fuzzy proportional derivative plus integral, fuzzy proportional integral derivative and conventional proportional integral derivative controllers subjected to the same data set with proposed controller. The projected AFSPD+I controller adhered to the desired path closer and smoother than the other mentioned controllers.

Adaptive neural controller for space robot system with an attitude controlled base

In this paper, an adaptive neural network-based controller is proposed for a space robot system with an attitude controlled base without joint acceleration measurements and in the presence of parametric uncertainties and external disturbances. Based on the dynamic model, a neural network-based controller is proposed that achieves the required tracking effectively. A feedforward neural network is employed to learn the existing unknown dynamics of robot system. The uniform ultimate boundedness of all signals in the closed-loop system is guaranteed by the Lyapunov approach. It is shown that the neural network can cope with the unknown nonlinearities through the adaptive learning process and requires no preliminary off learning. Finally, simulation study has been performed to evaluate the controller performance.

Enhancing precision performance of trajectory tracking controller for robot manipulators using RBFNN and adaptive bound

In this paper the design issues of trajectory tracking controller for robot manipulators are considered. The performance of classical model based controllers is reduced due to the presence of inherently existing uncertainties in the dynamic model of the robot manipulator. An intermediate approach between model based controllers and neural network based controllers is adopted to enhance the precision of trajectory tracking. The performance of the model based controller is enhanced by adding an RBF neural network and an adaptive bound part. The controller is able to learn the existing structured and unstructured uncertainties in the system in online manner. The RBF network learns the unknown part of the robot dynamics with no requirement of the offline training. The adaptive bound part is used to estimate the unknown bounds on unstructured uncertainties and neural network reconstruction error. The overall system is proved to be asymptotically stable. Finally, the numerical simulation results are produced with various controllers and the effectiveness of the proposed controller is shown in a comparative study for the case of a Microbot type robot Manipulator.

Neural Network Control of Coordinated Multiple Manipulator Systems

This paper proposes a neural network (NN) based control scheme for coordinated multiple robot manipulators carrying a common object. Firstly, an integrated dynamic model of the manipulators and the object is derived in terms of object position and orientation as states of the derived model. Based on this model a controller is proposed that achieves the stability in the sense of Lyapunov for the trajectory tracking of the object as well as tracking of the desired internal forces arising in the system. A feedforward neural network is employed to learn the unknown dynamics of robot manipulators and the object. Finally, numerical simulation studies are carried for two three-link planar manipulators moving a circular disc on specified trajectory

Control of mobile robot for trajectory tracking by sliding mode control technique

In this paper sliding mode controller is presented for the trajectory tracking by wheel mobile robot. Kinematic and dynamic model of mobile robot are derived using Lagrangian formulation. To achieve the desired trajectory tracking an auxiliary velocity controller is proposed based on the available error between the auxiliary velocity and actual velocity of wheel mobile robot. Sliding mode controller is proposed to produce the required torque signal at the wheels of mobile robot. The overall controller is shown to be asymptotically stable using Lyapunov stability theory. The errors of the system are shown to converge to zero. Finally the simulation result are presented to validate the proposed controller.

Intelligent control of space robot system using RBF neural network

In this paper, an intelligent controller is proposed for a space robot system with an attitude controlled base without joint acceleration measurements. The controller consists of computed torque type part, RBF neural network and an adaptive controller. The controller achieves the required tracking effectively. The controller is able to learn the existing structured and unstructured uncertainties in the system in online manner. The RBF network learns the unknown part of the space robot system dynamics with no requirement of the offline training. The adaptive controller is used to estimate the unknown bounds on unstructured uncertainties and neural network reconstruction error. The overall system is proved to be asymptotically stable in the sense of Lyapunov. Finally numerical simulation studies are performed to evaluate the controller performance.

Wavelet neural network-based H ∞ trajectory tracking for robot manipulators using fast terminal sliding mode control

Robotica / FirstView Article / July 2016, pp 1 16 DOI: 10.1017/S0263574716000278, Published online: 13 May 2016 Link to this article: http://journals.cambridge.org/abstract_S0263574716000278 How to cite this article: Vikas Panwar Wavelet neural network-based H∞ trajectory tracking for robot manipulators using fast terminal sliding mode control. Robotica, Available on CJO 2016 doi:10.1017/S0263574716000278 Request Permissions : Click here