Neural network controllers for robot manipulators application of damping neurons

Learning from adaptive neural output feedback control of robot manipulators

When a robot performs the same task repeatedly, a learning controller can enhance the performance of the system significantly. The function of the learning controller is to update the feedforward compensator which cancels the dynamics of robot manipulators and friction of each joints. The feedforward compensator especially plays an important role in the contact force control of robot manipulators with rigid workpiece since it allows more compliance in the force control direction as the force feedback gain is reduced. In this paper, the learning algorithm which guarantees the asymptotic stability is studied and applied to refine the feedforward compensator. Experiments with two degree of freedom direct drive robot confirm the effectiveness of the algorithm.

Magnetic levitation system is a typical nonlinear and instable system. Based on the complexity and inaccuracy of modelling, in this paper identified magnetic levitation system using the speciality that neural network(NN) can approach any nonlinear function. A Radial Basis Function neural network (RBFNN) controller is designed based on the neural network adaptive control principle. This paper proposes a control method which combine neural network adaptive control method and state feedback control method based on RBFNN. A simulation of the system is proposed, and the result shows that RBFNN could approach magnetic levitation system very well, neural network adaptive state feedback controller has a good effect on this nonlinear system; this control system has a preferable stability and control property.

The article proposes an estimator and command filtering-based adaptive neural network controller for the electrically driven flexible-joint robotic manipulators with output constraints under the circumstance of matched and mismatched disturbances in system dynamics. The presented method is designed based on electrically driven model of the n-link flexible-joint robotic manipulators, which introduces more uncertainties and increases the dimensionality of the system but is more in line with practical. In view of the properties of fast convergence speed and great estimation performance in radial basis function neural network, radial basis function neural network is used to approximate the internal uncertain dynamic parameters of the system. An observer-based estimator is introduced for estimating the matched and mismatched disturbances in flexible-joint robotic manipulator dynamics. As to the differential explosion problem in backstepping control design, this article utilizes second-order command filters to overcome it. This article also adopts barrier Lyapunov functions for implementing output constraint to consider security issues in practical use. For demonstrating the effectiveness of the proposed controller, numerical simulations on two-link flexible-joint robotic manipulators are conducted. On the basis of the comparisons among estimator and command filtering-based adaptive neural network controller and other advanced controllers, the superiorities of estimator and command filtering-based adaptive neural network controller in several areas are proved.

Neural network-based control of balanced robotic manipulators with joint flexibility

In this paper, a controller for robot manipulators is proposed to guarantee the tracking error of the systems bounded by predefined decreasing boundary. In this control scheme, a multi-layer neural network is used to approximate the unknown non-linear items, and the robustifying control term is used to compensate the approximation errors. The adaptive laws of weights of the neural network and robustifying control term are derived based on the Lyapunov stability analysis, so that, under appropriate assumptions, the transient and steady-state error bounds can be guaranteed. Compared with the existing work, the adaptable parameters in the proposed method do not need an off-line training procedure for better approximation. Simulations performed on a two-link robot manipulator illustrate the developed controller and demonstrate its performance.

This paper presents a comparative performance analysis of the control strategies for a two link planar robotic manipulator. In this work PD/PID computed torque control, filtered error approximation based adaptive control, and neural network (NN) control methods are considered for comparative performance analysis. The comparative analysis of the results demonstrates that the neural network controller gives the most effective results and confirms that the dynamical system can track the desired trajectory. The computer simulation is carried out using MATLAB and satisfactory results are presented which demonstrate the tracking capability and the effectiveness of the proposed control scheme.

Many advanced methods proposed for control of robot manipulators are based on the dynamic models of the robot systems. Model-based control design needs a correct dynamic model and precise parameters of the system. Practically speaking, however, every dynamic model has some degrees of incorrectness and every parameter associates with some degrees of identification error. The incorrectness and errors eventually result positioning or trajectory tracking errors, and even cause the system to be unstable. In the past two decades, intensive research activities have been devoted on the design of robust control systems and adaptive control systems for the robot in order to overcome the control system drawback caused by the model errors and uncertain parameters, and a great number of research results have been reported, for example, (Hsia, 1989), (Kou, and Wang, 1989), (Slotine and Li, 1989), ( Spong, 1992), and (Cheah, Liu and Slotine, 2006). However, almost parts of results associate with complicated control system design approaches and difficulties in the control system implementation for industrial robot manipulators. Recently, neural network technology attracts many attentions in the design of robot controllers. It has been pointed out that multi-layered neural network can be used for the approximation of any nonlinear function. Other advantages of the neural networks often cited are parallel distributed structure, and learning ability. They make such the artificial intelligent technology attractive not only in the application areas such as pattern recognition, information and graphics processing, but also in intelligent control of nonlinear and complicated systems such as robot manipulators (Sanger, 1994), (Kim and Lewis, 1999), (Kwan and Lewis, 2000), (Jung and Yim, 2001) (Yu and Wang, 2001). A new field in robot control using neural network technology is beginning to emerge to deal with the issues related to the dynamics in the robot control design. A neural network based dynamics compensation method has been proposed for trajectory control of a robot system (Jung and Hsia, 1996). A combined approach of neural network and sliding mode technology for both feedback linearization and control error compensation has been presented (Barambones and Etxebarria, 2002). Sensitivity of a neural network performance to learning rate in robot control has been investigated (Clark and Mills, 2000). In the following, we present a simple control system consisting of a traditional controller and a neural network controller with parallel structure for trajectory tracking control of 16

In this note, adaptive neural control is presented for a class of strict-feedback nonlinear systems with unknown time delays. Using appropriate Lyapunov-Krasovskii functionals, the uncertainties of unknown time delays are compensated for such that iterative backstepping design can be carried out. In addition, controller singularity problems are solved by using the integral Lyapunov function and employing practical robust neural network control. The feasibility of neural network approximation of unknown system functions is guaranteed over practical compact sets. It is proved that the proposed systematic backstepping design method is able to guarantee semiglobally uniformly ultimate boundedness of all the signals in the closed-loop system and the tracking error is proven to converge to a small neighborhood of the origin.

A direct-drive motor is an attractive actuator for a robot manipulator because of its high driving torque and accurate positioning abilities. The motion of a robot manipulator driven by a direct-drive motor is, however, strongly affected by inertial forces and nonlinear forces such as coliolis and centrifugal forces because it does not have any transmission mechanisms. It is, therefore, necessary to dynamically control the torque of the direct-drive motors in order to attain accurate motion of the robot manipulator. In this paper, the dynamics of a five-bar-link parallel direct-drive robot manipulator are analyzed. The torque control curves of the direct-drive motors for a three dimensional robot manipulator are derived. A new feedback method (learning control) is adopted, and the effects of the learning control on the motion of the direct-drive robot manipulator are investigated. The robot manipulator must be effective for machining and assembly when the torque is controlled with high accuracy.

Data-based adaptive neural network optimal output feedback control for nonlinear systems with actuator saturation

In this paper, adaptive neural network (NN) control is investigated for a class of multiinput and multioutput (MIMO) nonlinear systems with unknown bounded disturbances in discrete-time domain. The MIMO system under study consists of several subsystems with each subsystem in strict feedback form. The inputs of the MIMO system are in triangular form. First, through a coordinate transformation, the MIMO system is transformed into a sequential decrease cascade form (SDCF). Then, by using high-order neural networks (HONN) as emulators of the desired controls, an effective neural network control scheme with adaptation laws is developed. Through embedded backstepping, stability of the closed-loop system is proved based on Lyapunov synthesis. The output tracking errors are guaranteed to converge to a residue whose size is adjustable. Simulation results show the effectiveness of the proposed control scheme.

In the braking control of single rope winding hoisting systems (SRWHS), reasonable braking torque is of great significance in reducing the probability of significant hidden dangers such as overwinding, overspeeding, rope breaking, vibration, conveyance crash and so on. However, dynamic nonlinearity, time-varying disturbances, mechanical dynamic uncertainties and measurement noise severely affect the practical braking control performance. To address those problems, a neural adaptive braking torque controller with disturbance compensation is developed to enhance the braking performance for a single rope winding hoisting system in this paper. Firstly, considering the elastic of steel wire rope, the nonlinear braking model of the SRWHS is established using Lagrange equations and an extended state observer (ESO) is introduced to estimate the system’s unmeasured states and modelling error. Next, a neural adaptive controller is developed to estimate and compensate the mechanical dynamical disturbances resulted from friction forces and random external disturbances. Then, a neural adaptive network controller combined with the ESO (ESONAC) is designed to solve the modelling nonlinearity, time-varying disturbances and system’s unmeasurable states. Finally, the advantages of the ESONAC in improving the braking control performance of winding hoisting systems is verified by comparative experiments.

Model-based control such as computed torque control is frequently employed to ensure the accurate control of a robot manipulator. However, in some cases control performance is not satisfactory due to unmodeled nonlinearities or dynamics. To overcome this issue, this study investigates how using a quaternion neural network can adaptively compensate for the computed torque control. The control system consists of the quaternion neural network, feedforward model and feedback controller, resulting in a feedback error learning scheme utilised for the training of the quaternion neural network with a backpropagation algorithm extended to quaternion numbers. In computational experiments, the trajectory control of a three-link robot manipulator is performed using the proposed control system. Simulation results confirm the effectiveness of the quaternion neural network in practical control applications.

This article analyses the dynamic behaviour of a beam structure containing multiple transverse cracks using neural network controller. The first three natural frequencies and mode shapes have been calculated using theoretical, finite-element, and experimental analysis for the cracked and un-cracked beam. Comparisons of the results among theoretical, finite-element, and experimental analysis have also been presented. The calculated vibration signatures were used to train the feed-forward multi-layered neural network controller with back-propagation technique for the prediction of cracks. Relative crack locations and relative crack depths are the output of the neural controller. Results obtained from the various analyses are validated using the developed experimental set-up. Results from neural controller have been presented for comparison with the output from theoretical, finite-element, and experimental analysis. From the evaluation of the performance of the neural network controller it is observed that the developed method can be used as a crack diagnostic tool in the domain of dynamically vibrating structures.