Neural network-based sliding mode adaptive control for robot manipulators

Adaptive Robust Control of Uncertain Euler-Lagrange Systems Using Gaussian Processes

This article proposes a novel adaptive robust control approach based on Gaussian processes (GPs) for the high-precision tracking problem of uncertain Euler-Lagrange (EL) systems with time-varying external disturbances. Given a prior dynamic model, the GP regression (GPR) technique is employed to obtain a nonparametric data-based uncertainty model, including its probabilistic confidence intervals. Based on the adaptive sliding mode control (ASMC) framework, the posterior means of GPs are utilized for dynamic compensation, whereas the posterior variances are applied to adjust the feedback gains. This proposed control strategy is robust against significant system uncertainty with low feedback gains. A novel adaptive law for updating hyperparameters based on tracking error feedback is presented, thereby improving the performance of both tracking control and GP modeling simultaneously. Compared to existing likelihood-based optimization methods, this hyperparameter adaptive law enables data-efficient and fast uncertainty learning for control applications. The proposed control strategy guarantees the semiglobal asymptotic convergence to zero tracking error with a specified probability. Simulations using an underwater robot model demonstrate that the utilization of GPs and hyperparameter adaptive law significantly improves the performance of tracking control and uncertainty learning.

Finite-time adaptive super-twisting sliding mode control for autonomous robotic manipulators with actuator faults

This paper proposes a new adaptive super-twisting global integral terminal sliding mode control algorithm for the trajectory tracking of autonomous robotic manipulators with uncertain parameters, unknown disturbances, and actuator faults. Firstly, a novel global integral terminal sliding mode surface is designed to ensure that the tracking errors of autonomous robotic manipulators converge to zero in finite time and the global robustness of the system is also enhanced. Then a new adaptive method is devised to deal with the adverse effect of nonlinear uncertainty. To suppress the chattering phenomenon, the adaptive super-twisting algorithm is used in this paper, which can ensure that the control torque is a continuous input signal. Based on the adaptive mechanism, the adaptive super-twisting global integral terminal sliding mode controller is developed to provide superior control performance. The stability analysis of the system is demonstrated by using the Lyapunov method. Ultimately, the effectiveness of the control scheme is confirmed by a simulation study.

Neural network-based adaptive second-order sliding mode control for uncertain manipulator systems with input saturation

In order to solve the trajectory tracking problem for robotic manipulators with dynamic uncertainty, external disturbance and input saturation, a novel second-order sliding mode control scheme based on neural network is proposed in this paper. First of all, a model-based second-order non-singular fast terminal sliding mode controller (SONFTSMC) is designed to overcome the chattering problem under the consideration of uncertain parameters. Then attention is focused on the scenario that all those nonlinear uncertainties are unknown, and a new fuzzy wavelet neural network (FWNN) is designed to estimate those unknown uncertainties via lumping them into one compounded uncertainty. In addition, all parameters in FWNN are adjusted autonomously by using an adaptive method. The proposed second-order non-singular fast terminal sliding mode (SONFTSM) control method not only improves the convergence speed and tracking accuracy of the robotic manipulator, but also enhances its robustness. Finally, the advantages of SONFTSM control strategy over existing sliding mode control methods are verified with comparative simulations.

Switching Neural Network Control for Underactuated Spacecraft Formation Reconfiguration in Elliptic Orbits

A switching neural network control scheme, consisting of the adaptive neural network controller and sliding mode controller, is proposed for underactuated formation reconfiguration in elliptic orbits with the loss of either the radial or in-track thrust. By using the inherent coupling of system states, the switching neural network technique is then adopted to estimate the unmatched disturbances and design the underactuated controller to achieve underactuated formation reconfiguration with high precision. The adaptive neural network controller works in the active region, and the disturbances composed of linearization errors and external perturbations are approximated by radial basis function neural networks. The adaptive sliding mode controller works outside the active region, and the upper bound of the approximation errors is estimated by the adaptation law. The stability of the closed-loop control system is proved via the Lyapunov-based approach. The numerical simulation results have demonstrated the rapid, high-precision and robust performance of the proposed controller compared with the linear sliding mode controller.

Neural-Network-Based Sliding-Mode Control of an Uncertain Robot Using Dynamic Model Approximated Switching Gain

In this article, a new neural-network-based sliding-mode control (SMC) of an uncertain robot is presented. The distinguishing characteristic of the proposed control scheme is that the switching gain is designed as a dynamic model approximated value, which is handled by using the neural-network strategy to adapt the unknown dynamics and disturbances. In the presented control scheme, the modeling information of the robotic system is not required and only one parameter is required to be estimated in each joint of the robotic system. Subsequently, the Lyapunov method is utilized to prove that the trajectory tracking errors will eventually converge to a neighborhood of zero. Finally, the contrast simulation studies reveal that with the proposed control scheme, the problems of chattering and high-speed switching of control input, which takes place in a conventional SMC, can be addressed, and a satisfactory control precision is guaranteed.

Industrial Robot Trajectory Tracking Control Using Multi-Layer Neural Networks Trained by Iterative Learning Control

Fast and precise robot motion is needed in many industrial applications. Most industrial robot motion controllers allow externally commanded motion profiles, but the trajectory tracking performance is affected by the robot dynamics and joint servo controllers, to which users have no direct access and about which they have little information. The performance is further compromised by time delays in transmitting the external command as a setpoint to the inner control loop. This paper presents an approach for combining neural networks and iterative learning controls to improve the trajectory tracking performance for a multi-axis articulated industrial robot. For a given desired trajectory, the external command is iteratively refined using a high-fidelity dynamical simulator to compensate for the robot inner-loop dynamics. These desired trajectories and the corresponding refined input trajectories are then used to train multi-layer neural networks to emulate the dynamical inverse of the nonlinear inner-loop dynamics. We show that with a sufficiently rich training set, the trained neural networks generalize well to trajectories beyond the training set as tested in the simulator. In applying the trained neural networks to a physical robot, the tracking performance still improves but not as much as in the simulator. We show that transfer learning effectively bridges the gap between simulation and the physical robot. Finally, we test the trained neural networks on other robot models in simulation and demonstrate the possibility of a general purpose network. Development and evaluation of this methodology are based on the ABB IRB6640-180 industrial robot and ABB RobotStudio software packages.

Trajectory tracking control for chain-series robot manipulator: Robust adaptive fuzzy terminal sliding mode control with low-pass filter

This article investigates a difficult problem which focuses on the external disturbance and dynamic uncertainty in the process of trajectory tracking. This article presents a robust adaptive fuzzy terminal sliding mode controller with low-pass filter. The low-pass filter can provide smooth position and speed signals. The fuzzy terminal sliding mode controller can achieve fast convergence and desirable tracking precision. Chattering is eliminated with continuous control law, due to high-frequency switching terms contained in the first derivative of actual control signals. Ignoring the prior knowledge upper bound, the controller can reduce the influence of the uncertain kinematics and dynamics in the actual situation. Finally, the experiment is carried out and the results show the performance of the proposed controller.

A Critical Review of Control Techniques for Flexible and Rigid Link Manipulators

There is a high demand for developing effective controllers to perform fast and accurate operations for either flexible link manipulators (FLMs) or rigid link manipulators (RLMs). Thus, this paper is beneficial for such vast field, and it is also advantageous and indispensable for researchers who are interested in robotics to have sufficient knowledge about various controllers of FLMs and RLMs as the controllers’ concepts are elaborated in detail. The paper concentrates in critically reviewing classical controllers, intelligent controllers, robust controllers, and hybrid controllers for both FLMs and RLMs. The advantages and disadvantages of the aforementioned control methods are summarized in this paper; it also has a detailed comparison for the controllers in terms of the design difficulty, performance, and the suitability for controlling FLMs or RLMs.

A global time-varying sliding-mode control for the tracking problem of uncertain dynamical systems

In this paper, a global time-varying sliding-mode control scheme with prespecified convergence time is proposed for the tracking problem of a class of uncertain nonlinear systems under parameters uncertainties and external disturbances. Firstly, a novel time-varying sliding manifold with appropriate coefficients is presented. These coefficients are tuned to eliminate the reaching phase and to drive the system states to the equilibrium in a specified time. Hence, the system states are constrained to the sliding surface from the beginning of the motion which enables the global robustness, the reduction of the initial control effort, and the meet of the convergence time requirement. Moreover, in order to address the more practical case that the upper bound of the system uncertainties and disturbances is unavailable, an adaptive time-varying sliding mode control algorithm is derived, by which the tracking error vanish as time tends to infinity. The stability of the system has been proved by the Lyapunov stability theorem, and simulation studies are conducted to show the effectiveness of the suggested control schemes.

Adaptive neural network based position tracking control for Dual-master/Single-slave teleoperation system under communication constant time delays

The novel trajectory tracking control strategies for trilateral teleoperation systems with Dual-master/Single-slave robot manipulators under communication constant time delays are proposed in this article. By incorporating this design technique into the neural network (NN) based adaptive control framework, two controllers are designed for the trilateral teleoperation systems in free motion. First, with acceleration measurements, an adaptive controller under the synchronization variables containing the position and velocity error is constructed to guarantee the position and velocity tracking errors between the trilateral teleoperation systems asymptotically converge to zero. Second, without acceleration measurements, an adaptive controller under the new synchronization variables is presented such that the trilateral teleoperation systems can obtain the same trajectory tracking performance as the first controller. Third, in term of establishing suitable Lyapunov-Krasovskii functionals, the asymptotic tracking performances of the trilateral teleoperation systems can be derived independent of the communication constant time delays. Moreover, these two controllers are obtained without the knowledge of upper bounds of the NN approximation errors, respectively. Finally, simulation results are presented to demonstrate the validity of the proposed methods.

A Neural Network Based Sliding Mode Control for Tracking Performance with Parameters Variation of a 3-DOF Manipulator

The manipulator, in most cases, works in unstructured and changeable conditions. With large external variations, the demand for stability and robustness must be ensured. This paper proposes a neural network sliding mode control (NNSMC) to cope with uncertainties and improve the behavior of the robotic manipulator in the presence of an external disturbance. The proposed method is applied to the three degrees of freedom (DOF) manipulator. Some comparisons between the proposed and the conventional algorithms are given in both simulation and experiments to prove that the designed control can achieve higher accuracy in tracking motion.

Development of an adaptive radial basis function neural network estimator-based continuous sliding mode control for uncertain nonlinear systems

In this paper an adaptive neural network (NN)-based nonlinear controller is proposed for trajectory tracking of uncertain nonlinear systems. The adopted control algorithm combines a continuous second-order sliding mode control (CSOSMC), the radial basis function neural network (RBFNN) and the adaptive control methodology. First, a second-order sliding mode control scheme (SOSMC), which is published recently in literature for linear uncertain systems, is extended for nonlinear uncertain systems. Second, an adaptive radial basis function neural network estimator-based continuous second order sliding mode control algorithm (CSOSMC-ANNE) is adopted. In CSOSMC-ANNE control methodology, a radial basis function neural network with adaptive parameters is exploited to approximate the unknown system parameters and improve performance against perturbations. Also, the discontinuous switching control of SOSMC is supplanted with a smooth continuous control action to completely eliminate the chattering phenomenon. The convergence and global stability of the closed-loop system are proved using Lyapunov stability method. Numerical computer simulations, with dynamical model of the nonlinear inverted pendulum system, are presented to demonstrate the effectiveness and advantages of the presented control scheme.

A Reinforcement Learning Neural Network for Robotic Manipulator Control

We propose a neural network model for reinforcement learning to control a robotic manipulator with unknown parameters and dead zones. The model is composed of three networks. The state of the robotic manipulator is predicted by the state network of the model, the action policy is learned by the action network, and the performance index of the action policy is estimated by a critic network. The three networks work together to optimize the performance index based on the reinforcement learning control scheme. The convergence of the learning methods is analyzed. Application of the proposed model on a simulated two-link robotic manipulator demonstrates the effectiveness and the stability of the model.

Adaptive nonsingular fast terminal sliding-mode control for the tracking problem of uncertain dynamical systems

In this paper, robust and adaptive nonsingular fast terminal sliding-mode (NFTSM) control schemes for the trajectory tracking problem are proposed with known or unknown upper bound of the system uncertainty and external disturbances. The developed controllers take the advantage of the NFTSM theory to ensure fast convergence rate, singularity avoidance, and robustness against uncertainties and external disturbances. First, a robust NFTSM controller is proposed which guarantees that sliding surface and equilibrium point can be reached in a short finite-time from any initial state. Then, in order to cope with the unknown upper bound of the system uncertainty which may be occurring in practical applications, a new adaptive NFTSM algorithm is developed. One feature of the proposed control law is their adaptation techniques where the prior knowledge of parameters uncertainty and disturbances is not needed. However, the adaptive tuning law can estimate the upper bound of these uncertainties using only position and velocity measurements. Moreover, the proposed controller eliminates the chattering effect without losing the robustness property and the precision. Stability analysis is performed using the Lyapunov stability theory, and simulation studies are conducted to verify the effectiveness of the developed control schemes.

Adaptive Neural Synchronization Control for Bilateral Teleoperation Systems With Time Delay and Backlash-Like Hysteresis

This paper considers the master and slave synchronization control for bilateral teleoperation systems with time delay and backlash-like hysteresis. Based on radial basis functions neural networks' approximation capabilities, two improved adaptive neural control approaches are developed. By Lyapunov stability analysis, the position and velocity tracking errors are guaranteed to converge to a small neighborhood of the origin. The contributions of this paper can be summarized as follows: 1) by using the matrix norm established using the weight vector of neural networks as the estimated parameters, two novel control schemes are developed and 2) the hysteresis inverse is not required in the proposed controllers. The simulations are performed, and the results show the effectiveness of the proposed method.

Robust stabilizing control of nonholonomic systems with uncertainties via adaptive integral sliding mode

This article presents a robust stabilizing control for nonholonomic underwater systems that are affected by uncertainties. The methodology is based on adaptive integral sliding mode control. Firstly, the original underwater system is transformed in a way that the new system has uncertainties in matched form. A change of coordinates is carried out for this purpose, and the nonholonomic system is transformed into chained form system with matched uncertainties. Secondly, the chained form system with uncertainties is transformed into a special structure containing nominal part and some unknown terms through input transformation. The unknown terms are computed adaptively. Afterward, the transformed system is stabilized using integral sliding mode control. The stabilizing controller for the transformed system is constructed which consists of the nominal control plus some compensator control. The compensator controller and the adaptive laws are derived in a way that the derivative of a suitable Lyapunov function becomes strictly negative. Two different cases of perturbation are considered including the bounded uncertainty present in any single control input and the uncertainties present in the overall system model of the underwater vehicle. Finally, simulation results show the validity and correctness of the proposed controllers for both cases of nonholonomic underwater system affected by uncertainties.

Finite-time sliding surface constrained control for a robot manipulator with an unknown deadzone and disturbance

This paper presents finite-time sliding mode control (FSMC) with predefined constraints for the tracking error and sliding surface in order to obtain robust positioning of a robot manipulator with input nonlinearity due to an unknown deadzone and external disturbance. An assumed model feedforward FSMC was designed to avoid tedious identification procedures for the manipulator parameters and to obtain a fast response time. Two constraint switching control functions based on the tracking error and finite-time sliding surface were added to the FSMC to guarantee the predefined tracking performance despite the presence of an unknown deadzone and disturbance. The tracking error due to the deadzone and disturbance can be suppressed within the predefined error boundary simply by tuning the gain value of the constraint switching function and without the addition of an extra compensator. Therefore, the designed constraint controller has a simpler structure than conventional transformed error constraint methods and the sliding surface constraint scheme can also indirectly guarantee the tracking error constraint while being more stable than the tracking error constraint control. A simulation and experiment were performed on an articulated robot manipulator to validate the proposed control schemes.

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

This paper focuses on fast terminal sliding mode control (FTSMC) of robot manipulators using wavelet neural networks (WNN) with guaranteed H∞tracking performance. The FTSMC for trajectory tracking is employed to drive the tracking error of the system to converge to an equilibrium point in finite time. The tracking error arrives at the sliding surface in finite time and then converges to zero in finite time along the sliding surface. To deal with the case of uncertain and unknown robot dynamics, a WNN is proposed to fully compensate the robot dynamics. The online tuning algorithms for the WNN parameters are derived using Lyapunov approach. To attenuate the effect of approximation errors to a prescribed level, H∞tracking performance is proposed. It is shown that the proposed WNN is able to learn the system dynamics with guaranteed H∞tracking performance and finite time convergence for trajectory tracking. Finally, the simulation results are performed on a 3D-Microbot manipulator to show the effectiveness of the controller.

Optimized Assistive Human-Robot Interaction Using Reinforcement Learning

An intelligent human-robot interaction (HRI) system with adjustable robot behavior is presented. The proposed HRI system assists the human operator to perform a given task with minimum workload demands and optimizes the overall human-robot system performance. Motivated by human factor studies, the presented control structure consists of two control loops. First, a robot-specific neuro-adaptive controller is designed in the inner loop to make the unknown nonlinear robot behave like a prescribed robot impedance model as perceived by a human operator. In contrast to existing neural network and adaptive impedance-based control methods, no information of the task performance or the prescribed robot impedance model parameters is required in the inner loop. Then, a task-specific outer-loop controller is designed to find the optimal parameters of the prescribed robot impedance model to adjust the robot's dynamics to the operator skills and minimize the tracking error. The outer loop includes the human operator, the robot, and the task performance details. The problem of finding the optimal parameters of the prescribed robot impedance model is transformed into a linear quadratic regulator (LQR) problem which minimizes the human effort and optimizes the closed-loop behavior of the HRI system for a given task. To obviate the requirement of the knowledge of the human model, integral reinforcement learning is used to solve the given LQR problem. Simulation results on an x - y table and a robot arm, and experimental implementation results on a PR2 robot confirm the suitability of the proposed method.

A Sliding Mode Control-Based on a RBF Neural Network for Deburring Industry Robotic Systems

A sliding mode control method based on radial basis function (RBF) neural network is proposed for the deburring of industry robotic systems. First, a dynamic model for deburring the robot system is established. Then, a conventional SMC scheme is introduced for the joint position tracking of robot manipulators. The RBF neural network based sliding mode control (RBFNN-SMC) has the ability to learn uncertain control actions. In the RBFNN-SMC scheme, the adaptive tuning algorithms for network parameters are derived by a Koski function algorithm to ensure the network convergences and enacts stable control. The simulations and experimental results of the deburring robot system are provided to illustrate the effectiveness of the proposed RBFNN-SMC control method. The advantages of the proposed RBFNN-SMC method are also evaluated by comparing it to existing control schemes.

Nonlinear Perfect Tracking Control for a Robot Arm with Uncertainties Using Operator-Based Robust Right Coprime Factorization Approach

<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00270001/06.jpg"" width=""300"" />Plant uncertainties compensation</div> In this paper, a robust nonlinear perfect tracking control for a robot arm with uncertainties is proposed by using operator-based robust right coprime factorization approach. In general, there exist unknown modelling errors in measuring structural parameters of the robot arm and external disturbances in real situations. In the present control system design, the effect of the modelling errors and disturbances on the system performance is considered to be uncertainties of the robot arm dynamics. Considering the uncertainties, a robust nonlinear perfect tracking control using operator-based robust right coprime factorization is investigated. That is, first, considering the unknown uncertain plant generates limitations in obtaining the so-called universal stability and tracking conditions, the effect of uncertain plant is compensated by designed operator-based feedback control scheme. Second, a new perfect tracking condition is proposed for improving the trajectory of the robot arm. Finally, the effectiveness of the designed system is confirmed by simulation results. </span>

Adaptive neural PD control with semiglobal asymptotic stabilization guarantee

This paper proves that adaptive neural plus proportional-derivative (PD) control can lead to semiglobal asymptotic stabilization rather than uniform ultimate boundedness for a class of uncertain affine nonlinear systems. An integral Lyapunov function-based ideal control law is introduced to avoid the control singularity problem. A variable-gain PD control term without the knowledge of plant bounds is presented to semiglobally stabilize the closed-loop system. Based on a linearly parameterized raised-cosine radial basis function neural network, a key property of optimal approximation is exploited to facilitate stability analysis. It is proved that the closed-loop system achieves semiglobal asymptotic stability by the appropriate choice of control parameters. Compared with previous adaptive approximation-based semiglobal or asymptotic stabilization approaches, our approach not only significantly simplifies control design, but also relaxes constraint conditions on the plant. Two illustrative examples have been provided to verify the theoretical results.

Adaptive neural network motion control of manipulators with experimental evaluations

A nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired torque, a two-layer neural network is used. Then, adaptation laws for the neural network weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the neural network weights are shown to be uniformly bounded. The proposed scheme has been experimentally validated in real time. These experimental evaluations were carried in two different mechanical systems: a horizontal two degrees-of-freedom robot and a vertical one degree-of-freedom arm which is affected by the gravitational force. In each one of the two experimental set-ups, the proposed scheme was implemented without and with adaptive neural network compensation. Experimental results confirmed the tracking accuracy of the proposed adaptive neural network-based controller.