Adaptive P‐type iterative learning radial basis function control for robot manipulators with unknown varying disturbances and unknown input dead zone

This article proposes an adaptive iterative learning radial basis function (RBF) scheme to solve the trajectory‐tracking problem for perturbed robot manipulators with unknown iteration varying disturbances and unknown dead‐zone input. It is well known that the presence of the dead zone in actuators and mechatronics devices gives rise to extra difficulty due to the presence of singularity in the input channels. Hence, it is interesting to take this problem into account when synthesizing a controller. This synthesis is made here. In addition, the control design is very simple in the sense that we use, only, the proportional gain. Therefore, the considerable amount noise caused by the sensors for velocity measurements of robot manipulators is avoided. Another advantage of this work is that the unknown disturbances are assumed to be time varying and also varying from iteration to iteration. Thus, the RBF neural network is used to approximate these unknown nonlinear functions. Using the Lyapunov theory, the analysis of the stability of the closed‐loop system is guaranteed when the iteration number tends to infinity. Finally, simulation results on the PUMA 560 arm are provided to illustrate the effectiveness of the proposed method. In order to evaluate the performance of our controller, a comparison of our results with other method is also given.     

Adaptive fuzzy ILC of nonlinear discrete-time systems with unknown dead zones and control directions

This paper presents an adaptive fuzzy iterative learning control (ILC) design for non-parametrized nonlinear discrete-time systems with unknown input dead zones and control directions. In the proposed adaptive fuzzy ILC algorithm, a fuzzy logic system (FLS) is used to approximate the desired control signal, and an additional adaptive mechanism is designed to compensate for the unknown input dead zone. In dealing with the unknown control direction of the nonlinear discrete-time system, a discrete Nussbaum gain technique is exploited along the iteration axis and applied to the adaptive fuzzy ILC algorithm. As a result, it is proved that the proposed adaptive fuzzy ILC scheme can drive the ILC tracking errors beyond the initial time instants into a tunable residual set as iteration number goes to infinity, and keep all the system signals bounded in the adaptive ILC process. Finally, a simulation example is used to demonstrate the feasibility and effectiveness of the adaptive fuzzy ILC scheme.     

Robust Adaptive Dead Zone Technology for Fault-Tolerant Control of Robot Manipulators Using Neural Networks

In this paper, a multi-layered feed-forward neural network is trained on-line by robust adaptive dead zone scheme to identify simulated faults occurring in the robot system and reconfigure the control law to prevent the tracking performance from deteriorating in the presence of system uncertainty. Consider the fact that system uncertainty can not be known a priori, the proposed robust adaptive dead zone scheme can estimate the upper bound of system uncertainty on line to ensure convergence of the training algorithm, in turn the stability of the control system. A discrete-time robust weight-tuning algorithm using the adaptive dead zone scheme is presented with a complete convergence proof. The effectiveness of the proposed methodology has been shown by simulations for a two-link robot manipulator.     

Adaptive neural control for a class of stochastic nonlinear time‐delay systems with unknown dead zone using dynamic surface technique

This paper investigates the problem of adaptive control for a class of stochastic nonlinear time‐delay systems with unknown dead zone. A neural network‐based adaptive control scheme is developed by using the dynamic surface control (DSC) technique and the minimal learning parameters algorithm. The dynamic surface control technique, which can avoid the problem of ‘explosion of complexity’ inherent in the conventional backstepping design procedure, is first extended to the stochastic nonlinear time‐delay system with unknown dead zone. The unknown nonlinearities are approximated by the function approximation technique using the radial basis function neural network. For the purpose of reducing the numbers of parameters, which are updated online for each subsystem in the process of approximating the unknown functions, the minimal learning parameters algorithm is then introduced. Also, the adverse effects of unknown time‐delay are removed by using the appropriate Lyapunov–Krasovskii functionals. In addition, the proposed control scheme is systematically derived without requiring any information on the boundedness of the dead zone parameters and avoids the possible controller singularity problem in the approximation‐based adaptive control schemes with feedback linearization technique. It is shown that the proposed control approach can guarantee that all the signals of the closed‐loop system are bounded in probability, and the tracking errors can be made arbitrary small by choosing the suitable design parameters. Finally, a simulation example is provided to illustrate the performance of the proposed control scheme. Copyright © 2015 John Wiley & Sons, Ltd.     

Stable neurovisual servoing for robot manipulators

In this paper, we propose a stable neurovisual servoing algorithm for set-point control of planar robot manipulators in a fixed-camera configuration an show that all the closed-loop signals are uniformly ultimately bounded (UUB) and converge exponentially to a small compact set. We assume that the gravity term and Jacobian matrix are unknown. Radial basis function neural networks (RBFNNs) with online real-time learning are proposed for compensating both gravitational forces and errors in the robot Jacobian matrix. The learning rule for updating the neural network weights, similar to a back propagation algorithm, is obtained from a Lyapunov stability analysis. Experimental results on a two degrees of freedom manipulator are presented to evaluate the proposed controller.     

基于观测器的机械手神经网络自适应控制

提出了一种基于观测器的机械手神经网络自适应轨迹跟随控制器设计方法,这里机 械手的动力学非线性假设是未知的,并且假设机械手仅有关节角位置测量.文中采用一个线 性观测器重构机械手的关节角速度,用神经网络逼近修正的机械手动力学非线性,改进系统 的跟随性能.基于观测器的神经网络自适应控制器能够保证机械手角跟随误差和观测误差的 一致终结有界性以及神经网络权值的有界性,最后给出了机械手神经网络自适应控制器-观 测器设计的主要理论结果,并通过数字仿真验证了所提方法的性能.     

A Markov Game-Adaptive Fuzzy Controller for Robot Manipulators

This paper develops an adaptive fuzzy controller for robot manipulators using a Markov game formulation. The Markov game framework offers a promising platform for robust control of robot manipulators in the presence of bounded external disturbances and unknown parameter variations. We propose fuzzy Markov games as an adaptation of fuzzy Q-learning (FQL) to a continuous-action variation of Markov games, wherein the reinforcement signal is used to tune online the conclusion part of a fuzzy Markov game controller. The proposed Markov game-adaptive fuzzy controller uses a simple fuzzy inference system (FIS), is computationally efficient, generates a swift control, and requires no exact dynamics of the robot system. To illustrate the superiority of Markov game-adaptive fuzzy control, we compare the performance of the controller against a) the Markov game-based robust neural controller, b) the reinforcement learning (RL)-adaptive fuzzy controller, c) the FQL controller, d) the H_infin theory-based robust neural game controller, and e) a standard RL-based robust neural controller, on two highly nonlinear robot arm control problems of i) a standard two-link rigid robot arm and ii) a 2-DOF SCARA robot manipulator. The proposed Markov game-adaptive fuzzy controller outperformed other controllers in terms of tracking errors and control torque requirements, over different desired trajectories. The results also demonstrate the viability of FISs for accelerating learning in Markov games and extending Markov game-based control to continuous state-action space problems.     

具有未建模动态和输出约束的耦合系统的分散自适应控制

针对一类具有输入、状态未建模动态和非线性输入的耦合系统,提出一种自适应神经网络控制方案.利用径向基函数神经网络逼近未知非线性连续函数;引入动态信号和正则化信号处理状态及输入未建模动态;通过引入非线性映射,将具有时变输出约束的严格反馈系统化为不含约束的严格反馈系统.最后,通过理论分析验证闭环系统中所有信号是半全局一致最终有界的,仿真结果进一步验证了所提出控制方案的有效性.     

基于性能指标约束的一类输入死区非线性系统最优控制

针对一类考虑指定性能和带有输入死区约束的严格反馈非线性系统,本文提出了一种自适应模糊最优控制方法.采用模糊逻辑系统逼近系统的未知非线性函数及代价函数,利用backstepping方法及命令滤波技术,设计前馈控制器.针对仿射形式的误差系统,结合自适应动态规划技术,设计最优反馈控制器.采用指定性能控制方法,将系统跟踪误差约束在指定范围内.利用死区斜率信息解决具有死区输入的非线性系统的控制问题.基于Lyapunov稳定性理论,证明闭环系统内所有信号是一致最终有界的.最后仿真结果验证了本文方法的可行性和有效性.     

Fuzzy-Basis-Function-Network-Based $H_infty$ Tracking Control for Robotic Manipulators Using Only Position Feedback

This paper presents an H _infin fuzzy output-feedback tracking-control scheme for robotic manipulators without measuring joint velocities. The developed controller and observer are based on a fuzzy basis function network (FBFN), which is employed to approximate nonlinear functions in the dynamics of controller and observer. The FBFN-based observer that estimates joint velocities can remove the needs of full-state measurements. According to the inevitable approximation errors and external disturbances, an H _infin auxiliary control signal is used to suppress the effects of the uncertainties. Moreover, all parameters of the fuzzy basis functions (FBFs) and FBF-to-output weights can be tuned online. The proposed controller requires no prior knowledge about the dynamics of the robot manipulator and no offline learning phase. Finally, comparative simulations on a three-link robot manipulator are provided to illustrate the tracking performance of the H _infin FBFN-based output-feedback control approach.     

Nonsingular Terminal Sliding Mode Control of Robot Manipulators Using Fuzzy Wavelet Networks

This paper presents an adaptive nonsingular terminal sliding mode (NTSM) tracking control design for robotic systems using fuzzy wavelet networks. Compared with linear hyperplane-based sliding control, terminal sliding mode controller can provide faster convergence and higher precision control. Therefore, a terminal sliding controller combined with the fuzzy wavelet network, which can accurately approximate unknown dynamics of robotic systems by using an adaptive learning algorithm, is an attractive control approach for robots. In addition, the proposed learning algorithm can on-line tune parameters of dilation and translation of fuzzy wavelet basis functions and hidden-to-output weights. Therefore, a robust control law is used to eliminate uncertainties including the inevitable approximation errors resulted from the finite number of fuzzy wavelet basis functions. The proposed controller requires no prior knowledge about the dynamics of the robot and no off-line learning phase. Moreover, both tracking performance and stability of the closed-loop robotic system can be guaranteed by Lyapunov theory. Finally, the effectiveness of the fuzzy wavelet network-based control approach is illustrated through comparative simulations on a six-link robot manipulator     

GA-based fuzzy reinforcement learning for control of a magneticbearing system

This paper proposes a TD (temporal difference) and GA (genetic algorithm)-based reinforcement (TDGAR) learning method and applies it to the control of a real magnetic bearing system. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to perform the reinforcement learning task. The TDGAR learning system is composed of two integrated feedforward networks. One neural network acts as a critic network to guide the learning of the other network (the action network) which determines the outputs (actions) of the TDGAR learning system. The action network can be a normal neural network or a neural fuzzy network. Using the TD prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the GA to adapt itself according to the internal reinforcement signal. The key concept of the TDGAR learning scheme is to formulate the internal reinforcement signal as the fitness function for the GA such that the GA can evaluate the candidate solutions (chromosomes) regularly, even during periods without external feedback from the environment. This enables the GA to proceed to new generations regularly without waiting for the arrival of the external reinforcement signal. This can usually accelerate the GA learning since a reinforcement signal may only be available at a time long after a sequence of actions has occurred in the reinforcement learning problem. The proposed TDGAR learning system has been used to control an active magnetic bearing (AMB) system in practice. A systematic design procedure is developed to achieve successful integration of all the subsystems including magnetic suspension, mechanical structure, and controller training. The results show that the TDGAR learning scheme can successfully find a neural controller or a neural fuzzy controller for a self-designed magnetic bearing system.     

Controlling chaos by GA-based reinforcement learning neural network

Proposes a TD (temporal difference) and GA (genetic algorithm) based reinforcement (TDGAR) neural learning scheme for controlling chaotic dynamical systems based on the technique of small perturbations. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to fulfil the reinforcement learning task. Structurally, the TDGAR learning system is composed of two integrated feedforward networks. One neural network acts as a critic network for helping the learning of the other network, the action network, which determines the outputs (actions) of the TDGAR learning system. Using the TD prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the GA to adapt itself according to the internal reinforcement signal. This can usually accelerate the GA learning since an external reinforcement signal may only be available at a time long after a sequence of actions have occurred in the reinforcement learning problems. By defining a simple external reinforcement signal. the TDGAR learning system can learn to produce a series of small perturbations to convert chaotic oscillations of a chaotic system into desired regular ones with a periodic behavior. The proposed method is an adaptive search for the optimum control technique. Computer simulations on controlling two chaotic systems, i.e., the Henon map and the logistic map, have been conducted to illustrate the performance of the proposed method.     

Neural network controllers for robot manipulators application of damping neurons

^_This paper presents an effective adaptive neural network feedback controller for force control of robot manipulators in an unknown environment by applying damping neurons which possess elastic-viscous properties. The unexpected overshooting and oscillation caused by the unknown and/or unmodeled dynamics of a robot manipulator and an environment can be decreased efficiently by the effect of the proposed damping neurons. Furthermore, a fuzzy controlled evaluation function is applied for the learning of the proposed neural network controller, so that the controller is able to adapt to the unknown environment more effectively. The effectiveness of the proposed neural network controller is evaluated by experiment with a 3 d.o.f. direct-drive planar robot manipulator.     

Learning to Recognize and Grasp Objects

We apply techniques of computer vision and neural network learning to get a versatile robot manipulator. All work conducted follows the principle of autonomous learning from visual demonstration. The user must demonstrate the relevant objects, situations, and/or actions, and the robot vision system must learn from those. For approaching and grasping technical objects three principal tasks have to be done—calibrating the camera-robot coordination, detecting the desired object in the images, and choosing a stable grasping pose. These procedures are based on (nonlinear) functions, which are not known a priori and therefore have to be learned. We uniformly approximate the necessary functions by networks of gaussian basis functions (GBF networks). By modifying the number of basis functions and/or the size of the gaussian support the quality of the function approximation changes. The appropriate configuration is learned in the training phase and applied during the operation phase. All experiments are carried out in real world applications using an industrial articulation robot manipulator and the computer vision system KHOROS.     

Fuzzy self-adaptive radial basis function neural network-based control of a seven-link redundant industrial manipulator

This paper proposes a method for the identification of dynamics and control of a multi-link industrial robot manipulator using Runge-Kutta-Gill neural networks (RKGNNs). RKGNNs are used to identify an ordinary differential equation of the dynamics of the robot manipulator. A structured function neural network (NN) with sub-networks to represent the components of the dynamics is used in the RKGNNs. The sub-networks consist of shape adaptive radial basis function (RBF) NNs. An evolutionary algorithm is used to optimize the shape parameters and the weights of the RBFNNs. Due to the fact that the RKGNNs can accurately grasp the changing rates of the states, this method can effectively be used for long-term prediction of the states of the robot manipulator dynamics. Unlike in conventional methods, the proposed method can even be used without input torque information because a torque network is part of the functional network. This method can be proposed as an effective option for the dynamics identification of manipulators with high degrees-offreedom, as opposed to the derivation of dynamic equations and making additional hardware changes as in the case of statistical parameter identification such as linear least-squares method. Experiments were carried out using a seven-link industrial manipulator. The manipulator was controlled for a given trajectory, using adaptive fuzzy selection of nonlinear dynamic models identified previously. Promising experimental results are obtained to prove the ability of the proposed method in capturing nonlinear dynamics of a multi-link manipulator in an effective manner.     

Learning to Recognize and Grasp Objects

We apply techniques of computer vision and neural network learning to get a versatile robot manipulator. All work conducted follows the principle of autonomous learning from visual demonstration. The user must demonstra te the relevant objects, situations, and/or actions, and the robot vision system must learn from those. For approaching and grasping technical objects three principal tasks have to be done—calibrating the camera-robot coordination, detecting the desired object in the images, and choosing a stable grasping pose. These procedures are based on (nonlinear) functions, which are not known a priori and therefore have to be learned. We uniformly approximate the necessary functions by networks of gaussian basis functions (GBF networks). By modifying the number of basis functions and/or the size of the gaussian support the quality of the function approximation changes. The appropriate configuration is learned in the training phase and applied during the operation phase. All experiments are carried out in real world applications using an industrial articulation robot manipulator and the computer vision system KHOROS.     

Prescribed performance adaptive fault tolerant control approach for nonlinear large-scale systems with time delay interconnection and dead zone input

In this study, a prescribed performance adaptive fault tolerant tracking control scheme is presented for a class of nonlinear large-scale systems with time delay interconnection, dead zone input, and actuator fault. The radial basis function neural networks are used to approximate unknown nonlinear functions. Different from the barrier Lyapunov functions used to achieve the symmetrical prescribed performance, a new error transformation is introduced in this study to achieve the desired asymmetrical prescribed performance. In addition, Nussbaum function is introduced to solve the difficulties caused by dead zone input and actuator fault. Based on the appropriate Lyapunov–Krasovskii functions, the effect of time delay interconnection could be compensated. By using backstepping procedures, an adaptive fault tolerant tracking control approach is developed for the considered large-scale systems, and the stability of the closed-loop systems is analyzed by Lyapunov theory. Meanwhile, the prescribed performance of the tracking error could be guaranteed. Finally, the effectiveness of the proposed control approach is illustrated by two simulation examples.     

Robust adaptive critic control of nonlinear systems using fuzzy basis function networks: An LMI approach

This paper proposes an adaptive critic tracking control design for a class of nonlinear systems using fuzzy basis function networks (FBFNs). The key component of the adaptive critic controller is the FBFN, which implements an associative learning network (ALN) to approximate unknown nonlinear system functions, and an adaptive critic network (ACN) to generate the internal reinforcement learning signal to tune the ALN. Another important component, the reinforcement learning signal generator, requires the solution of a linear matrix inequality (LMI), which should also be satisfied to ensure stability. Furthermore, the robust control technique can easily reject the effects of the approximation errors of the FBFN and external disturbances. Unlike traditional adaptive critic controllers that learn from trial-and-error interactions, the proposed on-line tuning algorithm for ALN and ACN is derived from Lyapunov theory, thereby significantly shortening the learning time. Simulation results of a cart-pole system demonstrate the effectiveness of the proposed FBFN-based adaptive critic controller.     

输出非对称死区的非严格反馈非线性系统控制

本文研究了具有输出非对称死区和状态含未知控制方向的非严格反馈非线性系统, 设计了稳定的自适应 神经网络控制器. 首先, 针对输出非对称死区的问题, 本文采用死区逆的方法, 构造光滑模型逼近原死区模型. 其 次, 在控制器设计过程中, 基于障碍Lyapunov函数的构造, 动态面控制和反步法, 设计出自适应控制信号, 虚拟控制 信号和实际控制信号. 通过稳定性分析, 证明所设计的神经网络控制器可以保证闭环系统内所有信号是半全局一致 最终有界. 最后, 通过MATLAB数值仿真, 说明所设计控制器的有效性.