带执行器饱和的柔性关节机器人位置反馈动态面控制

针对带有执行器饱和的柔性关节机器人系统,提出一种位置反馈动态面控制,以实现机器人连杆的角位置跟踪.在一般动态面控制的设计框架下,设计观测器重构系统未知速度状态,利用径向基函数神经网络学习饱和非线性特性,结合“最小参数学习”算法减轻计算负担.通过Lyapunov方法证明得出闭环系统所有信号半全局一致有界,跟踪误差可以通过调节控制器参数达到任意小.仿真结果表明,控制系统能够克服外界干扰,有效补偿系统存在的执行器饱和,实现柔性关节机器人的准确跟踪控制.该方法避免了传统反演设计存在的“微分爆炸”现象,简化了设计过程.     

Adaptive recurrent neural network control using a structure adaptation algorithm

This paper proposes an adaptive recurrent neural network control (ARNNC) system with structure adaptation algorithm for the uncertain nonlinear systems. The developed ARNNC system is composed of a neural controller and a robust controller. The neural controller which uses a self-structuring recurrent neural network (SRNN) is the principal controller, and the robust controller is designed to achieve L ² tracking performance with desired attenuation level. The SRNN approximator is used to online estimate an ideal tracking controller with the online structuring and parameter learning algorithms. The structure learning possesses the ability of both adding and pruning hidden neurons, and the parameter learning adjusts the interconnection weights of neural network to achieve favorable approximation performance. And, by the L ² control design technique, the worst effect of approximation error on the tracking error can be attenuated to be less or equal to a specified level. Finally, the proposed ARNNC system with structure adaptation algorithm is applied to control two nonlinear dynamic systems. Simulation results prove that the proposed ARNNC system with structure adaptation algorithm can achieve favorable tracking performance even unknown the control system dynamics function.     

Robust control of flexible structures with stable bandpass controllers

In this paper, a control law for the active vibration control of mechanical flexible systems is considered. The proposed strategy minimizes an index and results in a stable stabilizing controller with bandpass frequency shape, due to the presence of zeros at the origin. The control authority is thus effective in a chosen band of frequency, resulting in a selective broadband control action, as opposed to narrow-band (tonal) vibration reduction. Moreover, the explicit closed-form solution of the controller is also obtained, thus avoiding numerical calculation of the solution of the Riccati equations, which can be ill-conditioned in the case of very high-order, poorly damped flexible systems. The parametrization of all the controllers is also given and a family of controllers with the above properties is deduced. The case is also obtained as a byproduct. The controller is based on a colocated actuators/sensors pair strategy and numerical simulations are presented, showing the robustness of the proposed approach even for systems with zero damping. Finally, experimental results on a skin panel of a Boeing 717 aircraft also prove the effectiveness of the proposed approach in practical complex applications, with global vibration reduction performances.     

基于RENN 的柔性关节机械臂自适应动态面控制

针对面贴式永磁同步电机驱动的柔性关节机械臂动力学模型具有非线性、不确定性和未知外部扰动等特点,提出一种自适应动态面控制方法来实现其关节轨迹跟踪控制．控制律由动态面技术得到,降低了反推控制器的复杂性．模型不确定因素由递归Elman神经网络在线补偿,神经网络权值自适应律通过Lyapunov稳定性分析推导得到．仿真研究表明,该方法对于载荷不确定和外界扰动具有较强的鲁棒性,与传统动态面法相比,大大提高了柔性关节的位置跟踪精度．     

Fractional-order dynamics and adaptive dynamic surface control of flexible-joint robots

This paper establishes a novel fractional-order model for n-links flexible-joint (FJ) robots and proposes an adaptive dynamic surface control (DSC) scheme to address the tracking control problem. The fractional-order FJ model is built by fractional-order viscoelastic dynamics model to have a more concise form. An adaptive DSC strategy is proposed to address the tracking control problem based on backstepping method. By selecting the appropriate orders for fractional filters, the controller could solve the “explosion of complexity” problem. The unknown nonlinearities of FJ robot systems are approximated by Radial basis function (RBF) neural networks (NNs). Based on the Lyapunov stability theory, the bounds of all signals in the closed-loop system are achieved. The simulation results confirm the effectiveness of the presented control scheme.     

Generalized predictive control using recurrent fuzzy neural networks for industrial processes

This paper presents a design methodology for predictive control of industrial processes via recurrent fuzzy neural networks (RFNNs). A discrete-time mathematical model using RFNN is constructed and a learning algorithm adopting a recursive least squares (RLS) approach is employed to identify the unknown parameters in the model. A generalized predictive control (GPC) law with integral action is derived based on the minimization of a modified predictive performance criterion. The stability and steady-state performance of the resulting control system are studied as well. Two examples including the control of a nonlinear process and the control of a physical variable-frequency oil-cooling machine are used to demonstrate the effectiveness of the proposed method. Both results from numerical simulations and experiments show that the proposed method is capable of controlling industrial processes with satisfactory performance under setpoint and load changes.     

Modelling and adaptive tracking control for flexible joint robots with random noises

This paper investigates modelling and adaptive tracking control problems for flexible joint robots subjected to random disturbances. A stochastic flexible joint robot model is given by introducing random noises reasonably. Under some weaker assumptions, a new controller is constructed by exploiting adaptive dynamic surface control technique. It is proved that the mean square of the tracking error can be made arbitrarily small by choosing appropriate design parameters. A mechanics model is provided in the simulation to show the effectiveness of the presented theory.     

Efference copies in neural control of dynamic biped walking

In the early 1950s, von Holst and Mittelstaedt proposed that motor commands copied within the central nervous system (efference copy) help to distinguish ‘reafference’ activity (afference activity due to self-generated motion) from ‘exafference’ activity (afference activity due to external stimulus). In addition, an efference copy can be also used to compare it with the actual sensory feedback in order to suppress self-generated sensations. Based on these biological findings, we conduct here two experimental studies on our biped “RunBot” where such principles together with neural forward models are applied to RunBot’s dynamic locomotion control. The main purpose of this article is to present the modular design of RunBot’s control architecture and discuss how the inherent dynamic properties of the different modules lead to the required signal processing. We believe that the experimental studies pursued here will sharpen our understanding of how the efference copies influence dynamic locomotion control to the benefit of modern neural control strategies in robots.     

受时变约束柔性臂鲁棒RBF神经网络力/位置控制

研究了受时变约束的柔性臂系统，建立了分布参数模型，通过奇异摄动方法将该模型划分为表征系统刚性运动的集中参数子系统和表征系统振动的分布参数子系统．设计了集中参数子系统的鲁棒RBF神经网络力／位置控制算法和分布参数子系统的鲁棒自适应振动抑制控制算法．理论分析及仿真结果验证了该方法的有效性．     

Decoupling and tracking control for elastic joint robots with coupled joint structure

The paper deals with the modeling, identification, and control of a flexible joint robot developed for medical applications at the German Aerospace Center (DLR). In order to design anthropomorphic kinematics, the robot uses a coupled joint structure realized by a differential gearbox, which however leads to strong mechanical couplings inside the coupled joints and must be taken into account. Therefore, a regulation MIMO state feedback controller based on modal analysis is developed for each coupled joint pair, which consists of full state feedback (motor position, link side torque, as well as their derivatives). Furthermore, in order to improve position accuracy and simultaneously keep good dynamic behavior of the MIMO state feedback controller, a cascaded tracking control scheme is proposed, based on the MIMO state feedback controller with additional feedforward terms (desired motor velocity, desired motor acceleration, derivative of the desired torque), which are computed in a computed torque controller and take the whole rigid body dynamics into account. Stability analysis is shown for the complete controlled robot. Finally, experimental results with the DLR medical robot are presented to validate the practical efficiency of the approaches.     

Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates

This paper proposes an indirect adaptive control method using self recurrent wavelet neural networks (SRWNNs) for dynamic systems. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). However, unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN can store the past information of wavelets. In the proposed control architecture, two SRWNNs are used as both an identifier and a controller. The SRWNN identifier approximates dynamic systems and provides the SRWNN controller with information about the system sensitivity. The gradient-descent method using adaptive learning rates (ALRs) is applied to train all weights of the SRWNN. The ALRs are derived from discrete Lyapunov stability theorem, which are applied to guarantee the convergence of the proposed control system. Finally, we perform some simulations to verify the effectiveness of the proposed control scheme.     

Reinforcement learning of dynamic behavior by using recurrent neural networks

Reinforcement learning is a learning scheme for finding the optimal policy to control a system, based on a scalar signal representing a reward or a punishment. If the observation of the system by the controller is sufficiently rich to represent the internal state of the system, the controller can achieve the optimal policy simply by learning reactive behavior. However, if the state of the controlled system cannot be assessed completely using current sensory observations, the controller must learn a dynamic behavior to achieve the optimal policy. In this paper, we propose a dynamic controller scheme which utilizes memory to uncover hidden states by using information about past system outputs, and makes control decisions using memory. This scheme integrates Q-learning, as proposed by Watkins, and recurrent neural networks of several types. It performs favorably in simulations which involve a task with hidden states. This work was presented, in part, at the International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1996     

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

In this paper, a continuous time recurrent neural network (CTRNN) is developed to be used in nonlinear model predictive control (NMPC) context. The neural network represented in a general nonlinear state-space form is used to predict the future dynamic behavior of the nonlinear process in real time. An efficient training algorithm for the proposed network is developed using automatic differentiation (AD) techniques. By automatically generating Taylor coefficients, the algorithm not only solves the differentiation equations of the network but also produces the sensitivity for the training problem. The same approach is also used to solve the online optimization problem in the predictive controller. The proposed neural network and the nonlinear predictive controller were tested on an evaporation case study. A good model fitting for the nonlinear plant is obtained using the new method. A comparison with other approaches shows that the new algorithm can considerably reduce network training time and improve solution accuracy. The CTRNN trained is used as an internal model in a predictive controller and results in good performance under different operating conditions.     

挠性系统的鲁棒控制设计

提出一种新的鲁棒设计思想：将挠性模态部分的Nyquist图线安排到右半平面。由于综合运用了频域分析、极点配置、正实性引理、线性矩阵不等式等概念和算法，使得这种鲁棒控制设计得以实现，且简单直观。通过两个算例说明了该设计方法的有效性。     

基于DSP/FPGA的反步法阻抗控制柔性关节机械臂

针对柔性关节机械臂与环境接触时的柔顺控制问题,提出一种反步法阻抗控制方法,并基于李雅普诺夫稳定性理论证明了控制器的稳定性.该方法是在建立柔性关节机器人模型的基础上,将李雅普诺夫函数选取与控制器设计相结合的一种回归设计方法.它从系统的最低阶次微分方程开始,逐步设计满足要求的虚拟控制,最终设计出真正的控制器.轨迹跟踪和阻抗控制实验结果表明,该方法是有效而可行的.     

Multiple models switching control based on recurrent neural networks

This paper presents a novel approach in designing adaptive controller to improve the transient performance for a class of nonlinear discrete-time systems under different operating modes. The proposed scheme consists of generalized minimum variance (GMV) controllers and a compensating controller. GMV controllers are based on the known nominal linear multiple models, while the compensating controller is based upon a recurrent neural network. The adaptation law of network weight is derived from Lyapunov stability theory. A suitable switching control strategy is applied to choose the best controller by the performance indices at every sampling instant. Simulations are discussed in order to illustrate the merits of the proposed method.     

Distributed adaptive containment control of networked flexible-joint robots using neural networks

This study presents a distributed adaptive containment control approach for a group of uncertain flexible-joint (FJ) robots with multiple dynamic leaders under a directed communication graph. The leaders are neighbors of only a subset of the followers. The derivatives of the leaders are unknown, namely, the position information of the leaders is only available for implementing the proposed control approach. The local adaptive dynamic surface containment controller for each follower is designed using only neighbors’ information to guarantee that all followers converge to the dynamic convex hull spanned by the dynamic leaders. The function approximation technique using neural networks is employed to estimate the model uncertainties of each follower. It is proved that the containment control errors converge to an adjustable neighborhood of the origin regardless of model uncertainties and the lack of shared communication information. Simulation results for FJ manipulators are provided to illustrate the effectiveness of the proposed adaptive containment control scheme.     

Central pattern generator based reflexive control of quadruped walking robots using a recurrent neural network

This paper presents a novel Central Pattern Generator (CPG) model for controlling quadruped walking robots. The improvement of this model focuses on generating any desired waveforms along with accurate online modulation. In detail, a well-analyzed Recurrent Neural Network is used as the oscillators to generate simple harmonic periodic signals that exhibit limit cycle effects. Then, an approximate Fourier series is employed to transform those mentioned simple signals into arbitrary desired outputs under the phase constraints of several primary quadruped gaits. With comprehensive closed-form equations, the model also allows the user to modulate the waveform, the frequency and the phase constraint of the outputs online by directly setting the inner parameters without the need for any manual tuning. In addition, an associated controller is designed using leg coordination Cartesian position as the control state space based on which stiffness control is performed at sub-controller level. In addition, several reflex modules are embedded to transform the feedback of all sensors into the CPG space. This helps the CPG recognize external disturbances and utilize inner limit cycle effect to stabilize the robot motion. Finally, experiments with a real quadruped robot named AiDIN III performing several dynamic trotting tasks on several unknown natural terrains are presented to validate the effectiveness of the proposed CPG model and controller.     

An iterative learning scheme for motion control of robots using neural networks: A case study

In this paper, an iterative learning controller using neural networks has been studied for the motion control of robotic manipulators. Simulations of a two-link robot have demonstrated that the proposed control scheme for robotic manipulators can greatly reduce tracking errors after a few trials. Our modification of the original back-propagation algorithm is employed in the neural network, resulting in a much faster learning rate. The results of simulation have also shown that the proposed iterative learning controller has a faster rate of convergence and better robustness.     

Robust adaptive control for greenhouse climate using neural networks

This paper presents a general framework for robust adaptive neural network (NN)‐based feedback linearization controller design for greenhouse climate system. The controller is based on the well‐known feedback linearization, combined with radial basis functions NNs, which allows the feedback linearization technique to be used in an adaptive way. In addition, a robust sliding mode control is incorporated to deal with the bounded disturbances and the approximation errors of NNs. As a result, an inherently nonlinear robust adaptive control law is obtained, which not only provides fast and accurate tracking of varying set‐points, but also guarantees asymptotic tracking even if there are inherent approximation errors. Copyright © 2010 John Wiley & Sons, Ltd.