不确定机器人的自适应神经网络控制与学习

针对具有未知动态的电驱动机器人,研究其自适应神经网络控制与学习问题.首先,设计了稳定的自适应神经网络控制器,径向基函数(RBF)神经网络被用来逼近电驱动机器人的未知闭环系统动态,并根据李雅普诺夫稳定性理论推导了神经网络权值更新律.在对回归轨迹实现跟踪控制的过程中,闭环系统内部信号的部分持续激励(PE)条件得到满足.随着PE条件的满足,设计的自适应神经网络控制器被证明在稳定的跟踪控制过程中实现了电驱动机器人未知闭环系统动态的准确逼近.接着,使用学过的知识设计了新颖的学习控制器,实现了闭环系统稳定、改进了控制性能.最后,通过数字仿真验证了所提控制方法的正确性和有效性.     

确定学习与基于数据的建模及控制

确定学习运用自适应控制和动力学系统的概念与方法, 研究未知动态环境下的知识获取、表达、存储和利用等问题. 针对产生周期或回归轨迹的连续 非线性动态系统, 确定学习可以对其未知系统动态进行局部准确建模, 其基本要 素包括: 1)使用径向基函数(Radial basis function, RBF)神经网络; 2)对于周期(或回归)状态轨迹 满足部分持续激励条件; 3)在周期(或回归)轨迹的邻域内实现对非线性系统动态的局部准确神经网络逼近(局部准确建模); 4)所学的知识以时不变且空间分布的方式表达、以常值神经网络权值的方式存储, 并可在动态环境下用于动态模式的快速识别或者闭环神经网络控制. 本文针对离散动态系统, 扩展了确定学习理论, 提出一个根据时态数据序列对离散动态系统进行建模与控制的框架. 首先, 运用确定学习原理和离散系统的自适应辨识方法, 实现对产生时态数据的离散非线性系统的未知动态进行局部准确的神经网络建模, 并利用此建模结果对时态数据序列进行时不变表达. 其次, 提出时态数据序列的基于动力学的相似性定义, 以及对离散动态系统产生的时态数据序列(亦可称为动态模式)进行快速识别方法. 最后, 针对离散非线性控制系统, 实现了基于时态数据序列对控制系统动态的闭环辨识(局部准确建模). 所学关于闭环动态的知识可用于基于模式的智能控制. 本文表明确定学习可以为时态数据挖掘的研究提供新的途径, 并为基于数据的建模与控制等问题提供新的研究思路.     

从机器人输出反馈自适应神经控制中学习

针对系统参数完全未知且仅输出可测的机器人,使用径向基函数(RBF)神经网络和高增益观测器设计了一种自适应神经控制算法.该算法不仅实现了闭环系统所有信号的最终一致有界,而且沿周期跟踪轨迹实现了对未知闭环系统动态的确定学习.学过的知识可用来改进系统的控制性能,也可应用于后续相同或相似的控制任务以节约时间和能量.仿真研究表明了所设计的控制算法的正确性和有效性.     

基于反步自适应神经网络的船舶航迹控制

针对欠驱动船舶在稳定航速条件下轨迹跟踪问题,提出了一种基于自适应神经网络与反步法相结合的控制算法.该算法将实际的欠驱动船舶视为模型完全未知的非线性系统,利用神经网络的函数逼近特性实现控制器中非线性部分的在线估计,采用同时调整输入层-隐层、隐层-输出层间的权值阵的方法进行神经网络权值调整.通过选取积分型Lyapunov函数证明了闭环系统的稳定性.仿真实验表明该控制策略具有良好的跟踪特性,可以实现对期望航迹的精确跟踪.     

含未知信息的轮式移动机器人编队确定学习控制

本文研究含未知信息的轮式移动机器人(wheeled mobile robots,WMR)的编队控制问题.首先,基于领航–跟随法和虚拟结构法,将WMR编队控制问题转化为跟随机器人对参考虚拟机器人的跟踪控制问题.然后,利用径向基函数神经网络(radial basis function neural networks,RBF NN)对WMR的未知系统动态进行学习,以及根据李雅普诺夫稳定性理论设计了稳定的自适应RBF NN控制器和RBF NN权值估计的学习率.依据确定学习理论,闭环系统内部信号在对回归轨迹实现跟踪控制的过程中满足部分持续激励(persistent excitation,PE)条件.随着PE条件的满足,RBF NN权值估计收敛到其理想权值,实现了对未知闭环系统动态的准确学习.最后,利用学习结果设计了RBF NN学习控制器,保证了控制系统的稳定与收敛,实现了闭环稳定性和改进了控制性能,并通过仿真验证了所提控制方法的正确性和有效性.     

AUV深度的神经网络辨识和学习控制仿真研究

将自主水下航行器（AUV）的深度控制问题转换为对非线性严格反馈系统的分析,提出了一种结合反步法和确定学习理论的自适应学习控制方法。通过反步法设计了一种输入状态稳定（ISS）神经网络控制器,其中引入小增益定理,避免了控制器设计中存在的奇异值问题,并在满足持续激励（PE）条件下,利用神经网络辨识实现了对系统未知动态的局部准确逼近和部分神经网络权值的收敛,保证了闭环系统的稳定。将从动态模式中学到的知识静态保存,提取动态特征设计学习控制器,仿真结果表明,该控制器避免了执行同样任务时的重复训练,改善了系统控制性能,验证了所提控制方法的有效性。     

输入受限四旋翼飞行器的模糊自适应动态面轨迹跟踪控制

针对输入受限条件下四旋翼飞行器的轨迹跟踪控制问题,考虑系统存在模型动态不确定和未知外界干扰的情况,提出一种模糊自适应动态面轨迹跟踪控制方法.该方法设计干扰观测器估计位置模型中复合扰动项,利用模糊系统逼近姿态模型中不确定项和外界干扰,并引入双曲正切函数和辅助系统处理输入受限问题,结合反演法和动态面技术设计轨迹跟踪控制器,以降低控制算法的复杂性,最后选取李雅普诺夫函数证明闭环系统所有信号一致最终有界.应用大疆M100飞行器模型进行仿真验证,结果表明所设计的控制器能够有效处理模型动态不确定和未知外界干扰问题,避免飞行器工作过程中因输入饱和导致执行器失效现象,精确地完成轨迹跟踪控制任务.     

多自主船协同路径跟踪的自适应动态面控制

为实现多自主船含模型不确定与未知风浪流干扰下的协同路径跟踪控制,提出了一种基于神经网络自适应动态面控制的协同路径跟踪算法.该算法采用单隐层(SHL)神经网络逼近模型不确定性以及海洋环境干扰,所引入的动态面设计技术显著降低了控制算法的复杂性.同时将网络通信约束考虑在内,通过设计分散式协同控制律有效地降低了信息通讯量.Lyapunov稳定性分析证明了闭环系统所有的状态和信号是有界的,并且通过选择合适的设计参数可使跟踪误差为任意小.对比仿真结果验证了所提方法的有效性.     

基于PNDSC 的欠驱动AUV编队控制器设计

针对含有模型不确定与未知海洋环境扰动下的欠驱动自主水下航行器(AUV)的编队控制问题, 提出一种基于预估器的神经网络动态面(PNDSC) 控制算法. 将动态面法引入控制器的设计中, 采用神经网络逼近AUV模型中的不确定项与海洋环境的扰动, 并结合预估器设计了神经网络权值的离散迭代更新率. Lyapunov 稳定性分析表明, 闭环系统所有信号是一致最终有界的. 仿真结果验证了所提出方法的有效性.

     

基于神经网络观测器的船舶轨迹跟踪递归滑模 动态面输出反馈控制

针对三自由度全驱动船舶速度向量不可测问题,考虑船舶模型参数和外部环境扰动均未知的情况,提出一种基于神经网络观测器的船舶轨迹跟踪递归滑模动态面输出反馈控制方法.该方法设计神经网络自适应观测器估计船舶速度向量,且利用神经网络逼近模型参数不确定项,综合考虑船舶位置和速度误差之间关系构造递归滑模面,再采用动态面控制技术设计轨迹跟踪控制律和参数自适应律,并引入低频增益学习方法消除外界扰动导致的高频振荡控制信号.选取李雅普诺夫函数证明了该控制律能够保证轨迹跟踪闭环系统内所有信号的一致最终有界性.最后,基于一艘供给船进行仿真验证,结果表明,船舶轨迹跟踪响应速度快,所设计控制器对系统模型参数摄动及外界扰动具有较强的鲁棒性.     

Adaptive neural control and learning of affine nonlinear systems

This paper presents deterministic learning from adaptive neural network control of affine nonlinear systems with completely unknown system dynamics. Thanks to the learning capability of radial basis function, neural network (NN), stable adaptive NN controller is designed for the unknown affine nonlinear systems. The designed adaptive NN controller is rigorously shown that learning of the unknown closed-loop system dynamics can be achieved during the stable control process because partial persistent excitation condition of some internal signals in the closed-loop system is satisfied. Subsequently, neural learning controller using the knowledge obtained from deterministic learning is constructed to achieve closed-loop stability and improve control performance. Numerical simulation is provided to show the effectiveness of the proposed control scheme.     

Learning from neural control of nonlinear systems in normal form

A deterministic learning theory was recently proposed which states that an appropriately designed adaptive neural controller can learn the system internal dynamics while attempting to control a class of simple nonlinear systems. In this paper, we investigate deterministic learning from adaptive neural control (ANC) of a class of nonlinear systems in normal form with unknown affine terms. The existence of the unknown affine terms makes it difficult to achieve learning by using previous methods. To overcome the difficulties, firstly, an extension of a recent result is presented on stability analysis of linear time-varying (LTV) systems. Then, with a state transformation, the closed-loop control system is transformed into a LTV form for which exponential stability can be guaranteed when a partial persistent excitation (PE) condition is satisfied. Accurate approximation of the closed-loop control system dynamics is achieved in a local region along a recurrent orbit of closed-loop signals. Consequently, learning of control system dynamics (i.e. closed-loop identification) from adaptive neural control of nonlinear systems with unknown affine terms is implemented.     

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.     

Learning from NN output feedback control of nonlinear systems in Brunovsky canonical form

In this paper, we investigate the learning issue in the adaptive neural network (NN) output feedback control of nonlinear systems in Brunovsky canonical form with unknown affine term. With only output measurements, a high-gain observer (HGO) is employed to estimate the derivatives of the system output which may be associated with the generation of peaking phenomenon. The adverse effect of peaking on learning and its elimination strategies are analyzed. When the gain of HGO is chosen too high, it may cause the failure of learning from the unknown closed-loop system dynamics. Hence, the gain of HGO is not chosen too high to relieve peaking and guarantee the accuracy of the estimated system states. Then, learning from the unknown closed-loop system dynamics can be achieved. When repeating the same or similar control tasks, a neural learning controller is presented which can effectively recall and reuse the learned knowledge to guarantee the output tracking performance. Finally, simulation results demonstrate the effectiveness of the proposed scheme.     

An observer-based adaptive neural network tracking control of robotic systems

Robotic systems have inherently nonlinear phenomena as joints undergo sliding and/or rotating. This in turn requires that the system running states be predicted correctly. This paper makes a full analysis of the robot states by applying observer-based adaptive wavelet neural network (OBAWNN) tracking control scheme to tackle these phenomena such as system uncertainties, multiple time-delayed state uncertainties, and external disturbances such that the closed loop system signals must obey uniform ultimate boundedness and achieve H^∞ tracking performance. The recurrent adaptive wavelet neural network model is used to approximate the dynamics of the robotic system, while an observer-based adaptive control scheme is to stabilize the system. The advantage of employing adaptive wavelet neural dynamics is that we can utilize the neuron information by activation functions to on-line tune the hidden-to-output weights, and the adaptation parameters to estimate the robot parameters and the bounds of the gains of delay states directly using linear analytical results. It is shown that the stability of the closed-loop system is guaranteed by some sufficient conditions derived from Lyapunov criterion and Riccati-inequality. Finally, a numerical example of a three-links rolling cart is given to illustrate the effectiveness of the proposed control scheme.     

Online adaptive optimal control for continuous-time nonlinear systems with completely unknown dynamics

An online adaptive optimal control is proposed for continuous-time nonlinear systems with completely unknown dynamics, which is achieved by developing a novel identifier-critic-based approximate dynamic programming algorithm with a dual neural network (NN) approximation structure. First, an adaptive NN identifier is designed to obviate the requirement of complete knowledge of system dynamics, and a critic NN is employed to approximate the optimal value function. Then, the optimal control law is computed based on the information from the identifier NN and the critic NN, so that the actor NN is not needed. In particular, a novel adaptive law design method with the parameter estimation error is proposed to online update the weights of both identifier NN and critic NN simultaneously, which converge to small neighbourhoods around their ideal values. The closed-loop system stability and the convergence to small vicinity around the optimal solution are all proved by means of the Lyapunov theory. The proposed adaptation algorithm is also improved to achieve finite-time convergence of the NN weights. Finally, simulation results are provided to exemplify the efficacy of the proposed methods.