迭代学习神经网络控制在机器人示教学习中的应用

示教学习是机器人运动技能获取的一种高效手段.当采用摄像机作为示教轨迹记录部件时,示教学习涉及如何通过反复尝试获得未知机器人摄像机模型问题.本文力图针对非线性系统重复作业中的可重复不确定性学习,提出一个迭代学习神经网络控制方案,该控制器将保证系统最大跟踪误差维持在神经网络有效近似域内.为此提出了一个适合于重复作业应用的分布式神经网络结构.该神经网络由沿期望轨线分布的一系列局部神经网络构成,每一局部神经网络对对应期望轨迹点邻域进行近似并通过重复作业完成网络训练.由于所设计的局部神经网络相互独立,因此一个全程轨迹可以通过分段训练完成,由起始段到结束段,逐段实现期望轨迹的准确跟踪.该方法在具有未知机器人摄像机模型的轨迹示教模仿中得到验证,显示了它是一种高效的训练方法,同时具有一致的误差限界能力.     

无奇异间接迭代学习控制及其在机器人运动模仿中的应用

针对相当广泛的一类非线性系统有限时间轨迹跟踪问题,提出了间接迭代学习方案. 采用最小二乘算法,根据重复跟踪历史辨识非线性系统的线性化模型.利用一个分段学习方案 可保证学习控制总在有效线性近似区域内进行.探讨了如何在学习过程中避免控制奇异问题, 提出了一种高效的参数修正方法,保证输入耦合矩阵的估计行列式不为零.本文将这一控制方 案应用于未知机器人及摄像机模型下的机器人运动模仿中,而不面临任何奇异问题.这是一个 采用摄像机替代传统程序编写的新的机器人编程方法.     

Observer-based Iterative and Repetitive Learning Control for a Class of Nonlinear Systems

In this paper, both output-feedback iterative learning control (ILC) and repetitive learning control (RLC) schemes are proposed for trajectory tracking of nonlinear systems with state-dependent time-varying uncertainties. An iterative learning controller, together with a state observer and a fully-saturated learning mechanism, through Lyapunov-like synthesis, is designed to deal with time-varying parametric uncertainties. The estimations for outputs, instead of system outputs themselves, are applied to form the error equation, which helps to establish convergence of the system outputs to the desired ones. This method is then extended to repetitive learning controller design. The boundedness of all the signals in the closed-loop is guaranteed and asymptotic convergence of both the state estimation error and the tracking error is established in both cases of ILC and RLC. Numerical results are presented to verify the effectiveness of the proposed methods.      

Iterative learning control for position tracking of a pneumatic actuated X–Y table

The iterative learning control (ILC) obtains the unknown information from repeated control operations. Meanwhile, the tracking error from previous stages is used as the correction factor for the next control action. Therefore, the ILC controller can make the system tracking error converge to a small region within a limited number of iterations. This study builds a proportional-valve-controlled pneumatic X–Y table system for performing position tracking control experiments. The experiments involve implementing the ILC controllers and comparing the results. The P-type updating law with delay parameters is used for both the x- and y-axes in the repetitive trajectory tracking control. Experimental results demonstrate that the ILC controller can effectively control the system and track the desired circular trajectory at different speeds. The control parameters are varied to investigate their effects on the ILC convergence.     

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.     

Adaptive NN state error PCH trajectory tracking control for unmanned surface vessel with uncertainties and input saturation

A novel robust state error port controlled Hamiltonian (PCH) trajectory tracking controller of an unmanned surface vessel (USV) subject to time-varying disturbances, dynamic uncertainties and control input saturation is presented. The proposed control scheme combines the advantages of the high robustness and energy minimization of the state error PCH approach and the approximation capability of adaptive radial basis function neural networks (RBFNNs). Adaptive RBFNNs are used to the time-varying disturbances of the environment and unknown dynamics uncertainties of the USV model. The state error PCH control approach is designed such that the system can optimize energy consumption, and the state error PCH technique makes the designed trajectory tracking controller be easy to implement in practice. To handle the effect of the control input saturation, a Gaussian error function model is employed. It has been demonstrated that the proposed approach can maintain the USV's trajectory at the desired trajectory, while the closed-loop control system can guarantee the uniformly ultimate boundedness. The energy consumption model of the USV is constructed to reveal to the energy consumption. Simulation results demonstrate the effectiveness of the proposed controller.     

不确定性自由漂浮空间机器人神经自适应控制

针对具有模型不确定性以及外部干扰下的自由漂浮空间机器人,采用一种整体逼近的神经网络自适应控制方法。该方法采用RBF神经网络对不同重力环境下系统模型的不确定项进行整体逼近,对系统的不确定项进行在线自适应学习。神经网络的逼近误差以及外界干扰由鲁棒项进行消除。该方法不依赖于系统模型,简化了控制系统的结构,在考虑重力等不确定项的情况下不用改变控制器也能进行控制,并且根据李亚普诺夫理论证明了所设计控制器使系统渐进稳定。在不同重力环境下进行了仿真,验证了控制方案的有效性。     

Robot learning control based on recurrent neural network inverse model

A non-linear model-based feedforward, feedback, and learning controller is presented. This controller can control a non-linear plant such as a robot whose dynamics are initially unknown. In the feedforward part, a recurrent neural network (RNN) is used to model the inverse dynamics of the plant. In the feedback part, a PD controller is added to handle unmodeled dynamics and disturbances. Furthermore, an add-on learning controller is established to reduce tracking errors for repetitive tasks. The controller is validated with the control of a simulated two-joint manipulator. Simulation results show that the controller can successfully learn the inverse dynamics of a robot, perform accurate tracking for a general trajectory, and improve its own performance over the repetitions of a trajectory, with and without a payload change. © 1997 John Wiley & Sons, Inc.     

环卫车辆轨迹跟踪系统的无模型自适应迭代学习控制

针对环卫车辆周期重复性工作特点,考虑模型时变以及未知扰动问题,提出一种基于无模型自适应迭代学习的环卫车辆轨迹跟踪控制方法.首先,针对环卫车辆建立了两轮移动机器人的运动学模型,然后,给出带时变参数和非线性不确定项的迭代域下全格式动态线性化数据模型,引入时间差分估计算法,设计基于最优性能指标的轨迹跟踪无模型自适应迭代学习控...     

Prescribed performance adaptive neural tracking control for strict-feedback Markovian jump nonlinear systems with time-varying delay

A prescribed performance adaptive neural tracking control problem is investigated for strict-feedback Markovian jump nonlinear systems with time-varying delay. First, a new prescribed performance constraint variable is proposed to generate the virtual control that forces the tracking error to fall within prescribed boundaries. Combining with the approximation capability of neural networks and backstepping design, the adaptive tracking controller is designed. The designed controller is independent on time delay by constructing appropriate Lyapunov functions to offset the unknown time-varying delays. It is proved that the closed-loop system is uniformly ultimately bounded in probability, and that both steady-state and transient-state performances are guaranteed. Finally, simulation results are given to illustrate the effectiveness of the proposed approach.     

Applications of neural networks for coordinate transformations in robotics

The use of artificial neural networks is investigated for application to trajectory control problems in robotics. The relative merits of position versus velocity control is considered and a control scheme is proposed in which neural networks are used as static maps (trained off-line) to compute the inverse of the manipulator Jacobian matrix. A proof of the stability of this approach is offered, assuming bounded errors in the static map. A representative two-link robot is investigated using an artificial neural network which has been trained to compute the components of the inverse of the Jacobian matrix. The controller is implemented in the laboratory and its performance compared to a similar controller with the analytical inverse Jacobian matrix.     

漂浮基空间机器人的径向基神经网络鲁棒自适应控制

针对一类同时具有参数及非参数不确定性的自由漂浮空间机器人系统的轨迹跟踪问题,采用了一种RBF神经网络的自适应鲁棒补偿控制策略.对于系统的参数不确定性,通过对径向基神经网络来自适应学习并补偿,逼近误差通过滑模控制器消除,神经网络权重的自适应修正规则基于Lyapunov函数方法得到;而非参数不确定通过鲁棒控制器来实时自适应...     

Task-space neuro-sliding mode control of robot manipulators under Jacobian uncertainties

Cartesian robot control is an appealing scheme because it avoids the computation of inverse kinematics, in contrast to joint robot control approach. For tracking, high computational load is typically required to obtain Cartesian robot dynamics. In this paper, an alternative approach for Cartesian tracking is proposed under assumption that robot dynamics is unknown and the Jacobian are uncertain. A neuro-sliding second order mode controller delivers a low dimensional neural network, which roughly estimates inverse robot dynamics, and an inner smooth control loop guarantees exponential tracking. Experimental results are presented to confirm the performance in a real time environment.     

An Adaptive Controller Dominant-Type Hybrid Adaptive and Learning Controller for Trajectory Tracking of Robot Manipulators

This paper proposes a new hybrid adaptive and learning control method based on combining model-based adaptive control, repetitive learning control (RLC) and proportional–derivative control to consider the periodic trajectory tracking problem of robot manipulators. The aim of this study is to obtain a high-accuracy trajectory tracking controller by developing a simpler adaptive dominant-type hybrid controller by using only one vector for estimation of the unknown dynamical parameters in the control law. The RLC input is adopted using the original learning control law, adding a forgetting factor to achieve the convergence of the learning control input to zero. We will improve and prove that the adaptive dominant-type controller could be applied for tracking a periodic desired trajectory in which adaptive control input increases and becomes dominant of the control input, whereas the other control inputs decrease close to zero. The domination of the adaptive control input gives the advantage that the proposed controller could adjust the feed-forward control input immediately and it does not spend much time relearning the learning control input when the periodic desired trajectory is switched over from the first trajectory to another trajectory. We utilize the Lyapunovlike method to prove the stability of the proposed controller and computer simulation results to validate the effectiveness of the proposed controller in achieving the accurate tracking to the periodic desired trajectory.     

Asymptotically stable visual servoing of manipulators via neural networks

In this article we present a class of position control schemes for robot manipulators based on feedback of visual information processed through artificial neural networks. We exploit the approximation capabilities of neural networks to avoid the computation of the robot inverse kinematics as well as the inverse task space–camera mapping which involves tedious calibration procedures. Our main stability result establishes rigorously that in spite of the neural network giving an approximation of these mappings, the closed‐loop system including the robot nonlinear dynamics is locally asymptotically stable provided that the Jacobian of the neural network is nonsingular. The feasibility of the proposed neural controller is illustrated through experiments on a planar robot. © 2000 John Wiley & Sons, Inc.     

非完整移动机器人的神经网络鲁棒自适应控制

在非完整移动机器人轨迹跟踪问题中,针对机器人运动学与动力学模型的参数和非参数不确定性,提出了一种混合神经网络鲁棒自适应轨迹跟踪控制器,该控制器由运动学控制器和动力学控制器两部分组成;其中,采用了参数自适应的径向基神经网络对运动学模型的未知部分进行了建模,并采用权值在线调整的单层神经网络和自适应鲁棒控制项构成了动力学控制器;基于Lyapunov方法的设计过程保证了系统的稳定性和收敛性,仿真结果证明了算法的有效性。     

Stable Sampled-data Adaptive Control of Robot Arms Using Neural Networks

Stable neural network-based sampled-data indirect and direct adaptivecontrol approaches, which are the integration of a neural network (NN)approach and the adaptive implementation of the discrete variable structurecontrol, are developed in this paper for the trajectory tracking control ofa robot arm with unknown nonlinear dynamics. The robot arm is assumed tohave an upper and lower bound of its inertia matrix norm and its states areavailable for measurement. The discrete variable structure control servestwo purposes, i.e., one is to force the system states to be within the stateregion in which neural networks are used when the system goes out of neuralcontrol; and the other is to improve the tracking performance within the NNapproximation region. Main theory results for designing stable neuralnetwork-based sampled data indirect and direct adaptive controllers aregiven, and the extension of the proposed control approaches to the compositeadaptive control of a flexible-link robot is discussed. Finally, theeffectiveness of the proposed control approaches is illustrated throughsimulation studies.     

Adaptive iterative learning control for robot manipulators

In this paper, we propose some adaptive iterative learning control (ILC) schemes for trajectory tracking of rigid robot manipulators, with unknown parameters, performing repetitive tasks. The proposed control schemes are based upon the use of a proportional-derivative (PD) feedback structure, for which an iterative term is added to cope with the unknown parameters and disturbances. The control design is very simple in the sense that the only requirement on the PD and learning gains is the positive definiteness condition and the bounds of the robot parameters are not needed. In contrast to classical ILC schemes where the number of iterative variables is generally equal to the number of control inputs, the second controller proposed in this paper uses just two iterative variables, which is an interesting fact from a practical point of view since it contributes considerably to memory space saving in real-time implementations. We also show that it is possible to use a single iterative variable in the control scheme if some bounds of the system parameters are known. Furthermore, the resetting condition is relaxed to a certain extent for a certain class of reference trajectories. Finally, simulation results are provided to illustrate the effectiveness of the proposed controllers.     

Learning of a controller for non-recurring fast movements

In this paper a learning method is described which enables a conventional industrial robot to accurately execute the teach-in path in the presence of dynamical effects and high speed. After training the system is capable of generating positional commands that in combination with the standard robot controller lead the robot along the desired trajectory. The mean path deviations are reduced to a factor of 20 for our test configuration. For low speed motion the learned controllers' accuracy is in the range of the resolution of the positional encoders. The learned controller does not depend on specific trajectories. It acts as a general controller that can be used for non-recurring tasks as well as for sensor-based planned paths. For repetitive control tasks accuracy can be even increased. Such improvements are caused by a three level structure estimating a simple process model, optimal a posteriori commands, and a suitable feedforward controller, the latter including neural networks for the representation of nonlinear behaviour. The learning system is demonstrated in experiments with a Manutec R2 industrial robot. After training with only two sample trajectories the learned control system is applied to other totally different paths which are executed with high precision as well.     

时变时滞非线性系统自适应神经网络控制

对于一类具有未知时变时滞和虚拟控制系数的不确定严格反馈非线性系统,基于后推设计提出一种自适应神经网络控制方案.选取适当的Lyapunov-Krasovskii泛函补偿未知时变时滞不确定项.通过构造连续的待逼近函数来解决利用神经网络对未知非线性函数进行逼近时出现的奇异问题.通过引入一个新的中间变量,保证了虚拟控制求导的正确性.仿真算例表明,所设计的控制器能保证闭环系统所有信号是半全局一致终结有界的,且跟踪误差收敛到零的一个邻域内.