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.     

Observer-Based Adaptive Controller Design of Flexible Manipulators Using Time-Delay Neuro-Fuzzy Networks

In this paper, a dynamical time-delay neuro-fuzzy controller is proposed for the adaptive control of a flexible manipulator. It is assumed that the robotic manipulator has only joint angle position measurements. A linear observer is used to estimate the robot joint angle velocity. For a perfect tracking control of the robot, the output redefinition approach is used in the adaptive controller design using time-delay neuro-fuzzy networks. The time-delay neuro-fuzzy networks with the rule representation of the TSK type fuzzy system have better learning ability for complex dynamics as compared with existing neural networks. The novel control structure and learning algorithm are given, and a simulation for the trajectory tracking of a flexible manipulator illustrates the control performance of the proposed control approach.     

Reinforcement learning neural-network-based controller for nonlinear discrete-time systems with input constraints.

A novel adaptive-critic-based neural network (NN) controller in discrete time is designed to deliver a desired tracking performance for a class of nonlinear systems in the presence of actuator constraints. The constraints of the actuator are treated in the controller design as the saturation nonlinearity. The adaptive critic NN controller architecture based on state feedback includes two NNs: the critic NN is used to approximate the "strategic" utility function, whereas the action NN is employed to minimize both the strategic utility function and the unknown nonlinear dynamic estimation errors. The critic and action NN weight updates are derived by minimizing certain quadratic performance indexes. Using the Lyapunov approach and with novel weight updates, the uniformly ultimate boundedness of the closed-loop tracking error and weight estimates is shown in the presence of NN approximation errors and bounded unknown disturbances. The proposed NN controller works in the presence of multiple nonlinearities, unlike other schemes that normally approximate one nonlinearity. Moreover, the adaptive critic NN controller does not require an explicit offline training phase, and the NN weights can be initialized at zero or random. Simulation results justify the theoretical analysis.     

Reinforcement learning-based output feedback control of nonlinear systems with input constraints.

A novel neural network (NN)-based output feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multi-input and multi-output (MIMO) strict feedback nonlinear discrete-time systems. Reinforcement learning is proposed for the output feedback controller, which uses three NNs: 1) an NN observer to estimate the system states with the input-output data, 2) a critic NN to approximate certain strategic utility function, and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. Using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the state estimation errors, the tracking errors and weight estimates is shown.     

Stable Neuro-Adaptive Control for Robots with the Upper Bound Estimation on the Neural Approximation Errors

An indirect adaptive control approach is developed in this paper for robots with unknown nonlinear dynamics using neural networks (NNs). A key property of the proposed approach is that the actual joint angle values in the control law are replaced by the desired joint angles, angle velocities and accelerators, and the bound on the NN reconstruction errors is assumed to be unknown. Main theoretical results for designing such a neuro-controller are given, and the control performance of the proposed controller is verified with simulation studies.     

Adaptive neural control for an uncertain robotic manipulator with joint space constraints

In this paper, adaptive neural tracking control is proposed for a robotic manipulator with uncertainties in both manipulator dynamics and joint actuator dynamics. The manipulator joints are subject to inequality constraints, i.e., the joint angles are required to remain in some compact sets. Integral barrier Lyapunov functionals (iBLFs) are employed to address the joint space constraints directly without performing an additional mapping to the error space. Neural networks (NNs) are utilised to compensate for the unknown robot dynamics and external force. Adapting parameters are developed to estimate the unknown bounds on NN approximations. By the Lyapunov synthesis, the proposed control can guarantee the semi-global uniform ultimate boundedness of the closed-loop system, and the practical tracking of joint reference trajectory is achieved without the violation of predefined joint space constraints. Simulation results are given to validate the effectiveness of the proposed control scheme.     

Neural networks for advanced control of robot manipulators

Presents an approach and a systematic design methodology to adaptive motion control based on neural networks (NNs) for high-performance robot manipulators, for which stability conditions and performance evaluation are given. The neurocontroller includes a linear combination of a set of off-line trained NNs, and an update law of the linear combination coefficients to adjust robot dynamics and payload uncertain parameters. A procedure is presented to select the learning conditions for each NN in the bank. The proposed scheme, based on fixed NNs, is computationally more efficient than the case of using the learning capabilities of the neural network to be adapted, as that used in feedback architectures that need to propagate back control errors through the model to adjust the neurocontroller. A practical stability result for the neurocontrol system is given. That is, we prove that the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the NN bank and the design parameters of the controller. In addition, a robust adaptive controller to NN learning errors is proposed, using a sign or saturation switching function in the control law, which leads to global asymptotic stability and zero convergence of control errors. Simulation results showing the practical feasibility and performance of the proposed approach to robotics are given.     

Output feedback tracking control of robot manipulators with model uncertainty via adaptive fuzzy logic

Many robot controllers require not only joint position measurements but also joint velocity measurements; however, most robotic systems are only equipped with joint position measurement devices. In this paper, a new output feedback tracking control approach is developed for the robot manipulators with model uncertainty. The approach suggested herein does not require velocity measurements and employs the adaptive fuzzy logic. The adaptive fuzzy logic allows us to approximate uncertain and nonlinear robot dynamics. Only one fuzzy system is used to implement the observer-controller structure of the output feedback robot system. It is shown in a rigorous manner that all the signals in a closed loop composed of a robot, an observer, and a controller are uniformly ultimately bounded. Finally, computer simulation results on three-link robot manipulators are presented to show the results which indicate good position tracking performance and robustness against payload uncertainty and external disturbances.     

Design of an amplitude-bounded output feedback adaptive neural control with guaranteed componentwise performance

This paper proposes a methodology for the design of a mixed output feedback linear and adaptive neural controller that guarantees componentwise boundedness of the tracking error within an a priori specified compact polyhedron for an uncertain nonlinear system. The approach is based on the design of a robust invariant ellipsoidal set where the adaptive neural network (NN) control is modeled as an amplitude-bounded signal. A linear error observer is employed to recover the unmeasured states, and a linear gain controller is used to enforce the containment of the ellipsoidal set within the performance polyhedron. The analysis and design of the observer and linear controller is set up as an LMI problem. The linear observer/controller scheme is then augmented with a general adaptive NN element having the purpose of approximating and compensating for the unknown nonlinearities thus providing performance improvement. The only requirement for the adaptive control signals is that their amplitudes must be confined within pre-specified limits. For this purpose, a novel mechanism called adaptive control redistribution is introduced to manage the adaptive NN control confinement during the online operation. A numerical example is used to illustrate the design methodology.     

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.     

Discrete-time neural network output feedback control of nonlinear discrete-time systems in non-strict form

An adaptive neural network (NN)-based output feedback controller is proposed to deliver a desired tracking performance for a class of discrete-time nonlinear systems, which are represented in non-strict feedback form. The NN backstepping approach is utilized to design the adaptive output feedback controller consisting of: (1) an NN observer to estimate the system states and (2) two NNs to generate the virtual and actual control inputs, respectively. The non-causal problem encountered during the control design is overcome by using a dynamic NN which is constructed through a feedforward NN with a novel weight tuning law. The separation principle is relaxed, persistency of excitation condition (PE) is not needed and certainty equivalence principle is not used. The uniformly ultimate boundedness (UUB) of the closed-loop tracking error, the state estimation errors and the NN weight estimates is demonstrated. Though the proposed work is applicable for second order nonlinear discrete-time systems expressed in non-strict feedback form, the proposed controller design can be easily extendable to an nth order nonlinear discrete-time system.     

High-performance object tracking and fixation with an online neural estimator.

Vision-based target tracking and fixation to keep objects that move in three dimensions in view is important for many tasks in several fields including intelligent transportation systems and robotics. Much of the visual control literature has focused on the kinematics of visual control and ignored a number of significant dynamic control issues that limit performance. In line with this, this paper presents a neural network (NN)-based binocular tracking scheme for high-performance target tracking and fixation with minimum sensory information. The procedure allows the designer to take into account the physical (Lagrangian dynamics) properties of the vision system in the control law. The design objective is to synthesize a binocular tracking controller that explicitly takes the systems dynamics into account, yet needs no knowledge of dynamic nonlinearities and joint velocity sensory information. The combined neurocontroller-observer scheme can guarantee the uniform ultimate bounds of the tracking, observer, and NN weight estimation errors under fairly general conditions on the controller-observer gains. The controller is tested and verified via simulation tests in the presence of severe target motion changes.     

Stable adaptive controller design of robotic manipulators via neuro‐fuzzy dynamic inversion

In this paper, a stable adaptive control approach is developed for the trajectory tracking of a robotic manipulator via neuro‐fuzzy (NF) dynamic inversion, an inverse model constructed by the dynamic neuro‐fuzzy (DNF) model with desired dynamics. The robot neuro‐fuzzy model is initially built in the Takagi‐Sugeno (TS) fuzzy framework with both structure and parameters identified through input/output (I/O) data from the robot control process, and then employed to dynamically approximate the whole robot dynamics rather than its nonlinear components as is done by static neural networks (NNs) through parameter learning algorithm. Since the NF dynamic inversion comprises a cluster of reference trajectories connecting the initial state to the desired state of the robot, the dynamic performance in the initial control stage of robot trajectory tracking can be guaranteed by choosing the optimum reference trajectory. Furthermore, the assumption that the robot states should be on a compact set can be excluded by NF dynamic inversion design. The system stability and the convergence of tracking errors are guaranteed by Lyapunov stability theory, and the learning algorithm for the DNF system is obtained thereby. Finally, the viability and effectiveness of the proposed control approach are illustrated through comparing with the dynamic NN (DNN) based control approach. © 2005 Wiley Periodicals, Inc.     

An adaptive neural network switching control approach of robotic manipulators for trajectory tracking

In this paper, an adaptive neural network (NN) switching control strategy is proposed for the trajectory tracking problem of robotic manipulators. The proposed system comprises an adaptive switching neural controller and the associated robust compensation control law. Based on the Lyapunov stability theorem and average dwell-time approach, it is shown that the proposed control scheme can guarantee tracking performance of the robotic manipulators system, in the sense that all variables of the closed-loop system are bounded and the effect due to the external disturbance and approximate error of radical basis function (RBF) NNs on the tracking error can be converged to zero in an infinite time. Finally, simulation results on a two-link robotic manipulator show the feasibility and validity of the proposed control scheme.     

电驱动刚性机器人的鲁棒神经网络复合控制

采用逐步逆向的设计思想，提出一种新的电驱动刚性机器人轨迹跟踪的鲁棒神经网络复合控制策略，该策略不仅能有效地消除模型不确定性的影响，而且可避免复杂的求导运算以及对关节角加速度可测的要求。给出了控制器的具体组成和神经网络连接权的在线学习算法，理论表明该算法能保证跟踪误差及神经网络连接权估计最终一致有界，仿真结果也验证了算法的有效性。     

Neural-Network-Based State Feedback Control of a Nonlinear Discrete-Time System in Nonstrict Feedback Form

In this paper, a suite of adaptive neural network (NN) controllers is designed to deliver a desired tracking performance for the control of an unknown, second-order, nonlinear discrete-time system expressed in nonstrict feedback form. In the first approach, two feedforward NNs are employed in the controller with tracking error as the feedback variable whereas in the adaptive critic NN architecture, three feedforward NNs are used. In the adaptive critic architecture, two action NNs produce virtual and actual control inputs, respectively, whereas the third critic NN approximates certain strategic utility function and its output is employed for tuning action NN weights in order to attain the near-optimal control action. Both the NN control methods present a well-defined controller design and the noncausal problem in discrete-time backstepping design is avoided via NN approximation. A comparison between the controller methodologies is highlighted. The stability analysis of the closed-loop control schemes is demonstrated. The NN controller schemes do not require an offline learning phase and the NN weights can be initialized at zero or random. Results show that the performance of the proposed controller schemes is highly satisfactory while meeting the closed-loop stability.      

Decentralized adaptive tracking control of robot manipulators

An asymptotically stable decentralized adaptive control scheme is presented to enable accurate trajectory tracking without requiring specific knowledge about the robot dynamics. The scheme is based on expressing the robot dynamics as the product of individual joint quantities, and bounds on certain robot parameters. Parameter adaptation laws are derived using the Lyapunov theory, and asymptotic stability of tracking errors, and boundedness of parameter estimates are established. The control system is shown to be robust to torque disturbances affecting the system and to a class of unmodeled dynamics. The structure of the controller and the performance of the closed-loop system are analyzed. Simulations results using the complete dynamic model of a six degree of freedom industrial robot are presented to demonstrate the excellent tracking performance of the proposed adaptive control scheme. © 1996 John Wiley & Sons, Inc.     

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.     

Adaptive neural controller for space robot system with an attitude controlled base

In this paper, an adaptive neural network-based controller is proposed for a space robot system with an attitude controlled base without joint acceleration measurements and in the presence of parametric uncertainties and external disturbances. Based on the dynamic model, a neural network-based controller is proposed that achieves the required tracking effectively. A feedforward neural network is employed to learn the existing unknown dynamics of robot system. The uniform ultimate boundedness of all signals in the closed-loop system is guaranteed by the Lyapunov approach. It is shown that the neural network can cope with the unknown nonlinearities through the adaptive learning process and requires no preliminary off learning. Finally, simulation study has been performed to evaluate the controller performance.