Search

To realize the robust control of multirotor unmanned aerial vehicle (UAV) systems, adaptive multilayer neural dynamics (AMND) controllers are proposed and analyzed. The proposed AMND controllers with the strong anti-perturbation property can drive multirotor UAVs to track time-varying tasks and deal with parameter uncertainty problems. First, the design method of the general multilayer neural dynamics (MLND) controllers is introduced and analyzed. Second, based on the design method, the attitude angles, height, and position controllers of a UAV system are designed. Third, according to the adaptive control theory, a novel AMND controller is designed, which can self-tune the parameters of the UAV. Finally, the proposed AMND method applies to a real-world hexrotor UAV system to illustrate its reliability. Mathematical analysis, computer simulations, and experiments verify the reliability, stability, and effectiveness of the proposed controllers which are used to track time-varying tasks. [ABSTRACT FROM AUTHOR]

To solve a general time-varying Sylvester equation, a novel integral recurrent neural network (IRNN) is designed and analyzed. This kind of recurrent neural networks is based on an error-integral design equation and does not need training in advance. The IRNN can achieve global convergence performance and strong robustness if odd-monotonically increasing activation functions [i.e., the linear, bipolar-sigmoid, power, or sigmoid-power activation functions (SP-AFs)] are applied. Specifically, if linear or bipolar-sigmoid activation functions are applied, the IRNN possess exponential convergence performance. The IRNN has finite-time convergence property by using power activation function. To obtain faster convergence performance and finite-time convergence property, an SP-AF is designed. Furthermore, by using the discretization method, the discrete IRNN model and its convergence analysis are also presented. Practical application to robot manipulator and computer simulation results with using different activation functions and design parameters have verified the effectiveness, stability, and reliability of the proposed IRNN. [ABSTRACT FROM AUTHOR]

Zeroing neural network (ZNN), as an important class of recurrent neural network, has wide applications in various computation and optimization fields. In this article, based on the traditional-type zeroing neural network (TT-ZNN) model, an adaptive fuzzy-type zeroing neural network (AFT-ZNN) model is proposed to settle time-variant quadratic programming problem via integrating an adaptive fuzzy control strategy. The most prominent feature of the AFT-ZNN model is to use an adaptive fuzzy control value to adaptively adjust its convergence rate according to the value of the computational error. Four different activation functions are injected to analyze the convergence rate of the AFT-ZNN model. In addition, different membership functions and different ranges of the fuzzy control value are discussed to study the character of the AFT-ZNN model. Theoretical analysis and numerical comparison results further show that the AFT-ZNN model has better performance than the TT-ZNN model. [ABSTRACT FROM AUTHOR]

To make manipulators fulfill end-effector maintaining tasks, such as writing or drawing tasks in a complex environment, two hybrid multiobjective motion planing schemes, i.e., end-effector posture-maintaining and obstacle avoidance (hybrid PM-OA) schemes are proposed and investigated for wheeled mobile redundant robot manipulators. Specifically, the end-effector posture maintaining, obstacle avoidance, and joint physical limits are considered in a quadratic programming (QP) problem. With these two hybrid PM-OA schemes, the wheeled mobile robot manipulators can maintain its end-effector posture, avoid the obstacle and joint physical limits during executing end-effector tasks. The hybrid PM-OA schemes are finally formulated into a piecewise-linear projection equations (PLPEs) and solved by a recurrent neural network (RNN). Computer simulations are given to substantiate the effectiveness, accuracy, safety, and practicability of the proposed hybrid PM-OA schemes. Comparisons with other schemes and simulations further show that the proposed hybrid PM-OA schemes are more suitable for applications. [ABSTRACT FROM AUTHOR]

Varying-parameter recurrent neural network, being a special kind of neural-dynamic methodology, has revealed powerful abilities to handle various time-varying problems, such as quadratic minimization (QM) and quadratic programming (QP) problems. In this paper, a novel power-type varying-parameter recurrent neural network (PT-VP-RNN) is proposed to solve the perturbed time-varying QM and QP problems. First, based on the generalization of time-varying QM and QP problems, the design process of the PT-VP-RNN is presented in detail. Second, the robustness performance of the proposed PT-VP-RNN is theoretically analyzed and proved. What is more, two numerical examples are simulated to illustrate the robustness convergence performance of PT-VP-RNN even in a large disturbance condition. Finally, two practical application examples (i.e., a robot tracking example and a venture investment example) further verify the effectiveness, accuracy, and widespread applicability of the proposed PT-VP-RNN. [ABSTRACT FROM AUTHOR]

In order to effectively decrease the joint-angular drifts and end-effector position accumulation errors, a novel adaptive fuzzy recurrent neural network (AFRNN) is proposed and exploited to solve the nonrepetitive motion problem of redundant robot manipulators in this paper. First, a quadratic programming (QP)-based repetitive motion scheme is designed according to the kinematics constraint of redundant robot manipulators. Second, the QP-based repetitive motion scheme is converted to a matrix equation according to the Lagrangian multiplier method. Third, inspired by the neural-dynamic and fuzzy control theory, the AFRNN model is designed, which can effectively solve the matrix equation as well as the original nonrepetitive motion problem of redundant robot manipulators. Computer simulation results verify the effectiveness, high accuracy, and robustness to resist external disturbance of the proposed AFRNN scheme. [ABSTRACT FROM AUTHOR]

Two novel nonlinearly activated recurrent neural networks (RNNs) with finite-time convergence [called finite-time RNNs (FTRNNs)] are proposed and analyzed to solve efficiently time-varying systems of nonlinear equations (SoNEs). Compared with previously presented neural networks for solving such a SoNE, the FTRNNs are activated by new nonlinear activation functions and thus possess a better finite-time convergence property. In addition, theoretical analyses about FTRNNs are presented to determine the upper bounds of convergence time under the context of using such two novel nonlinear activation functions. Computer simulations based on a numerical example validate the preponderance of the proposed FTRNNs for time-varying SoNE, as compared to the recently proposed Zhang neural network and its improved version. Finally, an engineering practical example to motion tracking of a robot manipulator demonstrates the feasibility and applicability of the FTRNNs. [ABSTRACT FROM AUTHOR]

A novel varying-parameter recurrent neural network [called varying-parameter convergent-differential neural network (VP-CDNN)] is proposed and investigated to solve time-varying convex quadratic programing (QP) problems and applied to solve nonrepetitive problems of redundant robot manipulators in this brief. First, the nonrepetitive problems of redundant robot manipulators are reformulated as a QP scheme. Second, the QP scheme is reformulated as a matrix equation. Third, the proposed VP-CDNN is applied to solve the matrix equation as well as the original QP problem. To illustrate the advantages of VP-CDNN solver, comparison simulations between the VP-CDNN and the fixed-parameter convergent-differential neural network (FP-CDNN) are constructed based on a six-degrees-of-freedom robot manipulator. Two end-effector tasks employed by the VP-CDNN with linear activation function and sinh activation function verify the effectiveness and advantages of the proposed VP-CDNN and its better expansibility. The results of computer simulations and physical experiments demonstrate that the VP-CDNN solver is more effective and accurate than the FP-CDNN solver to solve nonrepetitive problems of redundant robot manipulators. [ABSTRACT FROM AUTHOR]

A novel recurrent neural network, which is named as complex varying-parameter convergent-differential neural network (CVP-CDNN), is proposed in this paper for solving the time-varying complex Sylvester equation. Two kinds of CVP-CDNNs (i.e., CVP-CDNN Type I and Type II) are illustrated and proved to be effective. The proposed CVP-CDNNs can achieve super-exponential performance if the linear activation function is used. Some activation functions are considered for searching the better performance of the CVP-CDNN and the finite time convergence property of the CVP-CDNN with sign-bi-power activation function is testified. The convergence time of the CVP-CDNN with sign-bi-power activation function is shorter than complex fixed-parameter convergent-differential neural network (CFP-CDNN). Moreover, compared with traditional CFP-CDNN, better convergence performances of novel CVP-CDNN are verified by computer simulation comparisons. [ABSTRACT FROM AUTHOR]

Solving Sylvester equation is a common algebraic problem in mathematics and control theory. Different from the traditional fixed-parameter recurrent neural networks, such as gradient-based recurrent neural networks or Zhang neural networks, a novel varying-parameter recurrent neural network, [called varying-parameter convergent-differential neural network (VP-CDNN)] is proposed in this paper for obtaining the online solution to the time-varying Sylvester equation. With time passing by, this kind of new varying-parameter neural network can achieve super-exponential performance. Computer simulation comparisons between the fixed-parameter neural networks and the proposed VP-CDNN via using different kinds of activation functions demonstrate that the proposed VP-CDNN has better convergence and robustness properties. [ABSTRACT FROM AUTHOR]

The Lyapunov equation is widely employed in the engineering field to analyze stability of dynamic systems. In this paper, based on a new evolution formula, a novel finite-time recurrent neural network (termed finite-time Zhang neural network, FTZNN) is proposed and studied for solving a nonstationary Lyapunov equation. In comparison with the original Zhang neural network (ZNN) model for a nonstationary Lyapunov equation, the convergence performance has a remarkable improvement for the proposed FTZNN model and can be accelerated to finite time. Besides, by solving the differential inequality, the time upper bound of the FTZNN model is computed theoretically and analytically. Simulations are conducted and compared to validate the superiority of the FTZNN model to the original ZNN model for solving the nonstationary Lyapunov equation. At last, the FTZNN model is successfully applied to online tracking control of a wheeled mobile manipulator. [ABSTRACT FROM PUBLISHER]