A Novel Recurrent Neural Network for Manipulator Control With Improved Noise Tolerance

An FPGA-Implemented Antinoise Fuzzy Recurrent Neural Network for Motion Planning of Redundant Robot Manipulators

When a robot completes end-effector tasks, internal error noises always exist. To resist internal error noises of robots, a novel fuzzy recurrent neural network (FRNN) is proposed, designed, and implemented on field-programmable gated array (FPGA). The implementation is pipeline-based, which guarantees the order of overall operations. The data processing is based on across-clock domain, which is beneficial for computing units' acceleration. Compared with traditional gradient-based neural networks (NNs) and zeroing neural networks (ZNNs), the proposed FRNN has faster convergence rate and higher correctness. Practical experiments on a 3 degree-of-freedom (DOs) planar robot manipulator show that the proposed fuzzy RNN coprocessor needs 496 lookup table random access memories (LUTRAMs), 205.5 block random access memories (BRAMs), 41384 lookup tables (LUTs), and 16743 flip-flops (FFs) of the Xilinx XCZU9EG chip.

A Jump-Gain Integral Recurrent Neural Network for Solving Noise-Disturbed Time-Variant Nonlinear Inequality Problems

Nonlinear inequalities are widely used in science and engineering areas, attracting the attention of many researchers. In this article, a novel jump-gain integral recurrent (JGIR) neural network is proposed to solve noise-disturbed time-variant nonlinear inequality problems. To do so, an integral error function is first designed. Then, a neural dynamic method is adopted and the corresponding dynamic differential equation is obtained. Third, a jump gain is exploited and applied to the dynamic differential equation. Fourth, the derivatives of errors are substituted into the jump-gain dynamic differential equation, and the corresponding JGIR neural network is set up. Global convergence and robustness theorems are proposed and proved theoretically. Computer simulations verify that the proposed JGIR neural network can solve noise-disturbed time-variant nonlinear inequality problems effectively. Compared with some advanced methods, such as modified zeroing neural network (ZNN), noise-tolerant ZNN, and varying-parameter convergent-differential neural network, the proposed JGIR method has smaller computational errors, faster convergence speed, and no overshoot when disturbance exists. In addition, physical experiments on manipulator control have verified the effectiveness and superiority of the proposed JGIR neural network.

Self-Constructing Fuzzy Neural Fractional-Order Sliding Mode Control of Active Power Filter

In this article, a fractional-order sliding mode control (FOSMC) scheme is proposed for mitigating harmonic distortions in the power system, whereby a self-constructing recurrent fuzzy neural network (SCRFNN) is used to weaken the effect of compound nonlinearity caused by unknown uncertainties and environmental fluctuations. The fractional-order sliding mode controller (SMC) is constructed to maintain the control system to be asymptotically stable and a fractional-order calculus is introduced into an SMC to soften the sliding manifold design and realize chattering reduction. Considering parameter variations existing in the power system model, SCRFNN is adopted to approximate the unknown dynamics, which is able to dynamically update network structure by optimizing the fuzzy division, and a feedback connection is incorporated into the feedforward neural network, which is regarded as a storage unit to enhance the capability of coping with temporal problem. The control scheme combining the FOSMC with the SCRFNN can make the tracking error and its time derivative converge to zero. Experimental studies demonstrate the validity of the designed scheme, and comprehensive comparisons illustrate its superiority in harmonic suppression and high robustness.

A Novel Convolutional Neural Network Model Based on Beetle Antennae Search Optimization Algorithm for Computerized Tomography Diagnosis

Convolutional neural networks (CNNs) are widely used in the field of medical imaging diagnosis but have the disadvantages of slow training speed and low diagnostic accuracy due to the initialization of parameters before training. In this article, a CNN optimization method based on the beetle antennae search (BAS) optimization algorithm is proposed. The method optimizes the initial parameters of the CNN through the BAS optimization algorithm. Based on this optimization approach, a novel CNN model with a pretrained BAS optimization algorithm was developed and applied to the analysis and diagnosis of medical imaging data for intracranial hemorrhage. Experimental results on 330 test images show that the proposed method has a better diagnostic performance than the traditional CNN. The proposed method achieves a diagnostic accuracy of 93.9394% and 100% recall, and the diagnosis of 66 human head computerized tomography image data only takes 0.1596 s. Moreover, the proposed method has more advantages than the three other optimization algorithms.

SE-TCN network for continuous estimation of upper limb joint angles

The maturity of human-computer interaction technology has made it possible to use surface electromyographic signals (sEMG) to control exoskeleton robots and intelligent prostheses. However, the available upper limb rehabilitation robots controlled by sEMG have the shortcoming of inflexible joints. This paper proposes a method based on a temporal convolutional network (TCN) to predict upper limb joint angles by sEMG. The raw TCN depth was expanded to extract the temporal features and save the original information. The timing sequence characteristics of the muscle blocks that dominate the upper limb movement are not apparent, leading to low accuracy of the joint angle estimation. Therefore, this study squeeze-and-excitation networks (SE-Net) to improve the network model of the TCN. Finally, seven movements of the human upper limb were selected for ten human subjects, recording elbow angle (EA), shoulder vertical angle (SVA), and shoulder horizontal angle (SHA) values during their movements. The designed experiment compared the proposed SE-TCN model with the backpropagation (BP) and long short-term memory (LSTM) networks. The proposed SE-TCN systematically outperformed the BP network and LSTM model by the mean RMSE values: by 25.0 and 36.8% for EA, by 38.6 and 43.6% for SHA, and by 45.6 and 49.5% for SVA, respectively. Consequently, its R² values exceeded those of BP and LSTM by 13.6 and 39.20% for EA, 19.01 and 31.72% for SHA, and 29.22 and 31.89% for SVA, respectively. This indicates that the proposed SE-TCN model has good accuracy and can be used to estimate the angles of upper limb rehabilitation robots in the future.

Fuzzy Multiple Hidden Layer Recurrent Neural Control of Nonlinear System Using Terminal Sliding-Mode Controller

This study designs a fuzzy double hidden layer recurrent neural network (FDHLRNN) controller for a class of nonlinear systems using a terminal sliding-mode control (TSMC). The proposed FDHLRNN is a fully regulated network, which can be simply considered as a combination of a fuzzy neural network (FNN) and a radial basis function neural network (RBF NN) to improve the accuracy of a nonlinear approximation, so it has the advantages of these two neural networks. The main advantage of the proposed new FDHLRNN is that the output values of the FNN and DHLRNN are considered at the same time, and the outer layer feedback is added to increase the dynamic approximation ability. FDHLRNN was designed to approximate the nonlinear sliding-mode equivalent control term to reduce the switching gain. To ensure the best approximation capability and control performance, the proposed FDHLRNN using TSMC is applied for the second-order nonlinear model. Two simulation examples are implemented to verify that the proposed FDHLRNN has faster convergence speed and the FDHLRNN with TSMC has good dynamic property and robustness, and a hardware experimental study with an active power filter proves the feasibility of the method.

7-Instant Discrete-Time Synthesis Model Solving Future Different-Level Linear Matrix System via Equivalency of Zeroing Neural Network

Differing from the common linear matrix equation, the future different-level linear matrix system is considered, which is much more interesting and challenging. Because of its complicated structure and future-computation characteristic, traditional methods for static and same-level systems may not be effective on this occasion. For solving this difficult future different-level linear matrix system, the continuous different-level linear matrix system is first considered. On the basis of the zeroing neural network (ZNN), the physical mathematical equivalency is thus proposed, which is called ZNN equivalency (ZE), and it is compared with the traditional concept of mathematical equivalence. Then, on the basis of ZE, the continuous-time synthesis (CTS) model is further developed. To satisfy the future-computation requirement of the future different-level linear matrix system, the 7-instant discrete-time synthesis (DTS) model is further attained by utilizing the high-precision 7-instant Zhang et al. discretization (ZeaD) formula. For a comparison, three different DTS models using three conventional ZeaD formulas are also presented. Meanwhile, the efficacy of the 7-instant DTS model is testified by the theoretical analyses. Finally, experimental results verify the brilliant performance of the 7-instant DTS model in solving the future different-level linear matrix system.

Autonomous 6-DOF Manipulator Operation for Moving Target by a Capture and Placement Control System

The robot control technology combined with a machine vision system provides a feasible method for the autonomous operation of moving target. However, designing an effective visual servo control system is a great challenge. For the autonomous operation of the objects moving on the pipeline, this article is dedicated to developing a capture and placement control system for the six degrees of freedom (6-DOF) manipulator equipped with an eye-in-hand camera. Firstly, a path planning strategy of online capture and offline placement is proposed for real-time capture and efficient placement. Subsequently, to achieve the fast, stable, and robust capture for a moving target, a position-based visual servo (PBVS) controller is developed by combining estimated velocity feedforward and refined PID control. Feedforward control is designed using the estimated velocity by a proposed motion estimation method for high response speed. PID control is refined by dead zone constraint to reduce the manipulator’s jitter caused by the frequent adjustment of manipulator control system. Besides, the proportional, integral, and differential coefficients of PID controller are adaptively tuned by fuzzy control to reject the noise, disturbance, and dynamic variation in the capture process. Finally, validation experiments are performed on the constructed ROS–Gazebo simulation platform, demonstrating the effectiveness of the developed control system.

Adaptive Intelligent Sliding Mode Control of a Dynamic System with a Long Short-Term Memory Structure

In this work, a novel fuzzy neural network (NFNN) with a long short-term memory (LSTM) structure was derived and an adaptive sliding mode controller, using NFNN (ASMC-NFNN), was developed for a class of nonlinear systems. Aimed at the unknown uncertainties in nonlinear systems, an NFNN was designed to estimate unknown uncertainties, which combined the advantages of fuzzy systems and neural networks, and also introduced a special LSTM recursive structure. The special three gating units in the LSTM structure enabled it to have selective forgetting and memory mechanisms, which could make full use of historical information, and have a stronger ability to learn and estimate unknown uncertainties than general recurrent neural networks. The Lyapunov stability rule guaranteed the parameter convergence of the neural network and system stability. Finally, research into a simulation of an active power filter system showed that the proposed new algorithm had better static and dynamic properties and robustness compared with a sliding controller that uses a recurrent fuzzy neural network (RFNN).

Online Deflection Compensation of a Flexible Hydraulic Loader Crane Using Neural Networks and Pressure Feedback

The deflection compensation of a hydraulically actuated loader crane is presented. Measurement data from the laboratory are used to design a neural network deflection estimator. Kinematic expressions are derived and used with the deflection estimator in a feedforward topology to compensate for the static deflection. A dynamic deflection compensator is implemented, using pressure feedback and an adaptive bandpass filter. Simulations are conducted to verify the performance of the control system. Experimental results showcase the effectiveness of both the static and dynamic deflection compensator while running closed-loop motion control, with a 90% decrease in static deflection.

RNN for Repetitive Motion Generation of Redundant Robot Manipulators: An Orthogonal Projection-Based Scheme

For the existing repetitive motion generation (RMG) schemes for kinematic control of redundant manipulators, the position error always exists and fluctuates. This article gives an answer to this phenomenon and presents the theoretical analyses to reveal that the existing RMG schemes exist a theoretical position error related to the joint angle error. To remedy this weakness of existing solutions, an orthogonal projection RMG (OPRMG) scheme is proposed in this article by introducing an orthogonal projection method with the position error eliminated theoretically, which decouples the joint space error and Cartesian space error with joint constraints considered. The corresponding new recurrent neural networks (NRNNs) are structured by exploiting the gradient descent method with the assistance of velocity compensation with theoretical analyses provided to embody the stability and feasibility. In addition, simulation results on a fixed-based redundant manipulator, a mobile manipulator, and a multirobot system synthesized by the existing RMG schemes and the proposed one are presented to verify the superiority and precise performance of the OPRMG scheme for kinematic control of redundant manipulators. Moreover, via adjusting the coefficient, simulations on the position error and joint drift of the redundant manipulator are conducted for comparison to prove the high performance of the OPRMG scheme. To bring out the crucial point, different controllers for the redundancy resolution of redundant manipulators are compared to highlight the superiority and advantage of the proposed NRNN. This work greatly improves the existing RMG solutions in theoretically eliminating the position error and joint drift, which is of significant contributions to increasing the accuracy and efficiency of high-precision instruments in manufacturing production.

Visual Navigation With Multiple Goals Based on Deep Reinforcement Learning

Learning to adapt to a series of different goals in visual navigation is challenging. In this work, we present a model-embedded actor-critic architecture for the multigoal visual navigation task. To enhance the task cooperation in multigoal learning, we introduce two new designs to the reinforcement learning scheme: inverse dynamics model (InvDM) and multigoal colearning (MgCl). Specifically, InvDM is proposed to capture the navigation-relevant association between state and goal and provide additional training signals to relieve the sparse reward issue. MgCl aims at improving the sample efficiency and supports the agent to learn from unintentional positive experiences. Besides, to further improve the scene generalization capability of the agent, we present an enhanced navigation model that consists of two self-supervised auxiliary task modules. The first module, which is named path closed-loop detection, helps to understand whether the state has been experienced. The second one, namely the state-target matching module, tries to figure out the difference between state and goal. Extensive results on the interactive platform AI2-THOR demonstrate that the agent trained with the proposed method converges faster than state-of-the-art methods while owning good generalization capability. The video demonstration is available at https://vsislab.github.io/mgvn.

Inverse Kinematic Control of a Delta Robot Using Neural Networks in Real-Time

This paper presents an inverse kinematic controller using neural networks for trajectory controlling of a delta robot in real-time. The developed control scheme is purely data-driven and does not require prior knowledge of the delta robot kinematics. Moreover, it can adapt to the changes in the kinematics of the robot. For developing the controller, the kinematic model of the delta robot is estimated by using neural networks. Then, the trained neural networks are configured as a controller in the system. The parameters of the neural networks are updated while the robot follows a path to adaptively compensate for modeling uncertainties and external disturbances of the control system. One of the main contributions of this paper is to show that updating the parameters of neural networks offers a smaller tracking error in inverse kinematic control of a delta robot with consideration of joint backlash. Different simulations and experiments are conducted to verify the proposed controller. The results show that in the presence of external disturbance, the error in trajectory tracking is bounded, and the negative effect of joint backlash in trajectory tracking is reduced. The developed method provides a new approach to the inverse kinematic control of a delta robot.

Unified Model Solving Nine Types of Time-Varying Problems in the Frame of Zeroing Neural Network

Many time-varying problems have been solved using the zeroing neural network proposed by Zhang et al. In this article, nine types of time-varying problems, namely time-varying nonlinear equation system, time-varying linear equation system, time-varying convex nonlinear optimization under linear equalities, unconstrained time-varying convex nonlinear optimization, time-varying convex quadratic programming under linear equalities, unconstrained time-varying convex quadratic programming, time-varying nonlinear inequality system, time-varying linear inequality system, and time-varying division, are investigated to better understand the essence of zeroing neutral network. Discrete-form time-varying problems are studied by considering the nature of unknown future and the requirement of real-time computation for time-varying problems. A unified model is proposed in the frame of zeroing neural network to uniformly solve these time-varying problems on the basis of their connections and a newly developed discretization formula. Theoretical analyses and numerical experiments, including the tracking control of PUMA560 robot manipulator, verify the effectiveness and precision of the proposed unified model.

A Novel Supertwisting Zeroing Neural Network With Application to Mobile Robot Manipulators

Various zeroing neural network (ZNN) models have been investigated to address the tracking control of robot manipulators for the capacity of parallel processing and nonlinearity handling. However, two limitations occur in the existing ZNN models. The first one is the convergence time that tends to be infinitely large. The second one is the research of robustness that remains in the analyses of stability and asymptotic convergence. To simultaneously enhance the convergence performance and robustness, this article proposes a new ZNN model by using a supertwisting (ST) algorithm, termed STZNN model, for the tracking control of mobile robot manipulators. The proposed STZNN model inherently possesses the advantages of finite-time convergence and robustness making the control process fast and robust. The bridge from the sliding mode control to the ZNN is built, and the essential connection between the ST algorithm and ZNN is explored by constructing a unified design process. Theorems and proofs about global stability, finite-time convergence, and robustness are provided. Finally, path-tracking applications, comparisons, and tests substantiate the effectiveness and superiority of the STZNN model for the tracking control handling of mobile robot manipulators.

Mutual-Collision-Avoidance Scheme Synthesized by Neural Networks for Dual Redundant Robot Manipulators Executing Cooperative Tasks

Collision between dual robot manipulators during working process will lead to task failure and even robot damage. To avoid mutual collision of dual robot manipulators while doing collaboration tasks, a novel recurrent neural network (RNN)-based mutual-collision-avoidance (MCA) scheme for solving the motion planning problem of dual manipulators is proposed and exploited. Because of the high accuracy and low computation complexity, the linear variational inequality-based primal-dual neural network is used to solve the proposed scheme. The proposed scheme is applied to the collaboration trajectory tracking and cup-stacking tasks, and shows its effectiveness for avoiding collision between the dual robot manipulators. Through network iteration and online learning, the dual robot manipulators will learn the ability of MCA. Moreover, a line-segment-based distance measure algorithm is proposed to calculate the minimum distance between the dual manipulators. If the computed minimum distance is less than the first safe-related distance threshold, a speed brake operation is executed and guarantees that the robot cannot exceed the second safe-related distance threshold. Furthermore, the proposed MCA strategy is formulated as a standard quadratic programming problem, which is further solved by an RNN. Computer simulations and a real dual robot experiment further verify the effectiveness, accuracy, and physical realizability of the RNN-based MCA scheme when manipulators cooperatively execute the end-effector tasks.

Recurrent neural network with noise rejection for cyclic motion generation of robotic manipulators

Recurrent neural network (RNN), as a kind of neural network with outstanding computing capability, improvability, and hardware realizability, has been widely used in various fields, especially in robotics. In this paper, an RNN with noise rejection is deliberately constructed to remedy the issue of joint-angle drift frequently occurring during the cyclic motion generation (CMG) of a manipulator in a noisy environment. Different from general RNNs, the proposed RNN possesses inherent noise immunity, especially for time-varying polynomial noises. Besides, proofs on the convergence of the proposed RNN in the absence and presence of noises are given. Furthermore, we carry out simulations on manipulators PUMA 560 and UR5 to demonstrate the reliability of the proposed RNN in remedying joint-angle drift, and comparison simulations under different noisy conditions further verify its superiority. In addition, experiments are conducted on manipulator FRANKA Panda to elucidate the realizability of the proposed RNN.

Extended Robust Exponential Stability of Fuzzy Switched Memristive Inertial Neural Networks With Time-Varying Delays on Mode-Dependent Destabilizing Impulsive Control Protocol

This article investigates the problem of robust exponential stability of fuzzy switched memristive inertial neural networks (FSMINNs) with time-varying delays on mode-dependent destabilizing impulsive control protocol. The memristive model presented here is treated as a switched system rather than employing the theory of differential inclusion and set-value map. To optimize the robust exponentially stable process and reduce the cost of time, hybrid mode-dependent destabilizing impulsive and adaptive feedback controllers are simultaneously applied to stabilize FSMINNs. In the new model, the multiple impulsive effects exist between two switched modes, and the multiple switched effects may also occur between two impulsive instants. Based on switched analysis techniques, the Takagi-Sugeno (T-S) fuzzy method, and the average dwell time, extended robust exponential stability conditions are derived. Finally, simulation is provided to illustrate the effectiveness of the results.

RNN for Perturbed Manipulability Optimization of Manipulators Based on a Distributed Scheme: A Game-Theoretic Perspective

In order to leverage the unique advantages of redundant manipulators, avoiding the singularity during motion planning and control should be considered as a fundamental issue to handle. In this article, a distributed scheme is proposed to improve the manipulability of redundant manipulators in a group. To this end, the manipulability index is incorporated into the cooperative control of multiple manipulators in a distributed network, which is used to guide manipulators to adjust to the optimal spatial position. Moreover, from the perspective of game theory, this article formulates the problem into a Nash equilibrium. Then, a neural network with anti-noise ability is constructed to seek and approximate the optimal strategy profile of the Nash equilibrium problem with time-varying parameters. Theoretical analyses show that the neural network model has the superior global convergence and noise immunity. Finally, simulation results demonstrate that the neural network is effective in real-time cooperative motion generation of multiple redundant manipulators under perturbations in distributed networks.

Bi-criteria Acceleration Level Obstacle Avoidance of Redundant Manipulator

In this paper, an improved obstacle-avoidance-scheme-based kinematic control problem in acceleration level for a redundant robot manipulator is investigated. Specifically, the manipulator and obstacle are abstracted as mathematical geometries, based on the vector relationship between geometric elements, and the Cartesian coordinate of the nearest point to an obstacle on a manipulator can be found. The distance between the manipulator and an obstacle is described as the point-to-point distance, and the collision avoidance strategy is formulated as an inequality. To avoid the joint drift phenomenon of the manipulator, bi-criteria performance indices integrating joint-acceleration-norm minimization and repetitive motion planning is adopted by assigning a weighing factor. From the perspective of optimization, therefore, an acceleration level quadratic programming (QP) problem is eventually formulated. Considering the physical structure of robot manipulators, inherent joint angle, speed, and acceleration limits are also incorporated. To solve the resultant QP minimization problem, a recurrent neural network based neural dynamic solver is proposed. Then, simulation experiments performing on a four-link planar manipulator validate the feasibility and effectiveness of the proposed scheme.

Complex-Valued Discrete-Time Neural Dynamics for Perturbed Time-Dependent Complex Quadratic Programming With Applications

It has been reported that some specially designed recurrent neural networks and their related neural dynamics are efficient for solving quadratic programming (QP) problems in the real domain. A complex-valued QP problem is generated if its variable vector is composed of the magnitude and phase information, which is often depicted in a time-dependent form. Given the important role that complex-valued problems play in cybernetics and engineering, computational models with high accuracy and strong robustness are urgently needed, especially for time-dependent problems. However, the research on the online solution of time-dependent complex-valued problems has been much less investigated compared to time-dependent real-valued problems. In this article, to solve the online time-dependent complex-valued QP problems subject to linear constraints, two new discrete-time neural dynamics models, which can achieve global convergence performance in the presence of perturbations with the provided theoretical analyses, are proposed and investigated. In addition, the second proposed model is developed to eliminate the operation of explicit matrix inversion by introducing the quasi-Newton Broyden-Fletcher-Goldfarb-Shanno (BFGS) method. Moreover, computer simulation results and applications in robotics and filters are provided to illustrate the feasibility and superiority of the proposed models in comparison with the existing solutions.

Improved Sliding Mode Control for Finite-Time Synchronization of Nonidentical Delayed Recurrent Neural Networks

This brief further explores the problem of finite-time synchronization of delayed recurrent neural networks with the mismatched parameters and neuron activation functions. An improved sliding mode control approach is presented for addressing the finite-time synchronization problem. First, by employing the drive-response concept and the synchronization error of drive-response systems, a novel integral sliding mode surface is constructed such that the synchronization error can converge to zero in finite time along the constructed integral sliding mode surface. Second, a suitable sliding mode controller is designed by relying on Lyapunov stability theory such that all system state trajectories can be driven onto the predefined sliding mode surface in finite time. Moreover, it is found that the presented control approach can be conveniently verified and does not need to solve any linear matrix inequality (LMI) to guarantee the finite-time synchronization of delayed recurrent neural networks. Finally, three numerical examples are exploited to demonstrate the effectiveness of the presented control approach.

New P-type RMPC Scheme for Redundant Robot Manipulators in Noisy Environment

Repetitive motion planning and control (RMPC) is a significant issue in the research of redundant robot manipulators. Moreover, noise from rounding error, truncation error, and robot uncertainty is an important factor that greatly affects RMPC schemes. In this study, the RMPC of redundant robot manipulators in a noisy environment is investigated. By incorporating the proportional and integral information of the desired path, a new RMPC scheme with pseudoinverse-type (P-type) formulation is proposed. Such a P-type RMPC scheme possesses the suppression of constant and bounded time-varying noises. Comparative simulation results based on a five-link robot manipulator and a PUMA560 robot manipulator are presented to further validate the effectiveness and superiority of the proposed P-type RMPC scheme over the previous one.

Adaptive Global Sliding-Mode Control for Dynamic Systems Using Double Hidden Layer Recurrent Neural Network Structure

In this paper, a full-regulated neural network (NN) with a double hidden layer recurrent neural network (DHLRNN) structure is designed, and an adaptive global sliding-mode controller based on the DHLRNN is proposed for a class of dynamic systems. Theoretical guidance and adaptive adjustment mechanism are established to set up the base width and central vector of the Gaussian function in the DHLRNN structure, where six sets of parameters can be adaptively stabilized to their best values according to different inputs. The new DHLRNN can improve the accuracy and generalization ability of the network, reduce the number of network weights, and accelerate the network training speed due to the strong fitting and presentation ability of two-layer activation functions compared with a general NN with a single hidden layer. Since the neurons of input layer can receive signals which come back from the neurons of output layer in the output feedback neural structure, it can possess associative memory and rapid system convergence, achieving better approximation and superior dynamic capability. Simulation and experiment on an active power filter are carried out to indicate the excellent static and dynamic performances of the proposed DHLRNN-based adaptive global sliding-mode controller, verifying its best approximation performance and the most stable internal state compared with other schemes.

Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications

Many practical problems can be solved by being formulated as time-varying quadratic programing (TVQP) problems. In this paper, a novel power-type varying-parameter recurrent neural network (VPNN) is proposed and analyzed to effectively solve the resulting TVQP problems, as well as the original practical problems. For a clear understanding, we introduce this model from three aspects: design, analysis, and applications. Specifically, the reason why and the method we use to design this neural network model for solving online TVQP problems subject to time-varying linear equality/inequality are described in detail. The theoretical analysis confirms that when activated by six commonly used activation functions, VPNN achieves a superexponential convergence rate. In contrast to the traditional zeroing neural network with fixed design parameters, the proposed VPNN has better convergence performance. Comparative simulations with state-of-the-art methods confirm the advantages of VPNN. Furthermore, the application of VPNN to a robot motion planning problem verifies the feasibility, applicability, and efficiency of the proposed method.

A new noise-tolerant and predefined-time ZNN model for time-dependent matrix inversion

In this work, a new zeroing neural network (ZNN) using a versatile activation function (VAF) is presented and introduced for solving time-dependent matrix inversion. Unlike existing ZNN models, the proposed ZNN model not only converges to zero within a predefined finite time but also tolerates several noises in solving the time-dependent matrix inversion, and thus called new noise-tolerant ZNN (NNTZNN) model. In addition, the convergence and robustness of this model are mathematically analyzed in detail. Two comparative numerical simulations with different dimensions are used to test the efficiency and superiority of the NNTZNN model to the previous ZNN models using other activation functions. In addition, two practical application examples (i.e., a mobile manipulator and a real Kinova JACO² robot manipulator) are presented to validate the applicability and physical feasibility of the NNTZNN model in a noisy environment. Both simulative and experimental results demonstrate the effectiveness and tolerant-noise ability of the NNTZNN model.

Rejecting Chaotic Disturbances Using a Super-Exponential-Zeroing Neurodynamic Approach for Synchronization of Chaotic Sensor Systems

Due to the existence of time-varying chaotic disturbances in complex applications, the chaotic synchronization of sensor systems becomes a tough issue in industry electronics fields. To accelerate the synchronization process of chaotic sensor systems, this paper proposes a super-exponential-zeroing neurodynamic (SEZN) approach and its associated controller. Unlike the conventional zeroing neurodynamic (CZN) approach with exponential convergence property, the controller designed by the proposed SEZN approach inherently possesses the advantage of super-exponential convergence property, which makes the synchronization process faster and more accurate. Theoretical analyses on the stability and convergence advantages in terms of both faster convergence speed and lower error bound within the task duration are rigorously presented. Moreover, three synchronization examples substantiate the validity of the SEZN approach and the related controller for synchronization of chaotic sensor systems. Comparisons with other approaches such as the CZN approach, show the convergence superiority of the proposed SEZN approach. Finally, extensive tests further investigate the impact on convergence performance by choosing different values of design parameter and initial state.

New Discrete-Time ZNN Models for Least-Squares Solution of Dynamic Linear Equation System With Time-Varying Rank-Deficient Coefficient

In this brief, a new one-step-ahead numerical differentiation rule called six-instant -cube finite difference (6I CFD) formula is proposed for the first-order derivative approximation with higher precision than existing finite difference formulas (i.e., Euler and Taylor types). Subsequently, by exploiting the proposed 6I CFD formula to discretize the continuous-time Zhang neural network model, two new-type discrete-time ZNN (DTZNN) models, namely, new-type DTZNNK and DTZNNU models, are designed and generalized to compute the least-squares solution of dynamic linear equation system with time-varying rank-deficient coefficient in real time, which is quite different from the existing ZNN-related studies on solving continuous-time and discrete-time (dynamic or static) linear equation systems in the context of full-rank coefficients. Specifically, the corresponding dynamic normal equation system, of which the solution exactly corresponds to the least-squares solution of dynamic linear equation system, is elegantly introduced to solve such a rank-deficient least-squares problem efficiently and accurately. Theoretical analyses show that the maximal steady-state residual errors of the two new-type DTZNN models have an pattern, where denotes the sampling gap. Comparative numerical experimental results further substantiate the superior computational performance of the new-type DTZNN models to solve the rank-deficient least-squares problem of dynamic linear equation systems.

A Neural Controller for Image-Based Visual Servoing of Manipulators With Physical Constraints

Main issues in visual servoing of manipulators mainly include rapid convergence of feature errors to zero and the safety of joints regarding joint physical limits. To address the two issues, in this paper, an image-based visual servoing scheme is proposed for manipulators with an eye-in-hand configuration. Compared with existing schemes, the proposed one does not require performing pseudoinversion for the image Jacobian matrix or inversion for the Jacobian matrix associated with the forward kinematics of the manipulators. Theoretical analysis shows that the proposed scheme not only guarantees the asymptotic convergence of feature errors to zero but also the compliance with joint angle and velocity limits of the manipulators. Besides, simulation results based on a PUMA560 manipulator with a camera mounted on the end effector verify the theoretical conclusions and the efficacy of the proposed scheme.

A New Noise-Tolerant Obstacle Avoidance Scheme for Motion Planning of Redundant Robot Manipulators

Avoiding obstacle(s) is a challenging issue in the research of redundant robot manipulators. In addition, noise from truncation, rounding, and model uncertainty is an important factor that affects greatly the obstacle avoidance scheme. In this paper, based on the neural dynamics design formula, a new scheme with the pseudoinverse-type formulation is proposed for obstacle avoidance of redundant robot manipulators in a noisy environment. Such a scheme has the capability of suppressing constant and bounded time-varying noises, and it is thus termed as the noise-tolerant obstacle avoidance (NTOA) scheme in this paper. Theoretical results are also given to show the excellent property of the proposed NTOA scheme (particularly in noise situation). Based on a PA10 robot manipulator with point and window-shaped obstacles, computer simulation results are presented to further substantiate the efficacy and superiority of the proposed NTOA scheme for motion planning of redundant robot manipulators.

Robust Fuzzy Adaptive Tracking Control for Nonaffine Stochastic Nonlinear Switching Systems

This paper is concerned with the trajectory tracking control problem of a class of nonaffine stochastic nonlinear switched systems with the nonlower triangular form under arbitrary switching. Fuzzy systems are employed to tackle the problem from packaged unknown nonlinearities, and the backstepping and robust adaptive control techniques are applied to design the controller by adopting the structural characteristics of fuzzy systems and the common Lyapunov function approach. By using Lyapunov stability theory, the semiglobally uniformly ultimate boundness in the fourth-moment of all closed-loop signals is guaranteed, and the system output is ensured to converge to a small neighborhood of the given trajectory. The main advantages of this paper lie in the fact that both the completely nonaffine form and nonlower triangular structure are taken into account for the controlled systems, and the increasing property of whole state functions is removed by using the structural characteristics of fuzzy systems. The developed control method is verified through a numerical example.