Composite learning from adaptive backstepping neural network control

Neuro-Adaptive-Based Fixed-Time Composite Learning Control for Manipulators With Given Transient Performance

This article investigates an adaptive neural network (NN) control technique with fixed-time tracking capabilities, employing composite learning, for manipulators under constrained position error. The first step involves integrating the composite learning method into the NN to address the dynamic uncertainties that inevitably arise in manipulators. A composite adaptive updating law of NN weights is formulated, requiring adherence solely to the relaxed interval excitation (IE) conditions. In addition, for the output error, instead of knowing the initial conditions, this article integrates the error transfer function and asymmetric barrier function to achieve the specific performance for position error in both steady and transient states. Furthermore, the fixed-time control methodology and Lyapunov stability criterion are synergistically employed in order to guarantee the convergence of all signals in the manipulators to a compact neighborhood around the origin within a fixed-time. Finally, numerical simulation and experiments with the Baxter robot results both determine the capability of the NN composite learning technique and fixed-time control strategy.

UAV Trajectory Tracking Using Proportional-Integral-Derivative-Type-2 Fuzzy Logic Controller with Genetic Algorithm Parameter Tuning

Unmanned Aerial Vehicle (UAV)-type Quadrotors are highly nonlinear systems that are difficult to control and stabilize outdoors, especially in a windy environment. Many algorithms have been proposed to solve the problem of trajectory tracking using UAVs. However, current control systems face significant hurdles, such as parameter uncertainties, modeling errors, and challenges in windy environments. Sensitivity to parameter variations may lead to performance degradation or instability. Modeling errors arise from simplifications, causing disparities between assumed and actual behavior. Classical controls may lack adaptability to dynamic changes, necessitating adaptive strategies. Limited robustness in handling uncertainties can result in suboptimal performance. Windy environments introduce disturbances, impacting system dynamics and precision. The complexity of wind modeling demands advanced estimation and compensation strategies. Tuning challenges may necessitate frequent adjustments, posing practical limitations. Researchers have explored advanced control paradigms, including robust, adaptive, and predictive control, aiming to enhance system performance amidst uncertainties in a scientifically rigorous manner. Our approach does not require knowledge of UAVs and noise models. Furthermore, the use of the Type-2 controller makes our approach robust in the face of uncertainties. The effectiveness of the proposed approach is clear from the obtained results. In this paper, robust and optimal controllers are proposed, validated, and compared on a quadrotor navigating an outdoor environment. First, a Type-2 Fuzzy Logic Controller (FLC) combined with a PID is compared to a Type-1 FLC and Backstepping controller. Second, a Genetic Algorithm (GA) is proposed to provide the optimal PID-Type-2 FLC tuning. The Backstepping, PID-Type-1 FLC, and PID-Type-2 FLC with GA optimization are validated and evaluated with real scenarios in a windy environment. Deep robustness analysis, including error modeling, parameter uncertainties, and actuator faults, is considered. The obtained results clearly show the robustness of the optimal PID-Type-2 FLC compared to the Backstepping and PID-Type-1 FLC controllers. These results are confirmed by the numerical index of each controller compared to the PID-type-2 FLC, with 12% for the Backstepping controller and 51% for the PID-Type-1 FLC.

Composite Learning Adaptive Tracking Control for Full-State Constrained Multiagent Systems Without Using the Feasibility Condition

This article proposes a distributed consensus tracking controller for a class of nonlinear multiagent systems under a directed graph, in which all agents are subject to time-varying asymmetric full-state constraints, internal uncertainties, and external disturbances. The feasibility condition generally required in the existing constrained control is removed by using the proposed nonlinear mapping function (NMF)-based state reconstruction technology, and the Lipschitz condition usually needed in the consensus tracking is also canceled based on the adaptive command-filtered backstepping framework. The composite learning of the neural network-based function approximator (NN-FAP) and the finite-time smooth disturbance observer (DOB) provides a novel scheme for handling internal and external uncertainties simultaneously. One advantage of this scheme is that the use of online historical data of the closed-loop system strengthens the excitation of NN's learning. Another advantage is that the DOB with NN-FAP embedding realizes that the finite-time observation for external disturbance in the case of the system dynamics is unknown. A complete controller design, sufficient stability analysis, and numerical simulation are provided.

Adaptive NN Finite-Time Resilient Control for Nonlinear Time-Delay Systems With Unknown False Data Injection and Actuator Faults

This article considers neural network (NN)-based adaptive finite-time resilient control problem for a class of nonlinear time-delay systems with unknown fault data injection attacks and actuator faults. In the procedure of recursive design, a coordinate transformation and a modified fractional-order command-filtered (FOCF) backstepping technique are incorporated to handle the unknown false data injection attacks and overcome the issue of "explosion of complexity" caused by repeatedly taking derivatives for virtual control laws. The theoretical analysis proves that the developed resilient controller can guarantee the finite-time stability of the closed-loop system (CLS) and the stabilization errors converge to an adjustable neighborhood of zero. The foremost contributions of this work include: 1) by means of a modified FOCF technique, the adaptive resilient control problem of more general nonlinear time-delay systems with unknown cyberattacks and actuator faults is first considered; 2) different from most of the existing results, the commonly used assumptions on the sign of attack weight and prior knowledge of actuator faults are fully removed in this article. Finally, two simulation examples are given to demonstrate the effectiveness of the developed control scheme.

Composite learning sliding mode control of uncertain nonlinear systems with prescribed performance

This paper explores the prescribed performance tracking control problem of nonlinear systems with triangular structure. To obtain the desired transient performance and precise estimations of uncertain terms, the techniques of neural network control, sliding mode control and composite learning control are incorporated into the proposed control method. The presented control strategy can ensure the tracking error converges to a prescribed small residual set. Compared with the persistent excitation condition required in the conventional adaptive control, the interval excitation condition needed in the proposed control approach is weak, which guarantees that the radial basis function neural networks approximate the unknown nonlinear terms more accurately. Finally, two simulation examples are exploited to manifest the effectiveness of the proposed approach.

Composite-Learning-Based Adaptive Neural Control for Dual-Arm Robots With Relative Motion

This article presents an adaptive control method for dual-arm robot systems to perform bimanual tasks under modeling uncertainties. Different from the traditional symmetric bimanual robot control, we study the dual-arm robot control with relative motions between robotic arms and a grasped object. The robot system is first divided into two subsystems: a settled manipulator system and a tool-used manipulator system. Then, a command filtered control technique is developed for trajectory tracking and contact force control. In addition, to deal with the inevitable dynamic uncertainties, a radial basis function neural network (RBFNN) is employed for the robot, with a novel composite learning law to update the NN weights. The composite learning is mainly based on an integration of the historic data of NN regression such that information of the estimate error can be utilized to improve the convergence. Moreover, a partial persistent excitation condition is employed to ensure estimation convergence. The stability analysis is performed by using the Lyapunov theorem. Numerical simulation results demonstrate the validity of the proposed control and learning algorithm.

Composite learning sliding mode synchronization of chaotic fractional-order neural networks

•

A sliding surface extending from integer-order to fractional-order is introduced.

•

The stability of FONNs is analyzed by means of the Lyapunov function.

•

A composite learning law is designed for FONNs under the IE condition.

In this work, a sliding mode control (SMC) method and a composite learning SMC (CLSMC) method are proposed to solve the synchronization problem of chaotic fractional-order neural networks (FONNs). A sliding mode surface and an adaptive law are constructed to update parameter estimation. The SMC ensures that the synchronization error asymptotically tends to zero under a strict permanent excitation (PE) condition. To reduce its rigor, online recording data together with instantaneous data is used to define a prediction error about the uncertain parameter. Both synchronization error and prediction error are used to construct a composite learning law. The proposed CLSMC method can ensure that the synchronization error asymptotically approaches zero, and it can accurately estimate the uncertain parameter. The above results obtained in the CLSMC method only requires an interval-excitation (IE) condition which can be easily satisfied. Finally, comparative results reveal the control effects of the two proposed methods.

Composite Learning Adaptive Dynamic Surface Control of Fractional-Order Nonlinear Systems

Adaptive dynamic surface control (ADSC) is effective for solving the complexity problem in adaptive backstepping control of integer-order nonlinear systems. This article focuses on the ADSC design for parametric uncertain fractional-order nonlinear systems (FONSs). In each backstepping step, the virtual controller is driven to pass through a fractional dynamic surface whose fractional-order derivative can be calculated easily. An ADSC law that ensure tracking error convergence is designed. The proposed ADSC requires a stringent condition called persistent excitation (PE) to achieve parameter convergence. To relax this limitation, a prediction error is defined by using online recorded data and instantaneous data, and a composite learning law is proposed to utilize both the prediction error and the tracking error. Then, a composite learning ADSC (CLADSC) method is developed to guarantee tracking error convergence and accurate parameter estimation under an interval excitation condition that is weaker than the PE one. Finally, an illustrative example is presented to show the performance of our methods.

Adaptive trajectory tracking control for remotely operated vehicles considering thruster dynamics and saturation constraints

This paper discusses the problem of adaptive trajectory tracking control for remotely operated vehicles (ROVs). Considering thruster dynamics, a third-order state space equation is used to describe the dynamic model of ROVs. For the problem of unknown dynamics and partially known input gain, an adaptive sliding mode control design scheme based on RBF neural networks is developed using a backstepping design technique. Because of the saturation constraints of the thrusters, a first-order auxiliary state system is applied, and subsequently, a saturation factor is constructed for designing adaptive laws to ensure the stability of the adaptive trajectory tracking system when the thrusters are saturated. The proposed controller guaranteed that trajectory tracking errors are uniformly ultimately bounded (UUD). Finally, the effectiveness of the proposed controller is verified by simulations.

Time-delay estimation based computed torque control with robust adaptive RBF neural network compensator for a rehabilitation exoskeleton

A new approach to gait rehabilitation task of a 12 DOF lower limb exoskeleton is proposed combining time-delay estimation (TDE) based computed torque control (CTC) and robust adaptive RBF neural networks. In addition to the conventional advantages of the CTC, TDE technique is integrated to estimate unmodeled dynamics and external disturbance. To realize more accurate tracking, a robust adaptive RBF neural networks compensator is designed to approximate and compensate TDE error. The final asymptotic stability is guaranteed with Lyapunov criteria. To validate the proposed approach, co-simulation experiments are realized using SolidWorks, SimMechanics and MATLAB/Robotics Toolbox. Compared to CTC, sliding mode based CTC and TDE based CTC, the higher performances of the proposed controller are demonstrated by co-simulation.

Adaptive neural network terminal sliding mode control for uncertain spatial robot

The tracking control problem for uncertain spatial robot is investigated by means of adaptive terminal sliding mode control in this article. To approximate unknown nonlinear functions of these systems, a neural network model is employed. By using Lyapunov stability theory, adaptive terminal sliding mode controller is given, which guarantees that the tracking error converges to an arbitrary small region of zero and all the signals remain bounded. Finally, numerical simulation is given to confirm the effectiveness of the proposed method.

Identification and Control of Nonlinear Systems Using Neural Networks: A Singularity-Free Approach

In this paper, identification and control for a class of nonlinear systems with unknown constant or variable control gains are investigated. By reformulating the original system dynamic equation into a new form with a unit control gain and introducing a set of filtered variables, a novel neural network (NN) estimator is constructed and a new estimation error is used to update the augmented weights. Based on the identification results, two singularity-free NN indirect adaptive controllers are developed for nonlinear systems with unknown constant control gains or variable control gains, respectively. Because the singularity problem is eradicated, the proposed methods remove limitations on parameter estimates that are used to guarantee the positiveness of the estimated control gain. Consequently, a more accurate estimation result can be achieved and the system state can track the given reference signal more precisely. The effectiveness of the proposed identification and control algorithms are tested and the superiority of the proposed singularity-free approach is demonstrated by simulation results.

Deep Recurrent Neural Networks Based Obstacle Avoidance Control for Redundant Manipulators

Obstacle avoidance is an important subject in the control of robot manipulators, but is remains challenging for robots with redundant degrees of freedom, especially when there exist complex physical constraints. In this paper, we propose a novel controller based on deep recurrent neural networks. By abstracting robots and obstacles into critical point sets respectively, the distance between the robot and obstacles can be described in a simpler way, then the obstacle avoidance strategy is established in form of inequality constraints by general class-K functions. Using minimal-velocity-norm (MVN) scheme, the control problem is formulated as a quadratic-programming case under multiple constraints. Then a deep recurrent neural network considering system models is established to solve the QP problem online. Theoretical conduction and numerical simulations show that the controller is capable of avoiding static or dynamic obstacles, while tracking the predefined trajectories under physical constraints.

Decentralized adaptive neural prescribed performance control for high-order stochastic switched nonlinear interconnected systems with unknown system dynamics

In this paper, the problem of decentralized adaptive neural backstepping control is investigated for high-order stochastic nonlinear systems with unknown interconnected nonlinearity and prescribed performance under arbitrary switchings. For the control of high-order nonlinear interconnected systems, it is assumed that unknown system dynamics and arbitrary switching signals are unknown. First, by utilizing the prescribed performance control (PPC), the prescribed tracking control performance can be ensured, while the requirement for the initial error is removed. Second, at each recursive step, only one adaptive parameter is constructed to overcome the over-parameterization, and RBF neural networks are employed to tackle the difficulties caused by completely unknown system dynamics. At last, based on the common Lyapunov stability method, the decentralized adaptive neural control method is proposed, which decreases the number of learning parameters. It is shown that the designed common controller can ensure that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded (SGUUB), and the prescribed tracking control performance is guaranteed under arbitrary switchings. The simulation results are presented to further illustrate the effectiveness of the proposed control scheme.