Consensus-based distributed cooperative learning from closed-loop neural control systems

Bayesian-Learning-Based Diffusion Least Mean Square Algorithms Over Networks

To improve the learning performance of the conventional diffusion least mean square (DLMS) algorithms, this article proposes Bayesian-learning-based DLMS (BL-DLMS) algorithms. First, the proposed BL-DLMS algorithms are inferred from a Gaussian state-space model-based Bayesian learning perspective. By performing Bayesian inference in the given Gaussian state-space model, a variable step-size and an estimation of the uncertainty of information of interest at each node are obtained for the proposed BL-DLMS algorithms. Next, a control method at each node is designed to improve the tracking performance of the proposed BL-DLMS algorithms in the sudden change scenario. Then, a lower bound on the variable step-size of each node of the proposed BL-DLMS algorithms is derived to maintain the optimal steady-state performance in the nonstationary scenario (unknown parameter vector of interest is time-varying). Afterward, the mean stability and the transient and steady-state mean square performance of the proposed BL-DLMS algorithms are analyzed in the nonstationary scenario. In addition, two Bayesian-learning-based diffusion bias-compensated LMS algorithms are proposed to handle the noisy inputs. Finally, the superior learning performance of the proposed learning algorithms is verified by numerical simulations, and the simulated results are in good agreement with the theoretical results.

New Results on Rapid Dynamical Pattern Recognition via Deterministic Learning From Sampling Sequences

Rapid dynamical pattern recognition based on the deterministic learning method (DLM-based RDPR) aims to rapidly recognize the most similar dynamical pattern pair from perspectives of differences in inherent system dynamics. The basic mechanism is to use available recognition errors to reflect the differences in the dynamics of dynamical pattern pairs and then to make a decision based on a minimal recognition error (MRE) principle. This article focuses on providing a rigorous theoretical analysis of the MRE principle in DLM-based RDPR under the sampled-data framework. Specifically, we seek a unified methodology from the similarity definition to the measure implementation and then to derive general sufficient conditions and necessary conditions for the MRE principle. The main idea is to: 1) from the average signal energy aspect, define a time-dependent dynamics-based similarity in dynamical pattern pairs and reestablish the measure of recognition errors generated from the DLM-based RDPR; 2) introduce the energy-based Lyapunov method to establish the interrelation between the dynamical distance and the recognition error; and 3) derive sufficient conditions and necessary conditions from two directions of the interrelation. The proposed conditions distinguish themselves from virtually all of the existing DLM-based RDPR works with only sufficient conditions in the sense that it is shown in a rigorous analysis that under what conditions, the pattern pair recognized based on the MRE principle is indeed the most similar one. Therefore, the proposed work makes the DLM-based RDPR possess good interpretability and provides strong theoretical guidance in engineering applications.

Deterministic learning-based neural identification and knowledge fusion

Recent deterministic learning methods have achieved locally-accurate identification of unknown system dynamics. However, the locally-accurate identification means that the neural networks can only capture the local dynamics knowledge along the system trajectory. In order to capture a broader knowledge region, this article investigates the knowledge fusion problem of deterministic learning, that is, the integration of different knowledge regions along different individual trajectories. Specifically, two kinds of knowledge fusion schemes are systematically introduced: an online fusion scheme and an offline fusion scheme. The online scheme can be viewed as an extension of distributed cooperative learning control to cooperative neural identification for sampled-data systems. By designing an auxiliary information transmission strategy to enable the neural network to receive information learned from other tasks while learning its own task, it is proven that the weights of all localized RBF networks exponentially converge to their common true/ideal values. The offline scheme can be regarded as a knowledge distillation strategy, in which the fused network is obtained by offline training through the knowledge learned from all individual system trajectories via deterministic learning. A novel weight fusion algorithm with low computational complexity is proposed based on the least squares solution under subspace constraints. Simulation studies show that the proposed fusion schemes can successfully integrate the knowledge regions of different individual trajectories while maintaining the learning performance, thereby greatly expanding the knowledge region learned from deterministic learning.

Convex Temporal Convolutional Network-Based Distributed Cooperative Learning Control for Multiagent Systems

Due to its great efficiency, scalability, and inclusivity, distributed cooperative learning control has gotten a lot of attention. For complex uncertain multiagent systems, it is challenging to model the uncertainties and exploit the cooperative learning ability of the systems. To address these issues, we proposed a novel convex temporal convolutional network-based distributed cooperative learning control for uncertain discrete-time nonlinear multiagent systems. A new concept of using a convex temporal convolutional network (CTCNet) is proposed for estimating the uncertain agent dynamics in a cooperative way. Unlike previous methods that require adjustment of network weights for different control tasks, the proposed CTCNet can map the high-dimensional input-output space into a deep space spanned by basis features that represent the inherent properties of the system, so it has good robustness for different tasks. Consequently, to improve the control performance, a CTCNet-based distributed cooperative learning control method that shares learned knowledge through the communication topology among adaptive laws of CTCNet is proposed. Furthermore, the asymptotic convergence of system tracking errors to an arbitrarily small neighborhood of the origin is strictly proved. Finally, the simulation results are given to illustrate that our suggested method has higher control accuracy, stronger robustness, and anti-interference ability than the existing methods.

Adaptive Control of Uncertain Nonlinear Systems via Event-Triggered Communication and NN Learning

This article concentrates on adaptive tracking control of strict-feedback uncertain nonlinear systems with an event-based learning scheme. A novel neural network (NN) learning law is proposed to design the adaptive control scheme. The NN weights information driven by the prediction-error-based control process is intermittently transmitted in the event-triggered context to the NN learning law mainly for signal tracking. The online stored sampled data of NN driven by the tracking error are utilized in the event context to update the learning law. With the adaptive control and NN learning law updated via the event-triggered communication, the improvements of NN learning capability, tracking performance, and system computing resource saving are guaranteed. In addition, it is proved that the minimum time interval for triggering errors of the two types of events is bounded and the Zeno behavior is strictly excluded. Finally, simulation results illustrate the effectiveness and good performance of the proposed control method.

Distributed Nesterov Gradient and Heavy-Ball Double Accelerated Asynchronous Optimization

In this article, we come up with a novel Nesterov gradient and heavy-ball double accelerated distributed synchronous optimization algorithm, called NHDA, and adopt a general asynchronous model to further propose an effective asynchronous algorithm, called ASY-NHDA, for distributed optimization problem over directed graphs, where each agent has access to a local objective function and computes the optimal solution via communicating only with its immediate neighbors. Our goal is to minimize a sum of all local objective functions satisfying strong convexity and Lipschitz continuity. Consider a general asynchronous model, where agents communicate with their immediate neighbors and start a new computation independently, that is, agents can communicate with their neighbors at any time without any coordination and use delayed information from their in-neighbors to compute a new update. Delays are arbitrary, unpredictable, and time-varying but bounded. The theoretical analysis of NHDA is based on analyzing the interaction among the consensus, the gradient tracking, and the optimization processes. As for the analysis of ASY-NHDA, we equivalently transform the asynchronous system into an augmented synchronous system without delays and prove its convergence through using the generalized small gain theorem. The results show that NHDA and ASY-NHDA converge to the optimal solution at a linear convergence as long as the largest step size is positive and less than an explicitly estimated upper bound, and the largest momentum parameter is nonnegative and less than an upper bound. Finally, we demonstrate the advantages of ASY-NHDA through simulations.

Distributed Cooperative Learning Control of Uncertain Multiagent Systems With Prescribed Performance and Preserved Connectivity

For an uncertain multiagent system, distributed cooperative learning control exerting the learning capability of the control system in a cooperative way is one of the most important and challenging issues. This article aims to address this issue for an uncertain high-order nonlinear multiagent system with guaranteed transient performance and preserved initial connectivity under an undirected and static communication topology. The considered multiagent system has an identical structure and the uncertain agent dynamics are estimated by localized radial basis function (RBF) neural networks (NNs) in a cooperative way. The NN weight estimates are rigorously proven to converge to small neighborhoods of their common optimal values along the union of all agents' trajectories by a deterministic learning theory. Consequently, the associated uncertain dynamics can be locally accurately identified and can be stored and represented by constant RBF networks. Using the stored knowledge on identified system dynamics, an experience-based distributed controller is proposed to improve the control performance and reduce the computational burden. The theoretical results are demonstrated on an application to the formation control of a group of unmanned surface vehicles.

Debiasing and Distributed Estimation for High-Dimensional Quantile Regression

Distributed and parallel computing is becoming more important with the availability of extremely large data sets. In this article, we consider this problem for high-dimensional linear quantile regression. We work under the assumption that the coefficients in the regression model are sparse; therefore, a LASSO penalty is naturally used for estimation. We first extend the debiasing procedure, which is previously proposed for smooth parametric regression models to quantile regression. The technical challenges include dealing with the nondifferentiability of the loss function and the estimation of the unknown conditional density. In this article, the main objective is to derive a divide-and-conquer estimation approach using the debiased estimator which is useful under the big data setting. The effectiveness of distributed estimation is demonstrated using some numerical examples.

Cooperative Fault Diagnosis for Uncertain Nonlinear Multiagent Systems Based on Adaptive Distributed Fuzzy Estimators

This paper presents a cooperative fault diagnosis scheme for a class of uncertain nonlinear multiagent systems component and sensor faults in individual agents. Since the faulty system affects the healthy systems through interconnections, for each agent an estimator is designed to collect neighboring output estimations errors to consider its faulty effects on others, when computing its estimations for local state and faulty parameters. A new structure of distributed estimators is proposed by filtering regressor signals and sharing them among agents. Then, the sharings of signals are planned by properly constructing auxiliary graphs for undirected and directed networks. Two conditions are given to preselect estimators parameters for the convergences of the estimation errors. Unlike the existing results dealing with one common parameter with full state measurement and only for undirected graphs, this paper presents an output measurement-based approach for multiple parameters in undirected/directed networks. It shows that for the faults not providing persistent excitation in a signal agent, it is possible to estimate the faults exactly if the they excite all agents persistently. A simulation example of a group of single-link flexible-joint robots is given to verify the effectiveness of the proposed method.

Neural Network-Based Distributed Cooperative Learning Control for Multiagent Systems via Event-Triggered Communication

In this paper, an event-based distributed cooperative learning (DCL) law is proposed for a group of adaptive neural control systems. The plants to be controlled have identical structures, but reference signals for each plant are different. During control process, each agent intermittently broadcasts its neural network (NN) weight estimation to its neighboring agents under an event-triggered condition that is only based on its own estimated NN weights. If communication topology is connected and undirected, the NN weights of all neural control systems can converge to a small neighborhood of their optimal values. The generalization ability of NNs is guaranteed in the event-triggered context, that is, the approximation domain of each NN is the union of all system trajectories. Furthermore, a strictly positive lower bound on the interevent intervals is also guaranteed to avoid the Zeno behavior. Finally, a numerical example is given to illustrate the effectiveness of the proposed learning law.

Neural Network Controller Design for a Class of Nonlinear Delayed Systems With Time-Varying Full-State Constraints

This paper proposes an adaptive neural control method for a class of nonlinear time-varying delayed systems with time-varying full-state constraints. To address the problems of the time-varying full-state constraints and time-varying delays in a unified framework, an adaptive neural control method is investigated for the first time. The problems of time delay and constraint are the main factors of limiting the system performance severely and even cause system instability. The effect of unknown time-varying delays is eliminated by using appropriate Lyapunov-Krasovskii functionals. In addition, the constant constraint is the only special case of time-varying constraint which leads to more complex and difficult tasks. To guarantee the full state always within the time-varying constrained interval, the time-varying asymmetric barrier Lyapunov function is employed. Finally, two simulation examples are given to confirm the effectiveness of the presented control scheme.

Finite-Time Distributed Average Tracking for Second-Order Nonlinear Systems

This paper studies the distributed average tracking (DAT) problem for multiple reference signals described by the second-order nonlinear dynamical systems. Leveraging the state-dependent gain design and the adaptive control approaches, a couple of DAT algorithms are developed in this paper, which are named finite-time and adaptive-gain DAT algorithms. Based on the finite-time one, the states of the physical agents in this paper can track the average of the time-varying reference signals within a finite settling time. Furthermore, the finite settling time is also estimated by considering a well-designed Lyapunov function in this paper. Compared with asymptotical DAT algorithms, the proposed finite-time algorithm not only solve finite-time DAT problems but also ensure states of physical agents to achieve an accurate average of the multiple signals. Then, an adaptive-gain DAT algorithm is designed. Based on the adaptive-gain one, the DAT problem is solved without global information. Thus, it is fully distributed. Finally, numerical simulations show the effectiveness of the theoretical results.

Pose Consensus of Multiple Robots with Time-Delays Using Neural Networks

This paper proposes a novel control scheme based on Radial Basis Artificial Neural Network to solve the leader–follower and leaderless pose (position and orientation) consensus problems in the Special Euclidean space of dimension three (SE(3)). The controller is designed for robot networks composed of heterogeneous (kinematically and dynamically different) and uncertain robots with variable time-delays in the interconnection. The paper derives a sufficient condition on the controller gains and the robot interconnection, and using Barbalat’s Lemma, both consensus problems are solved. The proposed approach employs the singularity-free, unit-quaternions to represent the orientation of the end-effectors in theSE(3). The significance and advantages of the proposed control scheme are that it solves the two pose consensus problems for heterogeneous robot networks considering variable time-delays in the interconnection without orientation representation singularities, and the controller does not require to know the dynamic model of the robots. The performance of the proposed controller is illustrated via simulations with a heterogeneous robot network composed of robots with 6-DoF and 7-DoF.

Adaptive Asymptotic Neural Network Control of Nonlinear Systems With Unknown Actuator Quantization

In this paper, we propose an adaptive neural-network-based asymptotic control algorithm for a class of nonlinear systems subject to unknown actuator quantization. To this end, we exploit the sector property of the quantization nonlinearity and transform actuator quantization control problem into analyzing its upper bounds, which are then handled by a dynamic loop gain function-based approach. In our adaptive control scheme, there is only one parameter required to be estimated online for updating weights of neural networks. Within the framework of Lyapunov theory, it is shown that the proposed algorithm ensures that all the signals in the closed-loop system are ultimately bounded. Moreover, an asymptotic tracking error is obtained by means of introducing Barbalat's lemma to the proposed adaptive law.

Adaptive Control via Neural Output Feedback for a Class of Nonlinear Discrete-Time Systems in a Nested Interconnected Form

In this paper, an adaptive output feedback control is framed for uncertain nonlinear discrete-time systems. The considered systems are a class of multi-input multioutput nonaffine nonlinear systems, and they are in the nested lower triangular form. Furthermore, the unknown dead-zone inputs are nonlinearly embedded into the systems. These properties of the systems will make it very difficult and challenging to construct a stable controller. By introducing a new diffeomorphism coordinate transformation, the controlled system is first transformed into a state-output model. By introducing a group of new variables, an input-output model is finally obtained. Based on the transformed model, the implicit function theorem is used to determine the existence of the ideal controllers and the approximators are employed to approximate the ideal controllers. By using the mean value theorem, the nonaffine functions of systems can become an affine structure but nonaffine terms still exist. The adaptation auxiliary terms are skillfully designed to cancel the effect of the dead-zone input. Based on the Lyapunov difference theorem, the boundedness of all the signals in the closed-loop system can be ensured and the tracking errors are kept in a bounded compact set. The effectiveness of the proposed technique is checked by a simulation study.

Adaptive NN Control Using Integral Barrier Lyapunov Functionals for Uncertain Nonlinear Block-Triangular Constraint Systems

A neural network (NN) adaptive control design problem is addressed for a class of uncertain multi-input-multi-output (MIMO) nonlinear systems in block-triangular form. The considered systems contain uncertainty dynamics and their states are enforced to subject to bounded constraints as well as the couplings among various inputs and outputs are inserted in each subsystem. To stabilize this class of systems, a novel adaptive control strategy is constructively framed by using the backstepping design technique and NNs. The novel integral barrier Lyapunov functionals (BLFs) are employed to overcome the violation of the full state constraints. The proposed strategy can not only guarantee the boundedness of the closed-loop system and the outputs are driven to follow the reference signals, but also can ensure all the states to remain in the predefined compact sets. Moreover, the transformed constraints on the errors are used in the previous BLF, and accordingly it is required to determine clearly the bounds of the virtual controllers. Thus, it can relax the conservative limitations in the traditional BLF-based controls for the full state constraints. This conservatism can be solved in this paper and it is for the first time to control this class of MIMO systems with the full state constraints. The performance of the proposed control strategy can be verified through a simulation example.

Approximation-Based Adaptive Neural Tracking Control of Nonlinear MIMO Unknown Time-Varying Delay Systems With Full State Constraints

This paper deals with the tracking control problem for a class of nonlinear multiple input multiple output unknown time-varying delay systems with full state constraints. To overcome the challenges which cause by the appearances of the unknown time-varying delays and full-state constraints simultaneously in the systems, an adaptive control method is presented for such systems for the first time. The appropriate Lyapunov-Krasovskii functions and a separation technique are employed to eliminate the effect of unknown time-varying delays. The barrier Lyapunov functions are employed to prevent the violation of the full state constraints. The singular problems are dealt with by introducing the signal function. Finally, it is proven that the proposed method can both guarantee the good tracking performance of the systems output, all states are remained in the constrained interval and all the closed-loop signals are bounded in the design process based on choosing appropriate design parameters. The practicability of the proposed control technique is demonstrated by a simulation study in this paper.

Neural Network Control-Based Adaptive Learning Design for Nonlinear Systems With Full-State Constraints

In order to stabilize a class of uncertain nonlinear strict-feedback systems with full-state constraints, an adaptive neural network control method is investigated in this paper. The state constraints are frequently emerged in the real-life plants and how to avoid the violation of state constraints is an important task. By introducing a barrier Lyapunov function (BLF) to every step in a backstepping procedure, a novel adaptive backstepping design is well developed to ensure that the full-state constraints are not violated. At the same time, one remarkable feature is that the minimal learning parameters are employed in BLF backstepping design. By making use of Lyapunov analysis, we can prove that all the signals in the closed-loop system are semiglobal uniformly ultimately bounded and the output is well driven to follow the desired output. Finally, a simulation is given to verify the effectiveness of the method.

Finite-Time Consensus of Multiagent Systems With a Switching Protocol

In this paper, we study the problem of finite-time consensus of multiagent systems on a fixed directed interaction graph with a new protocol. Existing finite-time consensus protocols can be divided into two types: 1) continuous and 2) discontinuous, which were studied separately in the past. In this paper, we deal with both continuous and discontinuous protocols simultaneously, and design a centralized switching consensus protocol such that the finite-time consensus can be realized in a fast speed. The switching protocol depends on the range of the initial disagreement of the agents, for which we derive an exact bound to indicate at what time a continuous or a discontinuous protocol should be selected to use. Finally, we provide two numerical examples to illustrate the superiority of the proposed protocol and design method.

A Unified Approach to Adaptive Neural Control for Nonlinear Discrete-Time Systems With Nonlinear Dead-Zone Input

In this paper, an effective adaptive control approach is constructed to stabilize a class of nonlinear discrete-time systems, which contain unknown functions, unknown dead-zone input, and unknown control direction. Different from linear dead zone, the dead zone, in this paper, is a kind of nonlinear dead zone. To overcome the noncausal problem, which leads to the control scheme infeasible, the systems can be transformed into a m -step-ahead predictor. Due to nonlinear dead-zone appearance, the transformed predictor still contains the nonaffine function. In addition, it is assumed that the gain function of dead-zone input and the control direction are unknown. These conditions bring about the difficulties and the complicacy in the controller design. Thus, the implicit function theorem is applied to deal with nonaffine dead-zone appearance, the problem caused by the unknown control direction can be resolved through applying the discrete Nussbaum gain, and the neural networks are used to approximate the unknown function. Based on the Lyapunov theory, all the signals of the resulting closed-loop system are proved to be semiglobal uniformly ultimately bounded. Moreover, the tracking error is proved to be regulated to a small neighborhood around zero. The feasibility of the proposed approach is demonstrated by a simulation example.

Adaptive NN controller design for a class of nonlinear MIMO discrete-time systems

An adaptive neural network tracking control is studied for a class of multiple-input multiple-output (MIMO) nonlinear systems. The studied systems are in discrete-time form and the discretized dead-zone inputs are considered. In addition, the studied MIMO systems are composed of N subsystems, and each subsystem contains unknown functions and external disturbance. Due to the complicated framework of the discrete-time systems, the existence of the dead zone and the noncausal problem in discrete-time, it brings about difficulties for controlling such a class of systems. To overcome the noncausal problem, by defining the coordinate transformations, the studied systems are transformed into a special form, which is suitable for the backstepping design. The radial basis functions NNs are utilized to approximate the unknown functions of the systems. The adaptation laws and the controllers are designed based on the transformed systems. By using the Lyapunov method, it is proved that the closed-loop system is stable in the sense that the semiglobally uniformly ultimately bounded of all the signals and the tracking errors converge to a bounded compact set. The simulation examples and the comparisons with previous approaches are provided to illustrate the effectiveness of the proposed control algorithm.

Adaptive NN tracking control of uncertain nonlinear discrete-time systems with nonaffine dead-zone input

In the paper, an adaptive tracking control design is studied for a class of nonlinear discrete-time systems with dead-zone input. The considered systems are of the nonaffine pure-feedback form and the dead-zone input appears nonlinearly in the systems. The contributions of the paper are that: 1) it is for the first time to investigate the control problem for this class of discrete-time systems with dead-zone; 2) there are major difficulties for stabilizing such systems and in order to overcome the difficulties, the systems are transformed into an n-step-ahead predictor but nonaffine function is still existent; and 3) an adaptive compensative term is constructed to compensate for the parameters of the dead-zone. The neural networks are used to approximate the unknown functions in the transformed systems. Based on the Lyapunov theory, it is proven that all the signals in the closed-loop system are semi-globally uniformly ultimately bounded and the tracking error converges to a small neighborhood of zero. Two simulation examples are provided to verify the effectiveness of the control approach in the paper.