Because of the complexity consensus control nonlinear multiagent systems in state time-delay, most previous works focused only on linear with input time-delay. An adaptive neural network (NN) method for a class time-delay is proposed this paper. The approximation property radial basis function networks (RBFNNs) used to neutralize uncertain dynamics agents. appropriate Lyapunov-Krasovskii functional, which obtained from derivative an Lyapunov function, compensate uncertainties unknown time...

Combined with backstepping techniques, an observer-based adaptive consensus tracking control strategy is developed for a class of high-order nonlinear multiagent systems, which each follower agent modeled in semi-strict-feedback form. By constructing the neural network-based state observer follower, proposed method solves unmeasurable problem systems. The algorithm can guarantee that all signals system are semi-globally uniformly ultimately bounded and outputs synchronously track reference...

This paper studies an adaptive tracking control for a class of nonlinear stochastic systems with unknown functions. The considered are in the nonaffine pure-feedback form, and it is first to this disturbances. fuzzy-neural networks used approximate Based on backstepping design technique, controllers adaptation laws obtained. Compared most existing systems, proposed algorithm has fewer adjustable parameters thus, can reduce online computation load. By using Lyapunov analysis, proven that all...

This brief studies an adaptive neural output feedback tracking control of uncertain nonlinear multi-input-multi-output (MIMO) systems in the discrete-time form. The considered MIMO are composed n subsystems with couplings inputs and states among subsystems. In order to solve noncausal problem decouple couplings, it needs transform into a predictor higher networks utilized approximate desired controllers. By using Lyapunov analysis, is proven that all signals closed-loop system semi-globally...

Compared with the existing neural network (NN) or fuzzy logic system (FLS) based adaptive consensus methods, proposed approach can greatly alleviate computation burden because it needs only to update a few parameters online. In multiagent agreement control, uncertainties derive from unknown nonlinear dynamics are counteracted by employing NNs; state delays compensated designing Lyapunov-Krasovskii functional. Finally, on Lyapunov stability theory, is demonstrated that scheme steer...

In this study, a novel adaptive neural network (NN)‐based leader‐following consensus approach is proposed for class of non‐linear second‐order multi‐agent systems. For the existing NN approaches, to obtain desired approximation accuracy, NN‐based algorithms require number nodes must be large enough, and thus online computation burden often are very heavy. However, scheme can greatly reduce burden, because adjusting parameters designed in scalar form, which norm estimation optimal weight...

In this article, a control scheme based on optimized backstepping (OB) technique is developed for class of nonlinear strict-feedback systems with unknown dynamic functions. Reinforcement learning (RL) employed achieving the control, and it designed basis neural-network (NN) approximations under identifier-critic-actor architecture, where identifier, critic, actor are utilized estimating dynamic, evaluating system performance, implementing action, respectively. OB to design all virtual...

In this paper, a control technique named optimized backstepping is first proposed by implementing tracking for class of strict-feedback systems, which considers optimization as design philosophy the high-order system control. The basic idea that designing actual and virtual controls solutions corresponding subsystems so overall optimized. general, designed based on solution Hamilton-Jacobi-Bellman equation, but solving equation very difficult due to inherent nonlinearity intractability....

In this paper, a tracking control approach for surface vessel is developed based on the new technique named optimized backstepping (OB), which considers optimization as design principle. Since systems are modeled by second-order dynamic in strict feedback form, an ideal finishing task. of vessel, virtual and actual controls designed to be solutions corresponding subsystems, therefore overall optimized. general, solution Hamilton-Jacobi-Bellman equation. However, solving equation very...

This paper addresses formation control with obstacle avoidance problem for a class of second-order stochastic nonlinear multiagent systems under directed topology. Different deterministic systems, cases are more practical and challenging because the exogenous disturbances depicted by Wiener process considered. In order to achieve objective, both leader-follower approach artificial potential field (APF) method combined together, where is utilized solve problem. For obtaining good system...

The paper proposes an optimized leader-follower formation control for the multi-agent systems with unknown nonlinear dynamics. Usually, optimal is designed based on solution of Hamilton-Jacobi-Bellman equation, but it very difficult to solve equation because dynamic and inherent nonlinearity. Specifically, systems, will become more complicated owing state coupling problem in design. In order achieve control, reinforcement learning algorithm identifier-actor-critic architecture implemented...

This paper proposes an optimized tracking control approach using neural network (NN) based reinforcement learning (RL) for a class of nonlinear dynamic systems, which requires both and optimizing to be performed simultaneously. Generally, obtaining optimal solution, Hamilton-Jacobi-Bellman equation is expected solvable, but, owing strong nonlinearity, the solved difficultly or even impossibly by analytical methods. Therefore, adaptive NN approximation RL usually considered. In design,...

The article proposes an optimized leader-follower formation control using a simplified reinforcement learning (RL) of identifier-critic-actor architecture for class nonlinear multiagent systems. In general, optimal is expected to be obtained by solving Hamilton-Jacobi-Bellman (HJB) equation, but the equation associated with system difficult solve analytical method. Although difficulty can effectively overcome RL strategy, existing algorithms are very complex because their updating laws...

In this article, an adaptive optimized control scheme based on neural networks (NNs) is developed for a class of perturbed strict-feedback nonlinear systems. An backstepping (OB) technique employed breaking through the limitation matching condition. The disturbance existing systems may degrade system performance or even lead to instability. order improve system's robustness, observer constructed compensate impact coming from external disturbance. Because proposed needs train parameters not...

In this article, an optimized leader-following consensus control scheme is proposed for the nonlinear strict-feedback-dynamic multi-agent system by learning from controlling idea of backstepping technique, which designs virtual and actual controls to be solution corresponding subsystems so that entire optimized. Since needs not only ensure optimizing performance but also synchronize multiple state variables, it interesting challenging topic. order achieve control, neural network...

In this article, an optimized tracking control scheme is studied for the quadrotor unmanned aerial vehicle (QUAV) system by combining both reinforcement learning (RL) and backstepping technique. The RL aims to overcome difficulty coming from solving Hamilton–Jacobi–Bellman (HJB) equation, it performed via iterating critic actor each other, where improving performance executing behavior. mathematics, a QUAV composed of two connected subsystems that are, respectively, modeled translational...

In this article, a fuzzy logic system (FLS)-based adaptive optimized backstepping control is developed by employing reinforcement learning (RL) strategy for class of nonlinear strict feedback systems with unmeasured states. For making the virtual and actual controls are solution corresponding subsystem, RL observer-critic-actor architecture based on FLS approximations constructed in every step, where observer aims to estimate unmeasurable states, critic actor aim evaluate performance perform...

This article addresses a distributed time-varying optimal formation protocol for class of second-order uncertain nonlinear dynamic multiagent systems (MASs) based on an adaptive neural network (NN) state observer through the backstepping method and simplified reinforcement learning (RL). Each follower agent is subjected to only local information measurable partial states due actual sensor limitations. In view optimized strategic needs, dynamics undetectable may jointly affect stability...

In this article, an optimized backstepping (OB) control scheme is proposed for a class of stochastic nonlinear strict-feedback systems with unknown dynamics by using reinforcement learning (RL) strategy identifier-critic-actor architecture, where the identifier aims to compensate dynamic, critic evaluate performance and give feedback actor, actor perform action. The basic idea that all virtual controls actual are designed as solution corresponding subsystems so entire optimized. Different...

In this article, an optimized leader-follower consensus control is proposed for a class of second-order unknown nonlinear dynamical multiagent system. Different with the first-order consensus, case needs to achieve agreement not only on position but also velocity, therefore more challenging and interesting. To derive control, reinforcement learning (RL) can be natural consideration because it overcome difficulty solving Hamilton–Jacobi–Bellman (HJB) equation. implement RL, iterate both...