Optimal Tracking Control of Nonlinear Multiagent Systems Using Internal Reinforce Q-Learning

Peng, Zhinan; Luo, Rui; Hu, Jiangping; Shi, Kaibo; Nguang, Sing Kiong; Ghosh, Bijoy K.

doi:10.1109/tnnls.2021.3055761

Cited by 71 publications

(23 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hitherto, neural networks (NNs), as an important branch in the advance of artificial intelligent, have been attracting ever‐increasing research interest within the systems science and control communicates in previous decades owning primarily to its numerous applications, such as image encryption, 1,2 reinforcement learning, 3,4 smart antenna arrays, gramophone noise detection and reconstruction, secure communication, 5 and other aspects, which attribute to their powerful computing abilities and physical realizations. Actually, those practical applications extremely depend on its dynamic behaviors of the underlying NNs.…”

Section: Introductionmentioning

confidence: 99%

On event‐triggered guaranteed cost control for discrete‐time semi‐Markovian neural networks having communication delays and dual‐terminal probabilistic faults

She

Shi

et al. 2022

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

This article aims to address the guaranteed cost control synthesis problem for discrete‐time semi‐Markovian neural networks (D‐SMNNs) considering communication delays along with probabilistic faulty sensors and actuators (dual‐terminal probabilistic faults) by adopting a modified event‐triggered mechanism. Our primary target of this research is to implement a suitable feedback controller such that the resulting D‐SMNNs achieve stochastically stable. To be more concrete, the structural and coefficient switchings of the NNs are characterized by a semi‐Markovian process (SMP) along with the lower and upper bounds of the transition probabilities (TPs), which can reflect the reality more accurately and has a wider application scope. For optimize the resource utilization of the band‐limited communication networks, a modified event‐triggered transmission strategy is put forward to lessen the unnecessary data transmission over network. Additionally, according to different failure rates and the measurement distributions of intelligent modules, a more practical probabilistic sensors and actuators faulty model for networked D‐SMNNs is synthesized, which including additivity and multiplicity. The anamorphic probability of sensors and actuators are governed by a battery of mutually independent stochastic variables that obeys certain probabilistic distribution over the preknown interval false[0,𝕋false]false(𝕋≥1false). Therein, the distortion degree and failure rate for each sensor and actuator can be separately quantized and characterized with the aid of mathematical variance and expectation. Briefly, in comparison to the existing faulty models, the novelty of this extended fault model lies in it can characterize more features in practical industrial applications. Afterwards, by resorting to the Lyapunov functional method and combining with both the stochastic analysis technique and matrix inequality decoupling manipulation, several sufficient conditions on ensuring stabilization for solving both the guaranteed cost controller gains and event‐triggered coefficients are formulated in the shape of a group of linear matrix inequalities (LMIs), which can be verified by exploiting standard compute software. After that, the controller design is reformulated as an optimization problem with LMI constraints immediately. Eventually, three simulation examples are carried out to substantiate the potency and accuracy of the proposed control synthesis methodology.

show abstract

Section: Introductionmentioning

confidence: 99%

On event‐triggered guaranteed cost control for discrete‐time semi‐Markovian neural networks having communication delays and dual‐terminal probabilistic faults

She

Shi

et al. 2022

Intl J Robust & Nonlinear

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, several robust control techniques based on an observer were proposed in [24][25][26][27]. Recent methods proposed novel formation tracking control with good results, such as finite-time criteria design [28][29][30], optimal design with Q-learning [31], consensus design [32], command filtered backstepping [33], the adaptive backstepping technique [34], robust sliding mode with fixed-time stability [35], data driven-based formation control [36], output feedback formation [37], adaptive nonsingular terminal sliding mode [38], and neural networks [39]. However, most studies mentioned above lack experimental results or asymptotical convergence in quadcopter systems.…”

Section: Introductionmentioning

confidence: 99%

Quadrotor Formation Control via Terminal Sliding Mode Approach: Theory and Experiment Results

Nguyen

Park

Dao

et al. 2022

Drones

View full text Add to dashboard Cite

This article presents a formation tracking control method for the operation of multi-agent systems under disturbances. This study aims to ensure that the followers of a quadcopter converge into the desired formation while the center formation of the follower quadcopters tracks the leader’s trajectory within a finite time. The distributed finite-time formation control problem is first investigated using the fast terminal sliding mode control (FTSMC) theory. A disturbance observer is then integrated into the FTSMC to overcome the model uncertainties and bounded disturbances. Subsequently, the Lyapunov function is proposed to ensure the stability of the system. It is shown that formation tracking control can be achieved even in the presence of disturbances. Simulation and experimental results verify the effectiveness of the proposed formation tracking control method compared to existing ones.

show abstract

“…For the past few years, as one of the most effective and popular online learning methods, actor-critic RL was extensively applied in the research field of optimal control. [15][16][17][18][19][20][21][22][23] By utilizing a modified cost function, an optimal robust control strategy was proposed for a class of uncertain nonlinear systems. 19 In Reference 22, based on RL algorithm and improved Hamilton-Jacobi-Bellman (HJB) function, the finite-time optimal control problem was addressed for uncertain nonlinear systems with dead-zone input.…”

Section: Introductionmentioning

confidence: 99%

Performance‐guaranteed containment control for pure‐feedback multi agent systems via reinforcement learning algorithm

Luo

Xiao

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

In this article, a performance-guaranteed containment control scheme based on reinforcement learning (RL) algorithm is proposed for a class of pure-feedback multi agent systems (MASs) with unmeasurable states. The unknown nonlinear functions are approximated by the neural networks (NNs) and an adaptive NN state observer is designed for the states estimation. Based on estimated states, the algebraic loop problem can be removed by introducing filtered signals, and the actor-critic architecture of RL algorithm is employed to acquire the optimal controller in the framework of backstepping. Different from many optimal strategies, this article proposes a simpler mechanism based on the uniqueness of the optimal solution to obtain the actor and critic updating laws instead of gradient descent algorithm with complicated calculation. In addition, predefined performance function and an improved error transformation technique are utilized to guarantee the containment error within a prescribed boundary. By using Lyapunov stability theory and graph theory, the stability of the closed-loop system can be demonstrated. Finally, the effectiveness of the method proposed in this article is verified by a simulation example.

show abstract

Optimal Tracking Control of Nonlinear Multiagent Systems Using Internal Reinforce Q-Learning

Cited by 71 publications

References 54 publications

On event‐triggered guaranteed cost control for discrete‐time semi‐Markovian neural networks having communication delays and dual‐terminal probabilistic faults

On event‐triggered guaranteed cost control for discrete‐time semi‐Markovian neural networks having communication delays and dual‐terminal probabilistic faults

Quadrotor Formation Control via Terminal Sliding Mode Approach: Theory and Experiment Results

Performance‐guaranteed containment control for pure‐feedback multi agent systems via reinforcement learning algorithm

Contact Info

Product

Resources

About