In this paper, the multi-agent systems(MASs) typically with heterogeneous unknown nonlinearities and nonidentical unknown control coefficients are studied. Although the model information of MASs is coarse, the leader-...
详细信息
In this paper, the multi-agent systems(MASs) typically with heterogeneous unknown nonlinearities and nonidentical unknown control coefficients are studied. Although the model information of MASs is coarse, the leader-following consensus is still pursued, with a prescribed performance and zero consensus errors. Leveraging a powerful funnel control strategy, a fully distributed and completely relative-state-dependent protocol is designed. Distinctively, the time-varying function characterizing the performance boundary is introduced, not only to construct the funnel gains but also as an indispensable part of the protocol,enhancing the control ability and enabling the consensus errors to converge to zero(rather than a residual set). Remark that when control directions are unknown, coexisting with inherent system nonlinearities, it is essential to incorporate an additional compensation mechanism while imposing a hierarchical structure of communication topology for the control design and analysis. Simulation examples are given to illustrate the effectiveness of the theoretical results.
Aiming at the consensus control problem of nonlinear multi-agent systems(MASs) under directed topology, a leader-follower bipartite consensus control strategy is proposed. This strategy takes into account the potentia...
详细信息
Aiming at the consensus control problem of nonlinear multi-agent systems(MASs) under directed topology, a leader-follower bipartite consensus control strategy is proposed. This strategy takes into account the potential for denial-of-service(DoS) attacks and completely unknown system dynamics. Specifically, the bipartite consensus dynamics describes the cooperation and competition relationship between followers and the leader, that is, the follower chooses to move in accordance with or opposite to the leader according to its trajectory. In order to optimize the communication bandwidth and mitigate the impact of DoS attacks, the proposed consensus control scheme integrates the DoS attack detection mechanism and event-triggered mechanism. In addition, neural networks(NNs) are used to solve the nonlinear problem, and a speed function is designed to achieve the desired tracking performance, ensuring that all agents' tracking errors converge to a predefined set in a finite time. With the help of backstepping, graph theory, and Lyapunov stability theory, sufficient conditions for achieving bipartite consensus without Zeno behavior are established. Finally, the accuracy and feasibility of the theoretical analysis are verified by simulation cases.
As a crucial storage and buffering apparatus for balancing the production and consumption of byproduct gases in industrial processes, accurate prediction of gas tank levels is essential for optimizing energy system sc...
详细信息
As a crucial storage and buffering apparatus for balancing the production and consumption of byproduct gases in industrial processes, accurate prediction of gas tank levels is essential for optimizing energy system scheduling. Considering that the continuous switching of the pressure and valve status(mechanism knowledge) would bring about multiple working conditions of the equipment, a multi-condition time sequential network ensembled method is proposed. In order to especially consider the time dependence of different conditions, a centralwise condition sequential network is developed, where the network branches are specially designed based on the condition switching sequences. A branch combination transfer learning strategy is developed to tackle the sample imbalance problem of different condition data. Since the condition or status data are real-time information that cannot be recognized during the prediction process, a pre-trained and ensemble learning approach is further proposed to fuse the outputs of the multi-condition networks and realize a transient-state involved prediction. The performance of the proposed method is validated on practical energy data coming from a domestic steel plant, comparing with the state-of-the-art algorithms. The results show that the proposed method can maintain a high prediction accuracy under different condition switching cases, which would provide effective guidance for the optimal scheduling of the industrial energy systems.
This study investigates the deterministic learning(DL)-based output-feedback neural control for a class of nonlinear sampled-data systems with prescribed performance(PP). Specifically, first, a sampleddata observer is...
详细信息
This study investigates the deterministic learning(DL)-based output-feedback neural control for a class of nonlinear sampled-data systems with prescribed performance(PP). Specifically, first, a sampleddata observer is employed to estimate the unavailable system states for the Euler discretization model of the transformed system dynamics. Then, based on the observations and backstepping method, a discrete neural network(NN) controller is constructed to ensure system stability and achieve the desired tracking performance. The noncausal problem encountered during the controller deduction process is resolved using a command filter. Moreover, the regression characteristics of the NN input signals are demonstrated with the observed states. This ensures that the radial basis function NN, based on DL theory, meets the partial persistent excitation condition. Subsequently, a class of discrete linear time-varying systems is proven to be exponentially stable, achieving partial convergence of neural weights to their optimal/actual values. Consequently, accurate modeling of unknown closed-loop dynamics is achieved along the system trajectory from the output-feedback control. Finally, a knowledge-based controller is developed using the modeling *** controller not only enhances the control performance but also ensures the PP of the tracking error. The effectiveness of the scheme is illustrated through simulation results.
The maximum principle has bridged mathematical optimization to optimal control,ushering in significant developments and refinements in optimal control theory,notably during the 1960s with the advent of linear quadrati...
The maximum principle has bridged mathematical optimization to optimal control,ushering in significant developments and refinements in optimal control theory,notably during the 1960s with the advent of linear quadratic (LQ)control and linear quadratic estimation (LQE).This progression propelled optimal control theory into further advancements,encompassing stochastic control,robust/H-infinity control,model predictive control (MPC),networked control,and reinforcement learning *** control,established upon a rigorous mathematical foundation,extends static optimization theory to dynamic systems,exhibiting scientific essence,unity,and ***,since its inception,optimal control theory has served as an indispensable core role across all control-related domains,including communication-constrained control in networked systems,consensus control,cooperative control,and reinforcement learning control.
In the paper, we investigate the optimization problem(OP) by applying the optimal control method. The optimization problem is reformulated as an optimal control problem(OCP) where the controller(iteration updating) is...
详细信息
In the paper, we investigate the optimization problem(OP) by applying the optimal control method. The optimization problem is reformulated as an optimal control problem(OCP) where the controller(iteration updating) is designed to minimize the sum of costs in the future time instant, which thus theoretically generates the “optimal algorithm”(fastest and most stable). By adopting the maximum principle and linearization with Taylor expansion, new algorithms are proposed. It is shown that the proposed algorithms have a superlinear convergence rate and thus converge more rapidly than the gradient descent;meanwhile, they are superior to Newton's method because they are not divergent in general and can be applied in the case of a singular or indefinite Hessian matrix. More importantly, the OCP method contains the gradient descent and the Newton's method as special cases, which discovers the theoretical basis of gradient descent and Newton's method and reveals how far these algorithms are from the optimal algorithm. The merits of the proposed optimization algorithm are illustrated by numerical experiments.
Driven by practical applications, the achievement of distributed observers for nonlinear systems has emerged as a crucial advancement in recent years. However, existing theoretical advancements face certain limitation...
详细信息
Driven by practical applications, the achievement of distributed observers for nonlinear systems has emerged as a crucial advancement in recent years. However, existing theoretical advancements face certain limitations: They either fail to address more complex nonlinear phenomena, rely on hard-to-verify assumptions, or encounter difficulties in solving system ***, this paper aims to address these challenges by investigating distributed observers for nonlinear systems through the full-measured canonical form(FMCF), which is inspired by full-measured system(FMS) theory. To begin with, this study addresses the fact that the FMCF can only be obtained through the observable canonical form(OCF) in existing FMS *** paper demonstrates that a class of nonlinear systems can directly obtain FMCF through state space equations, independent of OCF. Also, a general method for solving FMCF in such systems is provided. Furthermore, based on the FMCF, A distributed observer is developed for nonlinear systems under two scenarios: Lipschitz conditions and open-loop bounded *** paper establishes their asymptotic omniscience and demonstrates that the designed distributed observer in this study has fewer design parameters and is more convenient to construct than existing approaches. Finally, the effectiveness of the proposed methods is validated through simulation results on Van der Pol oscillators and microgrid systems.
In this paper,the authors design a reinforcement learning algorithm to solve the adaptive linear-quadratic stochastic n-players non-zero sum differential game with completely unknown *** each player,a critic network i...
详细信息
In this paper,the authors design a reinforcement learning algorithm to solve the adaptive linear-quadratic stochastic n-players non-zero sum differential game with completely unknown *** each player,a critic network is used to estimate the Q-function,and an actor network is used to estimate the control input.A model-free online Q-learning algorithm is obtained for solving this kind of *** is proved that under some mild conditions the system state and weight estimation errors can be uniformly ultimately bounded.A simulation with five players is given to verify the effectiveness of the algorithm.
This paper focuses on a Pareto cooperative differential game with a linear mean-field backward stochastic system and a quadratic form cost functional. Based on a weighted sum optimality method, the Pareto game is equi...
详细信息
This paper focuses on a Pareto cooperative differential game with a linear mean-field backward stochastic system and a quadratic form cost functional. Based on a weighted sum optimality method, the Pareto game is equivalently converted to an optimal control problem. In the first place,the feedback form of Pareto optimal strategy is derived by virtue of decoupling technology, which is represented by four Riccati equations, a mean-field forward stochastic differential equation(MF-FSDE),and a mean-field backward stochastic differential equation(MF-BSDE). In addition, the corresponding Pareto optimal solution is further obtained. Finally, the author solves a problem in mathematical finance to illustrate the application of the theoretical results.
After detecting a target object,a service robot must approach the target object to perform the associated service *** active object detection(AOD)tasks,effective feature information representation and comprehensive ac...
详细信息
After detecting a target object,a service robot must approach the target object to perform the associated service *** active object detection(AOD)tasks,effective feature information representation and comprehensive action execution strategies are ***,most AOD tasks are accomplished by traditional reinforcement learning algorithms,but there are still problems such as high task failure rates and model training *** solve these problems,this paper proposes a combined data-driven and knowledge-guided ***,semantic information features,depth information features and target object bounding box information are used as inputs to comprehensively represent feature ***,a policy network is constructed based on the proximal policy optimizaton(PPO)*** reward value is set according to the robot′s action,the position of the bounding box,and the distance to the target object,and then applied to the robot′s training ***,the knowledge of the path experience in the task,the robot′s collision avoidance ability and the prediction of target object loss are combined to guide the robot′s behavior,and a comprehensive decision model is proposed to enable the robot to make the best *** experiments were conducted on an active vision *** robot achieves an average success rate of 91.36%and an average step size of 9.3631 in performing the AOD task in the test scenes,which verifies the effectiveness of the proposed scheme.
暂无评论