Distributed optimization is growing increasingly important in large-scale complex systems for its flexibility and efficiency. However, the pressing challenge in distributed scenarios is that the cost functions are unknown and communication resources are limited. In response to the dual challenges of inaccessible gradients and limited communication resources, a distributed zero-order gradient scheme with a local prediction mechanism is proposed. It is suitable for unbalanced directed networks and reduces communication overhead via sparsification strategies. The proposed algorithm employs an error feedback mechanism to compensate for corrupted information, thereby ensuring the effectiveness of the zero-order gradient scheme. Furthermore, the devised local prediction mechanism improves the convergence performance of the algorithm in the presence of inaccurate transmission information and gradient estimation bias. With appropriate selection of the step size and setting of the perturbation radius, the proposed algorithm can converge linearly to the optimal point. Finally, the validity of findings is verified by numerical simulations.

This article is concerned with the recursive neural network (NN)-based state estimation problem for a class of stochastic discrete time-varying systems subjected to both unknown nonlinear dynamics and the token bucket communication protocol. The token bucket protocol is utilized to determine whether the sensor signal is granted access to the network at each transmission instant, wherein the transmission may fail due to an insufficient number of tokens in the bucket. The objective of the addressed problem is to design a recursive NN-based state estimator such that, under the influence of the unknown nonlinear dynamics and the token bucket communication protocol, certain upper bounds of both the state estimation error covariance and the NN-weight (NNW) error covariance are guaranteed, while the explicit expressions of the NN-based estimator gain and the NN tuning parameters are derived. By employing two sets of matrix difference equations, two upper bounds for the state estimation error covariance and the NNW error covariance are established, and these upper bounds are subsequently minimized by parameterizing the NN-based estimator gain in terms of the solutions to the matrix difference equations. Finally, an illustrative example is provided to demonstrate the feasibility and effectiveness of the proposed estimation approach.

Reinforcement learning methods for manipulator trajectory generation often suffer from low sample efficiency and inadequate exploration. To address this issue, an efficient expert guidance mechanism with dynamic movement primitives is incorporated into reinforcement learning. In the mechanism, the expert model is built to provide suggested actions and guided rewards for the agent. It gradually improves the performance of the agent through a learning strategy of multiple stages, combined with expert demonstration and self-exploration. The proposed method enhances the performance of actor–critic-based reinforcement learning algorithms, which is verified in simulation, and further validated in a sweet pepper harvesting experiment.

In this article, we investigate aggregative games with coupling constraints and local feasibility constraints over digraphs. It is noted that the imbalance introduced by the digraph leads to an inaccurate estimation of the global aggregation function and increases the difficulty of handling coupling constraints. To overcome this issue, a consensus dynamics is designed to estimate the right eigenvector associated with the zero eigenvalue of the Laplacian matrix constructed using the nodes’ out-degree information. By normalizing with the estimated right eigenvector, the imbalance is eliminated, enabling accurate estimation of the global aggregation function. Based on this, a distributed projection-based algorithm is developed, and through the aid of the proposed consensus dynamics, the asymptotic convergence to the Nash equilibrium (NE) is rigorously proven via singular perturbation theory. In particular, when either local feasibility constraints or coupling constraints are absent, the proposed algorithm achieves exponential convergence to the NE. Finally, the effectiveness of the proposed algorithms is validated through simulations on the location problem and Nash–Cournot games.

Robots operating in agricultural environments require a robust, fast perception system to accurately identify picking points. This paper proposed a lightweight method for detecting sweet pepper peduncles, which uses an active illumination camera system and DUTU2-Net+to achieve efficient and accurate peduncle detection. The camera system is used to overcome the influence of ambient light through flash and no-flash (FNF) image pairs, achieving more robust color detection and quickly locating the peduncle’s region of interest (ROI). The improved DUTU2-Net+is used accurately for peduncle ROI detection. It uses an encoder with depthwise separable convolution (DSC), dilated convolution, and a feature enhancement structure with a triple attention module (TAM) to reduce the computational load and parameters while ensuring detection accuracy. Experimental results show that the proposed method can effectively identify the position of the peduncle. The DUTU2-Net+model achieves an average absolute error of 0.002, a maximum F1score of 0.992, a frame rate of 36.3 FPS, and a model size of 6.9 MB. The source code is available at https://gitee.com/rosdx/detection-for-harvesting.git.

Energy trading in industrial parks has great potential for reducing carbon emissions and lowering energy bills. This article proposes a safe multiagent deep reinforcement learning algorithm for optimizing the energy trading strategy in industrial parks to achieve less reliance on the main grid and save energy costs. Specifically, an industrial park that contains multiple industrial users with both thermal and electrical load requirements is considered, in which the different users can trade energy with each other and with the main grid based on their own strategies. Unlike the existing studies, the time-phased energy trading problem is transformed into a constrained partially observable Markov game, which models the industrial users and objectives of the buyers and sellers. Finally, a novel multiagent primal-dual proximal policy optimization algorithm that guarantees safety is developed to achieve the optimal trading strategies between the main grid and multiple users. Numerical simulations with real-world data demonstrate that the proposed algorithm allows higher total revenue for sellers and lower total costs for buyers in the park, limits each user's bid or offer to a relatively safe range, and increases the amount of electricity traded locally, while reducing trading with the grid.

Load forecasting is critical to the task of energy management in power systems, for example, balancing supply and demand and minimizing energy transaction costs. There are many approaches used for load forecasting such as the support vector regression (SVR), the autoregressive integrated moving average (ARIMA), and neural networks, but most of these methods focus on single-step load forecasting, whereas multistep load forecasting can provide better insights for optimizing the energy resource allocation and assisting the decision-making process. In this work, a novel sequence-to-sequence (Seq2Seq)-based deep learning model based on a time series decomposition strategy for multistep load forecasting is proposed. The model consists of a series of basic blocks, each of which includes one encoder and two decoders; and all basic blocks are connected by residuals. In the inner of each basic block, the encoder is realized by temporal convolution network (TCN) for its benefit of parallel computing, and the decoder is implemented by long short-term memory (LSTM) neural network to predict and estimate time series. During the forecasting process, each basic block is forecasted individually. The final forecasted result is the aggregation of the predicted results in all basic blocks. Several cases within multiple real-world datasets are conducted to evaluate the performance of the proposed model. The results demonstrate that the proposed model achieves the best accuracy compared with several benchmark models.

The aging population and diminishing working population in agriculture motivate the development of autonomous harvesting robots. Although autonomous harvesting is expanding rapidly, the commercial application of sweet pepper harvesting robots still faces challenges. This paper presents the development of a sweet pepper harvesting robot and reports its experimental verification, which mainly includes end-effector design, visual perception, and grasping pose control. The end-effector adopts electrical control, mainly composed of a servo-electric two-finger parallel clamping module, a swing-cutting module, and a fruit recovery device. Equipped with a tactile sensor array, it can accurately sense the sweet pepper peduncle position and the end-effector state (harvesting failure) to complete the precise cutting. An end-effector grasping pose control algorithm of the manipulator is proposed, which can control the end-effector to grasp along the direction of the fruit peduncle and perpendicular to the tangent direction of the picking point by estimating the pose of the sweet pepper peduncle. Finally, the robot and proposed method were verified in a plant factory. The experimental findings demonstrate that the developed harvesting robot can complete robust detection of fruit peduncles and non-destructive picking of sweet pepper, with an average picking time of about 15 seconds.

This article studies the stability problem of discrete-time switched positive linear systems (SPLSs) with marginally stable subsystems. Based on the weak common linear copositive Lyapunov function (weak CLCLF) approach, the switching property and the state component property are combined to ensure the asymptotic stability of SPLSs under three types of switching signals. First, considering the transfer-restricted switching signal described by the switching digraph, novel cycle-dependent joint path conditions are proposed in combination with state component digraphs. Second, under the time interval sequence, two types of path conditions are constructed for designing switching schemes. Third, necessary and sufficient conditions for the asymptotic stability of SPLSs under arbitrary switching are established. Finally, three examples are provided to illustrate the effectiveness of the proposed method.

This paper proposes a novel dynamic eventtriggered scheme for nonlinear multi-agent systems under denialof-service (DoS) attacks via an adaptive fuzzy resilient control method. At the beginning, fuzzy logic systems are utilized to identify the unknown system dynamics. Then, a reliable attack detection mechanism forms the basis for establishing a dynamic event-triggered protocol, where dynamic parameters are introduced to adjust the threshold of event-triggered conditions. Compared with common attack detection methods relying on residuals between system and observer values, a novel and reliable mechanism for detecting DoS attacks is proposed, grounded in the logical relationship of voltage level signals derived from the outputs of detection components. Finally, a backstepping recursive design framework is utilized for constructing an eventtriggered adaptive fuzzy controller. Through the Lyapunov analysis, it is strictly demonstrated that, even under DoS attacks, the followers remain inside the leaders’ defined convex hull. The effectiveness of the presented control scheme is illustrated through the simulation results.

As environmental pollution becomes increasingly serious and industrial energy consumption continuously rises, an intelligent and efficient industrial energy management policy is urgently needed to reduce costs and maximize the benefits of industrial energy systems. However, modern industrial energy systems are characterized by hybrid industrial equipment actions, diverse objectives, and highly intermittent and stochastically distributed renewable energy sources. Therefore, efficient operation and control are difficult. This article presents a novel, model-free energy management policy using a hybrid action deep reinforcement learning algorithm for energy scheduling of industrial equipments operating in various modes. Specifically, the interaction process between the industrial energy management center and each equipment is modeled as a Markov decision process that minimizes the daily operating cost of the energy system and maximizes the revenue of the production equipment. Then, a double parameterized deep Q-networks that does not require an explicit environmental model is developed to learn the hybrid action signals using actor and critic networks, in which the double Q value mechanism avoids value overestimation and improves the algorithm efficiency. In addition, the policy gradient of the proposed algorithm is derived and its convergence proof is discussed. Finally, numerical studies are conducted using real-world data to evaluate algorithm performance and verify its effectiveness.

This article investigates the bumpless transfer (BT) control problem of switched systems with unmeasured states. Note that the control input signal of the switched system jumps when switching occurs, which may adversely affect the performance of switched systems. By introducing a modified state observer and an auxiliary continuous control signal, a novel description of the BT performance for the system is presented. Moreover, a compensation-based dynamic BT controller and a bump-dependent switching law are designed to solve the BT control problem. As a result, the developed control method ensures the stability of the closed-loop system while maintaining BT performance. The validation of the results can be provided by applying the proposed BT control method to an example of an aero-engine control system.

Residential energy consumption continues to climb steadily, requiring intelligent energy management strategies to reduce power system pressures and residential electricity bills. However, it is challenging to design such strategies due to the random nature of electricity pricing, appliance demand, and user behavior. This article presents a novel reward shaping (RS)-based actor–critic deep reinforcement learning (ACDRL) algorithm to manage the residential energy consumption profile with limited information about the uncertain factors. Specifically, the interaction between the energy management center and various residential loads is modeled as a Markov decision process that provides a fundamental mathematical framework to represent the decision-making in situations where outcomes are partially random and partially influenced by the decision-maker control signals, in which the key elements containing the agent, environment, state, action, and reward are carefully designed, and the electricity price is considered as a stochastic variable. An RS-ACDRL algorithm is then developed, incorporating both the actor and critic network and an RS mechanism, to learn the optimal energy consumption schedules. Several case studies involving real-world data are conducted to evaluate the performance of the proposed algorithm. Numerical results demonstrate that the proposed algorithm outperforms state-of-the-art RL methods in terms of learning speed, solution optimality, and cost reduction.

This article presents a novel control protocol for a class of switched large-scale nonlinear systems subject to prescribed performance constraints and bumpless transfer constraints. The prescribed performance constraints enforce the output tracking error to converge to a predefined residual set, with a predefined maximum overshoot and minimum convergence rate. Meanwhile, the bumpless transfer constraints restrict the bump of the control input when switching between two adjacent modes. By incorporating the modification signals into the prescribed performance functions (PPFs), control-bump PPFs (CPPFs) are provided to proactively reduce the performance bounds to a reasonable level. The modification signals are associated with control bumps and generated by an auxiliary switched positive system. Furthermore, a model of control bump is developed to enhance the dynamic response, and switched disturbance observers are employed to estimate external disturbances. In the framework of dynamic surface control and multiple Lyapunov stability theory, a prescribed performance bumpless transfer control (PPBTC) approach is proposed to guarantee the prescribed performance and bumpless transfer performance. Finally, a practical example of the proposed control scheme is presented to demonstrate its validity and applicability.

This article is concerned with the containment control problem for a class of multiagent systems (MASs) based on event-triggered output feedback. For homogeneous MASs, a distributed observer-based containment control protocol and a distributed hybrid event-triggered scheme are proposed. The observers, containment controllers, and event-triggered conditions are designed simultaneously by means of the matrix transformation technique. The proposed event-triggered mechanism includes not only the traditional triggering function but also a running time upper bound, which saves the communication workload and improves system performance. Furthermore, based on the output regulation framework, a hybrid distributed event-triggered scheme and a distributed containment control protocol for heterogeneous MASs are developed, where the dynamics of the followers vary. Multiply unmanned aerial vehicles are modeled as a linear MAS to verify the effectiveness of the presented algorithm.

In this paper, a distributed randomized gradient-free optimization protocol of multiagent systems over weight-unbalanced digraphs described by row-stochastic matrices is proposed to solve a distributed constrained convex optimization problem. Each agent possesses its local nonsmooth, but Lipschitz continuous, objective function and assigns the weight to information gathered from in-neighbor agents to update its decision state estimation, which is applicable and straightforward to implement. In addition, our algorithm relaxes the requirements of diminishing step sizes to only a nonsummable condition under convex bounded constraint sets. The boundedness and ultimate limit, instead of the supermartingale convergence theorem, are utilized to analyze the consistency and convergence and demonstrate convergence rates with different step sizes. Finally, the validity of the proposed algorithm is verified through numerical examples.

In this article, we consider the distributed optimal consensus problem under nominal and nonfragile cases for a class of minimum-phase uncertain nonlinear systems with unity-relative degree and disturbances generated by an external autonomous system. The involved cost function is the sum of all local cost functions associated with each individual agent. Two different edge-based distributed adaptive algorithms utilizing the internal model principle are designed to solve the problem in a fully distributed manner. Graph theory, nonsmooth analysis, convex analysis, and the Lyapunov theory are employed to show that the proposed algorithms converge accurately to the optimal solution of the considered problem. Finally, an example involving the dynamics of a Lorenz-type system is provided to demonstrate the effectiveness of the obtained results.

This article is concerned with the distributed recursive filtering issue for stochastic discrete time-varying systems subjected to both state saturations and round-robin (RR) protocols over sensor networks. The phenomenon of state saturation is considered to better describe practical engineering. The RR protocol is introduced to mitigate a network burden by determining which component of the sensor node has access to the network at each transmission instant. The purpose of the issue under consideration is to construct a distributed recursive filter such that a certain filtering error covariance's upper bound can be found and the corresponding filter parameters' explicit expression is given with both state saturations and RR protocols. By taking advantage of matrix difference equations, a filtering error covariance's upper bound can be presented and then be minimized by appropriately designing filter parameters. In particular, by using a matrix simplification technique, the sensor network topology's sparseness issue can be tackled. Finally, the feasibility for the addressed filtering scheme is demonstrated by an example.

This paper considers the containment control problem for multiple Euler-Lagrange systems with unknown nonlinear dynamics, where the dynamics of the leaders are different from those of the followers. In addition, some followers cannot obtain information of the leaders owing to the limited communication range. We first adopt an event-based observer to estimate a trajectory inside the convex hull spanned by states of the leaders, in which continuous communication can be avoided as well. Then, we further utilize the fuzzy logic systems to approximate the unknown nonlinear dynamics and propose an adaptive control scheme. Under the proposed scheme, we can ensure that the states of the followers can converge to the convex hull formed by these states of the leaders. Finally, a simulation example is given to validate the effectiveness of the proposed control scheme.

This article tackles the recursive filtering problem for a class of stochastic nonlinear time-varying complex networks (CNs) suffering from both the state saturations and the deception attacks. The nonlinear inner coupling and the state saturations are taken into account to characterize the nonlinear nature of CNs. From the defender's perspective, the randomly occurring deception attack is governed by a set of Bernoulli binary distributed white sequence with a given probability. The objective of the addressed problem is to design a state-saturated recursive filter such that, in the simultaneous presence of the state saturations and the randomly occurring deception attacks, a certain upper bound is guaranteed on the filtering error covariance, and such an upper bound is then minimized at each time instant. By employing the induction method, an upper bound on the filtering error variance is first constructed in terms of the solutions to a set of matrix difference equations. Subsequently, the filter parameters are appropriately designed to minimize such an upper bound. Finally, a numerical simulation example is provided to demonstrate the feasibility and usefulness of the proposed filtering scheme.

In this paper, we focus on a constrained convex optimization problem of multiagent systems under a time-varying topology. In such topology, it is not only B-strongly connected, but the communication noises are also existent. Each agent has access to its local cost function, which is a nonsmooth function. A gradient-free random protocol is come up with minimizing a sum of cost functions of all agents, which are projected to local constraint sets. First, considering the stochastic disturbances in the communication channels among agents, the upper bounds of disagreement estimate of agents' states are obtained. Second, a sufficient condition on choosing step sizes and smoothing parameters is derived to guarantee that all agents almost surely converge to the stationary optimal point. At last, a numerical example and a comparison are provided to illustrate the feasibility of the random gradient-free algorithm.

This paper proposes a method of robot formation and tracking control based on the comprehensive application of multiple sensors. The method uses a two-dimensional laser radar to construct a high-precision map and performs multi-point sequential navigation to provide a travel path for the robot formation. Then use binocular vision to complete the recognition and positioning of other robot members in the formation, and adopt the leader-follower mode to realize different formations. Next, the wireless communication module is used to send and receive commands, thereby implementing the formation transformation. Finally, the effectiveness of the method is verified by experiments.

In this paper, based on differential inclusions and the saddle point dynamics, a novel second-order continuous-time algorithm is proposed to solve the optimal resource allocation problem in power systems. The considered cost function is the sum of all local cost functions with a set of affine equality demand constraints and an inequality constraint on generating capacity of the generator. In virtue of nonsmooth analysis, geometric graph theory, and Lyapunov stability theory, all generators achieve consensus on the Lagrange multipliers associated with a set of affine equality constraints while the proposed algorithm converges exponentially to the optimal solution of the resource allocation problem starting from any initial states over an undirected and connected graph. Moreover, the obtained results can be further extended to the optimal resource allocation problem in case of switching communication topologies. Finally, two numerical examples involving a smart grid system composed of five generators and the IEEE 30-bus system demonstrate the effectiveness and the performance of the theoretical results.

This paper proposes a first-order extremum-seeking algorithm to solve the resource allocation problem, where the specific expression form and gradient information of the local cost functions are not required. Agents take advantage of measurements of local cost functions to minimize the sum of their cost functions while satisfying the resource constraint, where agents exchange the estimated decisions with their neighbors under an undirected and connected graph. Making use of the Lyapunov stability theory and the average analysis method, the convergence of the proposed algorithm to the neighborhood of the optimal solution is presented. In addition, it is obtained that the designed algorithm is semiglobally practically asymptotically stable. Then, the first-order algorithm is extended to the second-order algorithm with low-pass filters, which achieves better convergence performance than the first-order algorithm. Finally, the effectiveness of the proposed algorithm is illustrated by numerical examples and its application to economic dispatch in smart grids.

This paper is concerned with the problem of average consensus control for multi-agent systems with linear and Lipschitz nonlinear dynamics under a switching topology. First, a proportional and derivative-like consensus algorithm for linear cases with a time delay is designed to address such a problem. By a system transformation, such a problem is converted to the stability problem of a switched delay system. The stability analysis is performed based on a proposed Lyapunov-Krasoversusii functional including a triple-integral term and sufficient conditions are obtained to guarantee the average consensus for multi-agent systems under arbitrary switching. Second, extensions to the Lipschitz nonlinear cases are further presented. Finally, numerical examples are given to illustrate the effectiveness of the results.

The cooperative containment control for multiagent systems with high-order linear dynamics under a directed graph is studied. A follower-based observer based on relative outputs of neighboring agents is developed to estimate the relative states of neighbors which avoid designing the observer for the leaders in the existing literature. A matrix transformation is introduced to eliminate the coupling terms resulting from the simultaneous design of observers and controllers. A feasible condition on devising observers and controllers is obtained. Furthermore, the result is extended to deal with the case with transmission time delay. The effectiveness of the proposed design method is verified by providing two simulation examples.

This paper is concerned with the problem of output feedback adaptive control for switched systems with unmodeled dynamics and relative degree p. Firstly, for the former p states, based on the local filters, an adaptive controller is designed by using a backstepping recursive design method and a common coordinate transformation for all subsystems. Second, a common Lyapunov function is constructed to establish the boundedness of all signals in the resulting closed-loop switched systems under arbitrary switching signals. Finally, it is shown that a system output can track the desired trajectory.

This paper is concerned with the problem of stabilization for positive switched delay systems. A hysteresis switching law is designed to stabilize positive switched systems with a time delay. On one hand, such switching laws can eliminate the chattering resulting from state-dependent switching laws. On the other hand, a constant time delay may sometimes lead to the instability of positive switched systems. Sufficient conditions on the existence of hysteresis switching laws are presented by making use of linear programming approach. The validity of the proposed approaches is illustrated by a numerical example.

In this paper, an integral sliding mode control approach is employed to analyze the mean-square exponential stability for a class of uncertain switched nonlinear stochastic systems under asynchronous switching signals. Firstly, an integral sliding surface is designed and a sufficient condition for its existence are presented to guarantee the mean-square exponential stability of switched systems in the sliding motion. Then variable controllers are designed such that switched systems remain in the sliding motion from the initial time instant. Due to the asynchronous switching between system modes and the corresponding controllers, the results presented allow the closed-loop systems to be unstable in the mismatched periods. Finally, a numerical example is presented to illustrate the effectiveness of the proposed results.

This paper presents anH∞controller design method for networked control systems (NCSs) with bounded packet dropouts. A new model is proposed to represent packet dropouts satisfying a Markov process and late-arrival packets. The closed-loop NCS with a state-feedback controller is transformed into a Markov system, which is convenient for the controller synthesis. Two types of state-feedback control laws are taken into account. Sufficient conditions on the existence of controllers for stochastic stability with anH∞disturbance attenuation level are derived through a Lyapunov function dependent on the upper bound of the number of consecutive packet dropouts. A numerical example is finally provided to show the effectiveness of the proposed method.

This correspondence deals with the problem of robust fault detection for discrete-time switched systems with state delays under an arbitrary switching signal. The fault detection filter is used as the residual generator, in which the filter parameters are dependent on the system mode. Attention is focused on designing the robust fault detection filter such that, for unknown inputs, control inputs, and model uncertainties, the estimation error between the residuals and faults is minimized. The problem of robust fault detection is converted into an H(infinity)-filtering problem. By a switched Lyapunov functional approach, a sufficient condition for the solvability of this problem is established in terms of linear matrix inequalities. A numerical example is provided to demonstrate the effectiveness of the proposed method.