This article focuses on the design of inverse optimal control (IOC) based on inverse reinforcement learning (IRL) for distributed parameter systems (DPSs) with unknown dynamic parameters. First, considering that the optimal policies may not display the expected performance when they are migrated to real-world DPSs due to model bias, the human-behavior learning (HBL) strategy is utilized to transfer the optimal strategy of the reference systems to the real-world DPSs. Furthermore, to avoid performance degradation caused by predefined reward-weight matrices during the optimal control process of the reference systems, the IRL policy iteration algorithm is employed to realize the IOC of the reference systems, and the equivalent reward-weight matrices and optimal control gains of the reference systems are solved. Finally, the effectiveness and superiority of the algorithms are verified in simulation.

This article investigates impulsive fault-tolerant control for singular partial differential equation (PDE) systems subject to stochastic actuator failures. First, an impulsive observer is designed to estimate unmeasurable system states, which reduces the observation frequency while maintaining estimation accuracy, thereby effectively alleviating the computational burden and implementation challenges of complex dynamic systems. To capture potential stochastic actuator failures in engineering practice, a semi-Markov chain with a partially unknown kernel is then employed. Based on the measured outputs and estimated data, an impulsive controller is subsequently developed to stabilize the system. Furthermore, sufficient conditions for the admissibility of the singular PDE system are obtained by analyzing a Lyapunov function that incorporates discrete-time state information. Finally, the input–output control system between the petrochemical and the equipment manufacturing industries is characterized by a singular PDE system based on the Leontief dynamic input–output model, and the validity and effectiveness of the proposed control method are validated through a simulation.

With the growth of multisource sensor technology, multimodal learning has become pivotal in remote sensing (RS) image segmentation. Despite its potential, current methods face challenges in acquiring large-scale paired samples. When annotated optical images are available, but synthetic aperture radar (SAR) images lack annotations, learning discriminative features for SAR images from optical images becomes difficult. Unsupervised domain adaptation (UDA) offers a potential solution to this challenge, which we refer to as unpaired cross-modality UDA. In this article, we propose unlocking pseudolabel potential and alignment (ULPA) for unpaired cross-modality adaptation in RS image segmentation, a novel one-stage adaptation framework designed to enhance cross-modality knowledge transfer. Our approach employs a prototypical multidomain alignment (PMDA) strategy, which reduces the modality gap through contrastive learning between features and prototypes of identical classes across different modalities. In addition, we introduce the unreliable-sample-guided feature contrast (UFC) loss to address the underutilization of unreliable pixels during training. This strategy separates reliable and unreliable pixels based on prediction confidence, assigning unreliable pixels to a category-wise queue of negative samples, thus ensuring all candidate pixels contribute to the training process. Extensive experiments show that the integration of PMDA and UFC loss can lead to more effective cross-modality domain alignment and substantially boost the model's generalization capability.

This article considers the adaptive fuzzy optimized secure self-triggered control (STC) problem for constrained fractional-order nonlinear systems (FONSs) subject to unknown false data injection attacks (FDIAs). To fulfill the unilateral full-state constraints (UFSCs), an emerging nonlinear state-dependent function with convexity is utilized by means of its property in removing the feasibility conditions existing in the traditional constraint control. Meanwhile, since the true information of the state variables under attack signals is unavailable, a method of coordinate transformation combining the compromised system and dynamic surface control is used for designing the corresponding controller while alleviating the adverse impacts of the FDIAs. Additionally, by constructing the equivalent auxiliary systems and employing actor-critic neural networks (NNs), a reinforcement learning (RL)-based adaptive fuzzy optimal program is provided to achieve optimal control. Furthermore, considering that event-triggered mechanism needs real-time supervision of the control signals, a STC strategy is introduced to circumvent this drawback and reduce communication consumption. Leveraging the fractional Lyapunov stability theory, it has been confirmed that the devised controller can ensure that the stabilization errors tend toward a small area nearby the origin at the minimum costs and all the signals arising in the closed-loop system (CLS) are bounded. Eventually, two simulation examples are offered to demonstrate the reported control algorithm’s validity.

This article zeroes in on the adaptive resilient optimized containment control for multiple quadrotor uncrewed aerial vehicle under malicious attacks and input saturation. First, a flexible tunnel performance constraint strategy is presented to reduce the conservative constraints distributed on both sides of traditional prescribed performance methods, where the auto-adjustable envelopes effectively prevent the containment error from exceeding the maximum allowable tight sets. Subsequently, by constructing a modified fixed-time filter and the identifier-actor-critic structure, a reinforcement-learning-based dynamic surface containment control strategy is established to train an approximate optimal control solution. In addition, an adaptive fuzzy wavelet neural resilient optimal fixed-time containment protocol is developed to counteract malicious attacks, effectively removing the conservatism assumption of the boundaries of multiplicative and additive attack signals. Stability analysis demonstrates that all signals of the closed-loop attitude control system are fixed-time bounded, and the output signals of the followers enter into the convex hull formed by the leaders. Finally, the feasibility of the proposed control algorithm is substantiated by illustrative results.

This article focuses on an adaptive neural optimal output feedback control strategy for stochastic nonaffine multiple input multiple output nonlinear systems with input saturation. Initially, an emerging local state estimation filter is delicately formulated to identify the unavailable states while economizing the redundant resource usage in the state estimation filter-to-controller channel. Then, the tracking error can be regulated within a flexible envelope range by designing a modified flexible global prescribed time function depending on the intermittent systems at the expense of certain user-prescribed indexes. Technically, an amended nonlinear filter featuring the hyperbolic tangent function is constructed to overcome the curse of dimensionality while compensating for the effect of neglected filter error. Meanwhile, an optimized adaptive event-triggered controller is developed to adjust the triggered threshold online to release networked resources and consumed control expenses employed in the controller-to-actuator channel. Since the trigger criteria of different channels are not correlated with each other, the designer can tune the signal delivery frequency of each channel separately following the practical requirements. The boundedness of all signals is ensured via Itô’s differential equation. Herein, two illustrative analyses verify the efficacy and feasibility of the established control algorithm.

This article studies the adaptive prescribed-time fuzzy optimal containment control issue for multiagent systems (MASs) with deferred output constraints based on the reinforcement learning (RL) algorithm. Given that agents require confidential state messages, an output mask scheme is delicately synthesized to ensure that other agents cannot identify the true state message, potentially adding to the sophistication of the containment control process of MAS. Then, an adaptive prescribed-time fuzzy optimal containment control strategy is developed that counts on the masked state of neighboring agents. In addition, an auxiliary error via the shifting function is incorporated into the nonlinear mapping function to manage error constraints, not only avoiding the feasibility criteria but also realizing the unified control. Notably, an emerging intermediate variable is executed to tackle the issue of unknown control gains acting on the RL-based recursive design procedure. Moreover, the drawback of semiglobal boundedness of the error surface induced by dynamic surface control can be avoided with the aid of the novel Lyapunov-like energy candidate. With the assistance of the practical prescribed-time stability, it can be guaranteed that the original state value of each agent remains undisclosed, and the output of the followers can be centered on a convex hull made up of leaders within a prescribed time. Herein, the efficacy of the suggested tactic is exemplified through two illustrative examples.

Unsupervised domain adaptation for remote sensing image semantic segmentation aims to train a deep model on the labeled source domain and apply it to the unlabeled target domain. However, resolution and scene inconsistencies of cross-domain remote sensing images lead to great distribution differences, which weakens the semantic segmentation effect. To solve the above issues, an unsupervised remote sensing image semantic segmentation method is proposed based on multi-scale contrastive domain adaptation. Firstly, the mean teacher model is introduced into the unsupervised domain adaptation paradigm to generate pseudo-labels for target domain data, thereby achieving the cross-domain segmentation capability. A dynamic class balance sampling method is proposed to mitigate the class imbalance problem in cross-domain data by increasing the sampling frequency of the categories with fewer samples. Then, a data augmentation method called cross-domain mixup is developed to reduce the gap between the source and target domains. Finally, a multi-scale cross-domain contrastive loss is developed, which introduces the contrastive learning to learn domain-consistent features across the source and target domains, resulting in a more coherent and discriminative feature representation. Experimental results show that the proposed method can yield superior performance for unsupervised remote sensing image semantic segmentation.

The problem of predefined-time cooperative formation control for multiple unmanned surface vehicles with sensor faults and universal global performance constraints is investigated in this paper. Initially, a generic performance constraint strategy is proposed by integrating an improved global performance function, which eliminates the subpar reconfigurability present in the specific performance function-based global constraint schemes. By embedding the saturation compensation function, a feedback mechanism between the saturation constraint and performance constraint is established, instead of cutting off the analysis separately, by giving the constraint boundaries the flexibility to expand and contract. Subsequently, the inherently unmodeled dynamics and uncertainties of the controlled vehicle are reconstructed online by interval type-2 fuzzy logic systems. By integrating the predefined-time differentiator into the recursive design framework, an adaptive fuzzy predefined-time formation protocol is developed to provide a streamlined solution for adjusting the settling time and facilitates engineering implementation. The stability analysis rigorously proves that all the variables are practical predefined-time bounded. The illustrative results verify the feasibility and functionality of the developed formation control strategy.

This article investigates a novel neural adaptive boundary control strategy for a class of switched partial differential equation (PDE) systems with persistent dwell-time (PDT) switching rules. First, a PDT switching regularity-based PDE is proposed to model systems with fast and slow switching characteristics and time-space evolutionary properties, which can overcome spatiotemporal dynamics’ switching frequency constraint. Furthermore, to eliminate the negative effects of unknown uncertainties on the system stability, a neural adaptive boundary control scheme is developed by using radial basis function neural networks. Next, through the use of mode-dependent multiple Lyapunov functions and with the help of integrating by parts, iteration, and geometric progression methods, sufficient conditions can be derived to guarantee the exponential input-to-state stability of closed-loop switched PDE systems. Finally, a practical example concerning the temperature control of semiconductor power chips is carried out to demonstrate the validity of the obtained results.

The building change detection (BCD) task serves urban planning by monitoring land use. However, due to the complexity of remote-sensing images and high foreground–background similarity, it leads to inaccurate detection of building edge regions. Existing methods deal with this problem by fusing features of different layers. But the fusing operation cannot separate details information from the overall information of buildings, resulting in inaccurate detection of building edge area. To address the above challenges, we propose an iterative edge-enhancing framework (IEEF). The IEEF alleviates the building edge detection difficulty by densely implementing a detail semantic enhancement module (DSEM) in the decoding part. This module takes differential features between adjacent scales to explicitly represent the building edge information. Simultaneously, to deal with the class imbalance problem, a Density-Guided Sampling method dedicated to change detection is proposed to increase the proportion of positive samples during training. Our proposed method achieves state-of-the-art performance on the LEarning, VIsion and Remote sensing laboratory building Change Detection (LEVIR-CD) dataset and the Wuhan University (WHU) dataset and obtains accurate changed building edges.

Online 3D Bin Packing Problem (3D-BPP) has a wide range of industrial applications and there is an emerging research interest in learning optimal bin packing policy and deploying it for real logistics applications. From the heuristic methods to the deep reinforcement learning (DRL) methods, the previous works have proposed many solutions to solve the online 3D-BPP. However, none of them have studied what and how heuristics can be modelled into DRL to build a more effective and practical bin packing pipeline. In this work, we thoroughly investigate what heuristics can be used in online 3D-BPP and how to effectively integrate the heuristics with the DRL. First, we design 3 different heuristics based on the physical rules of the real world and the experiences of the human packers, including the Physics-Heuristics, the Packing-Heuristics and the Unpacking-Heuristics. Second, we model the 3 types of heuristics into the DRL framework and propose a novel heuristic DRL method to solve the online 3D-BPP. Extensive experimental results show that our method achieves state-of-the-art bin packing performance and the resulting real-world system is able to reliably finish the bin packing task in real logistics scenarios. Supplementary video is available athttps://www.youtube.com/watch?v=x8GpmEELq18. Note to Practitioners—The rapid growth of e-commerce has significantly increased the burden of human packers in logistic warehouses, where the workers need to pick the products from a conveyor and pack them into bins (i.e. the online 3D bin packing). Thus it is of great importance to develop intelligent robotic systems to replace human labor, which is a long-standing topic in the field of control and automation science. This paper makes a substantial contribution to the related field by studying the online 3D bin packing in terms of both the theory and practice. On the one hand, the simulated experiments suggest that the presented algorithm significantly improves the space utilization of bin packing. On the other hand, the robotic system developed based on the proposed method can favourably finish the bin packing task in real logistics scenarios, demonstrating the practical use of our approach. Consequently, the approach proposed in this paper is totally applicable in logistic warehouses and is promising to drastically improve the working efficiency of the product packing in real warehouses. In the future, we will extend the presented approach to pack irregular-shaped objects and then facilitate more logistics applications.

This study focuses on the dynamic event-triggered synchronization of semi-Markov jump complex dynamical networks with multi-time delay. First, compared to traditional complex dynamical network models, the introduction of semi-Markovian switching topologies and conic-type nonlinearity makes network models more general and practical. Then, a dynamic event-triggered controller based on non-uniform sampling is designed, which greatly saves the limited network communication resources. Moreover, by using some advanced inequality techniques and the two-sided looped-functional approach, a less conservative synchronization condition is established, which ensures the stochastic stability of the constructed error system while achieving a prescribed dissipative performance. Finally, two simulation examples are provided to demonstrate the effectiveness, practicality, and superiority of the theoretical results.

Semantic segmentation is a significant task for remote sensing interpretation, which takes advantage of contextual semantic information to classify each pixel into a specific category. Most current methods apply convolutional neural networks (CNN) to learn feature representation from remote sensing images, which may ignore the global dependencies due to the limitation of convolutional kernels. Inspired by the global feature learning ability of Transformer, we propose a novel deep model called dual-path feature aware network (DPFANet), which combines the structure of CNN and Transformer for semantic segmentation of remote sensing images. DPFANet aims to learn effective modeling ability from local to global features of images. Simultaneously, an adaptive feature fusion network is developed to fuse features from dual-path networks. Moreover, an edge optimization block is applied to constrain the edge features, whose purpose is to obtain more representative features for segmentation. Experimental results on three public remote sensing datasets verify that our proposed network yields better segmentation performance compared to other related methods.

Unlike the traditional studies on multiagent systems (MASs), this article investigates a class of MASs with spatial properties, whose agents are modeled by partial differential equations (PDE), in addition, to make the model more comprehensive, the Markovian switching topology with partially unknown probability is taken into account. The purpose of this article is to achieve the bipartite consensus for the above PDE-based MASs. In fact, the consideration of spatial factors in MASs will exacerbate the network transmission pressure, to overcome this problem, a novel spatiotemporal event-triggered mechanism is developed. Compared with the existing event-triggered mechanism, the proposed one is not only time-dependent but also covers the influence of spatial variables on the trigger conditions, which helps to further reduce the triggering frequency. Finally, three examples are given to verify the validity of the conclusion we proposed.

This article focuses on the switching event-triggered predefined-time fuzzy optimal control for full-state constrained nonlinear systems based on reinforcement learning (RL) algorithms. To fulfill the asymmetric full-state time-varying constraints (AFTCs), an emerging universal transformed function and error transformation were delicately adopted because they assist in eliminating the feasibility requirement induced by the related constrained issues. Additionally, an RL-based optimal dynamic surface control solution was performed by leveraging the characteristics of predefined-time stability. The highlights of this study are that a modified non-singular predefined-time filter featuring the hyperbolic tangent item and an adaptive parameter was constructed to overcome the curse of dimensionality and that the AFTC property was integrated into the optimal framework. Moreover, communication costs and control expenses were considerably minimized using an amended switching event-triggered mechanism. Under the predefined-time stability criterion, the reported control tactic ensures that the tracking error can approach the vicinity of the origin within a user-specified time while excluding the violation of the AFTC. Herein, two illustrative analyses with comparisons are provided to confirm the efficacy and benefits of the reported control algorithm.

Stepped frequency continuous wave (SFCW) ground penetrating radar (GPR) is a geophysical method to detect the structure and characteristics of underground burial targets by using high-frequency electromagnetic waves. In this article, in order to reconstruct the 3-D structure of underground objects with complex structures, we design a reconfigurable multistate GPR (RM-GPR) and propose a pipelined 3-D back-projection (BP) algorithm. The system generates range profiles by using the phase of the echoes, which can effectively avoid the decline in resolution caused by the attenuation of the high-frequency part. Then, we improve the BP imaging algorithm into 3-D space and improve the computational efficiency of the algorithm by limiting the single imaging area and embedding a part of the calculation process into the signal acquisition process. Compared with the classical GPR system, the unique aspect of the RM-GPR system includes lower complexity for hardware components and lower uncertainty, higher clarity, and less calculation cost for pipelined 3-D BP imaging algorithm, which helps people have an intuitive understanding of unknown targets underground.

A state estimator based on a time-space sampled-data mechanism is proposed for reaction-diffusion neural networks with uncertain parameters over a rectangular domain$\Omega $. The specific sampling strategy is to establish a coordinate system for the two-dimensional space, divide the two coordinate axis into finite sampling intervals, and then take the midpoints of the respective sampling intervals as the coordinates of the sampling points. The objective is to further reduce the burden of communication by decreasing the number of spatial sampling points while maintaining satisfactory estimation performance. Sufficient conditions for the error system’s stability and the convergence region of quasi-estimation are derived by the Lyapunov function method and the improved Halanay’s inequality. Three numerical examples illustrate the validity and advantage of the proposed method.

This article develops a novel state observer for delayed reaction–diffusion neural networks by utilizing incomplete measurements. To reduce the transmission cost efficiently, the space domain is divided into$L$parts and only partial information needs to be measured in every subdomain, such as a point in one-dimensional space, a line and a plane in two- and three-dimensional space, respectively. In addition, the time domain is divided: the measured output signals are transmitted intermittently. Then, new conditions that assure the asymptotic stability of observation error system are derived based on the Lyapunov direct method and several inequality techniques. Finally, the proposed approach’s effectiveness is demonstrated via three numerical examples.

This work investigates the problems of decentralized fault estimation within a finite-time interval (FTI) and fault-tolerant control for nonlinear interconnected distributed parameter systems under the situation of unpredictable faults. First, the fault estimator using interconnected information is designed to estimate the occurred faults over an FTI. Second, the designed fault-tolerant controller has a non-fragile characteristic and can make the considered system satisfy the prescribed performance index. Additionally, this article considers a real scenario where multiple switching channels exist in the network and supposes that the channel switching follows a Markovian switching law with discrete state. Furthermore, by establishing a global Lyapunov functional based on graph theory and employing the canonical Bessel–Legendre inequality method, the final results that are less conservative can be obtained reasonably. Finally, the feasibility, practicability and superiority of the main results are illustrated through three simulations.

In this paper, state observation of coupled reaction-diffusion genetic regulatory networks (GRNs) with time-varying delays is investigated under Dirichlet boundary conditions. First, the above GRNs are constructed to model gene regulatory properties, where the feedback regulation function of the GRNs is assumed to exhibit the Hill form and a novel method to deal with it is introduced. Then a time-space sampled-data state observer is designed for the mentioned networks and new criteria are established by utilizing the Lyapunov stability theory and the inequality techniques of Halanay et al. Finally, the validity of the theoretical results is proved by numerical examples.

This article presents a novel reliable fuzzy output feedback controller for a class of semilinear parabolic partial differential equation systems with Markov jump actuator failures. First, the control strategy's novelties include the following aspects: 1) the considered system is represented by using a fuzzy modeling approach, based on which a new asynchronous fuzzy observer is constructed via utilizing a series of discrete output signals that are induced by samplers and quantizers; 2) a novel Markov jump input model, which is more fit for real applications, is introduced to depict various stochastically occurring actuator faults; and 3) inspired by the above discussion, a reliable mode-dependent fuzzy piecewise control strategy, which only needs limited actuators, is developed. Then, some new conditions, which can ensure that the closed-loop system is finite-time bounded, are established. Furthermore, some slave matrices are introduced to relax the strict constraints caused by asynchronous membership functions. Finally, two simulation examples are provided to support the validity of the proposed method.

This article investigates a spatial-$\mathcal {L}^{\infty }$-norm-based reliable bounded control problem for a class of nonlinear partial differential equation systems in a finite-time interval. The main novelties are reflected in the following aspects: 1) inspired by the sector-nonlinearity approach, the considered nonlinear system is reconstructed by a Takagi–Sugeno fuzzy model, which provides an effective method for control design. Besides, several actuator failures, such as stuck faulty, outage faulty, and bias faulty, are taken into account and modeled by a novel Markov process; 2) partial areas’ states are sampled and transmitted based on a new distributed event-triggered communication strategy, which reduces the cost of the system design and saves the limited network resources to some extent; and 3) on the basis of the first two works, a new piecewise fuzzy controller, which requires fewer actuators compared with the distributed control method, is constructed. Then, some sufficient conditions to guarantee the finite-time boundedness (in the sense of spatial$\mathcal {L}^{\infty }$norm) and mixed$\mathcal {L}_{2}-\mathcal {L}_{\infty }/\mathcal {H}_{\infty }$disturbance attenuation performance are established, and a new linear matrix inequality relax technique is introduced to deal with the strict constraint that is caused by the asynchronous phenomenon between plant and controller. Finally, two simulation studies are given to illustrate the effectiveness and advantages of the developed controller.

This article investigates the event-triggered adaptive fuzzy fixed-time secure control problem for a class of nonlinear cyber-physical systems subject to unknown deception attacks and backlashlike hysteresis. Based on an improved fractional-order command filtered backstepping method, fuzzy approximation technique, and Nussbaum gain technique, a novel adaptive practical fixed-time secure control scheme is proposed. Theoretical analyses prove that the fixed-time stability of the resulting control system and boundedness of all signals in the closed-loop system can be guaranteed by using the presented resilient controller. Especially, the given convergence time is independent of the initial states of the system and better system performance consisting of higher control accuracy and faster convergence rate can be ensured. Finally, a chemical reaction system is carried out to show the validity and superiority of the developed secure control scheme.

This study focuses on the security control problem of networked fuzzy partial differential equation (PDE) systems under hybrid cyber attacks. First, the nonlinear parabolic PDE system is exactly represented by a Takagi–Sugeno fuzzy PDE model. Second, with taking the insecure transmission network into consideration, a more practical stochastic hybrid cyber attacks model for PDE-based networked control systems is introduced. This model contains both denial-of-service attacks and deception attacks in a unified framework. Then, based on spatially pointwise nonuniform sampled-data measurements, an adaptive event-triggered control scheme with an adjustable threshold is newly designed to counter the hybrid cyber attacks’ impact while saving communication resources. Moreover, by constructing a novel Lyapunov–Krasovskii functional and employing some inequality techniques, stability conditions with less conservatism are derived. Finally, the developed method is applied to the Fisher equation to demonstrate its viability and superiority.

This article presents a new sampled-data-based event-triggered pointwise security controller by pointwise measurements for partial differential equation (PDE) systems under stochastic cyberattacks. First, according to the Takagi–Sugeno fuzzy model, the considered nonlinear system is reconstructed and an event-triggered pointwise fuzzy controller is proposed with pointwise measurements. Moreover, networked control systems are introduced to improve the transmission convenience; however, two deception cyberattacks with different characteristics are brought into PDE systems for the first time. In addition, based on novel Lyapunov–Krasovskii functionals, some relaxed conditions to assure system’s exponential stability are established. Finally, the effectiveness and practicability of the designed controller are demonstrated by numerical and application examples.

In this article, an event-triggered control problem for partial differential equation systems with pointwise measurements is investigated via relaxed Lyapunov–Krasovskii functionals. First, the Takagi–Sugeno fuzzy model is introduced to describe the nonlinear systems and a fuzzy event-triggered pointwise controller is proposed with pointwise measurements, which can make a tradeoff between the system’s performance and implementation complexity subject to limited transmission bandwidth. Second, some relaxed conditions are established to ensure the closed-loop system’s stability by using the Lyapunov method and inequality techniques. Finally, two simulation examples are provided to demonstrate the effectiveness and practicability of the designed controller.

For the considered reaction-diffusion inertial memristive neural networks (IMNNs), this article proposes a novel gain-scheduled generalized pinning control scheme, where three pinning control strategies are involved and$2^{n}$controller gains can be scheduled for different system parameters. Moreover, a time delay is considered in the controller to make it has a memory function. With the designed controller, drive-and-response systems can be synchronized within a finite-time interval. Note that the final finite-time synchronization criterion is obtained in the forms of linear matrix inequalities (LMIs) by introducing a memristor-dependent sign function into the controller and constructing a new Lyapunov–Krasovskii functional (LKF). Furthermore, by utilizing some improved integral inequality methods, the conservatism of the main results can be greatly reduced. Finally, three numerical examples are provided to illustrate the feasibility, superiority, and practicability of this article.

This article considers neural network (NN)-based adaptive finite-time resilient control problem for a class of nonlinear time-delay systems with unknown fault data injection attacks and actuator faults. In the procedure of recursive design, a coordinate transformation and a modified fractional-order command-filtered (FOCF) backstepping technique are incorporated to handle the unknown false data injection attacks and overcome the issue of "explosion of complexity" caused by repeatedly taking derivatives for virtual control laws. The theoretical analysis proves that the developed resilient controller can guarantee the finite-time stability of the closed-loop system (CLS) and the stabilization errors converge to an adjustable neighborhood of zero. The foremost contributions of this work include: 1) by means of a modified FOCF technique, the adaptive resilient control problem of more general nonlinear time-delay systems with unknown cyberattacks and actuator faults is first considered; 2) different from most of the existing results, the commonly used assumptions on the sign of attack weight and prior knowledge of actuator faults are fully removed in this article. Finally, two simulation examples are given to demonstrate the effectiveness of the developed control scheme.

This article studies the adaptive finite-time quantized tracking control problem for a class of full state-constrained nonlinear systems with unknown control directions based on a modified fractional-order dynamic surface control (FODSC) technique. First, fractional calculus is introduced to filter design to avoid the issue of the “explosion of complexity” exposed in the traditional backstepping technique. To facilitate the control design, barrier Lyapunov functions and Nussbaum gain technique are utilized to handle full state-constrained problem and the unknown control directions, respectively. In addition, the fuzzy logic systems are employed to approximate the unknown nonlinearity of the system. By integrating with the approximation errors and compensating signals, a composite adaptive quantized controllers is designed to guarantee all the signals of the closed-loop systems are bounded and tracking error converges to an arbitrarily small neighborhood of the zero within a finite time. Finally, a mechanical horizontal platform model and a Brusselator model are carried out to verify the effectiveness of the presented control method.

Product packing is a typical application in ware-house automation that aims to pick objects from unstructured piles and place them into bins with optimized placing policy. However, it still remains a significant challenge to finish the product packing tasks in general logistics scenarios where the objects are variable-sized and the configurations are complex. In this work, we present the PackerBot, a complete robotic pipeline for performing variable-sized product packing in unstructured scenes. First, by leveraging the imperfect experience of human packer, we propose a heuristic DRL framework for learning optimal online 3D bin packing policy. Then we integrate it with a 6-DoF suction-based picking module and a product size estimation module, leading to a complete product packing system, namely the PackerBot. Extensive experimental results show that our method achieves the state-of-the-art performance in both simulated and real-world tests. The video demonstration is available at: https://vsislab.github.io/packerbot.

In this paper, a novel class of quaternion-valued memristive neural networks (QVMNNs) that considers both the spatial factor and Markov jump phenomenon is proposed, the finite/fixed-time anti-synchronization (F/FTAS) of which is investigated. It is worth mentioning that the considered master and slave systems are assumed to jump along two inconsistent Markov chains, which is a first attempt at the issue of the anti-synchronization of Markovian systems and may be more realistic than most existing Markovian systems' models. Then, a suitable feedback controller is designed, such that the error system can be finite/fixed-time stable. Moreover, by integrating algebraic inequality technologies and Lyapunov theory, a new F/FTAS theorem can be obtained for the proposed systems. Finally, this paper provides two examples, so that the rationality, superiority, and practical value of the main results can be illustrated.

A novel state estimator is designed for genetic regulatory networks with reaction-diffusion terms in this study. First, the diffusion space (where mRNA and protein exist) is divided into several parts and only a point, a line, or a plane, etc., is measured in every subspace to reduce the measurement cost effectively. Then, samplers and network-induced time delay are considered to meet the network transmission requirement. A new criterion to ensure that the estimation error converges to zero is established by using the Lyapunov functional combined with Wirtinger's inequality, reciprocally convex approach, and Halanay's inequality; furthermore, the estimator's parameters are derived by solving linear matrix inequalities. Finally, two simulation examples (including one-dimensional and two-dimensional spaces) are presented to demonstrate the developed scheme's applicability.

This article investigates the adaptive output feedback resilient control problem for a class of incommensurate fractional-order (FO) nonlinear systems in the presence of time-varying delays and actuator faults by combining with an adaptive backstepping technique and a modified FO dynamic surface control (FODSC) method. Considering that the information of system states is not fully available, a hybrid fuzzy observer is designed to estimate the unmeasurable system states, where the neuro-fuzzy network system is introduced to handle the unknown nonlinear functions existing in the system. Furthermore, in order to overcome the problem of the explosion of complexity caused by traditional backstepping design procedure, an FO filter is constructed to pass the virtual control signal based on the FODSC scheme. Moreover, according to an indirect Lyapunov stability method, an adaptive hybrid fuzzy output feedback controller is designed to guarantee that all the signals of the closed-loop systems are bounded. Finally, three examples are given to verify the validity and superiority of the presented control scheme.

An innovative class of drive-response systems that are composed of Markovian reaction-diffusion memristive neural networks, where the drive and response systems follow inconsistent Markov chains, is proposed in this article. For this kind of nonlinear parameter-varying systems, a suitable gain-scheduled controller that involves a mode and memristor-dependent item is designed, so that the error system is bounded within a finite-time interval. Moreover, by constructing a novel Lyapunov-Krasovskii functional and employing the canonical Bessel-Legendre inequality and free-weighting matrix method, the conservatism of the finite-time synchronization criterion can be greatly reduced. Finally, two numerical examples are provided to illustrate the feasibility and practicability of the obtained results.

A novel generalized neural network (NN), which includes Markovian jump parameters, inertial items, and reaction-diffusion terms, is proposed, and the issue of finite-time dissipative synchronization for this kind of NNs is discussed in this article. First, an appropriate variable substitution is employed so that the original second-order differential system is transformed into a first-order one. Second, a novel time-varying memory-based controller is designed to ensure the dissipative synchronization of the drive and response systems over a finite-time interval. Then, a new Lyapunov-Krasovskii function is processed by reciprocally convex combination and free-weighting matrix methods, therefore, a less conservative synchronization criterion is derived. Finally, by providing three examples, the feasibility, superiority, and practicality of the obtained results are illustrated.

This article studies the adaptive backstepping control problem for a class of fractional-order (FO) nonlinear systems subject to input quantization and unknown control directions by combining with an indirect FO Lyapunov stability method, and a command filter-based FO dynamic surface control (FODSC) technique. First, a modified FODSC method is utilized to reduce the computational complexity existing in the conventional recursive procedure in which an FO command filter is designed to obtain the command signals and their FO derivatives. Furthermore, the Nussbaum function and neuro-fuzzy networks (NFNs) are adopted to deal with the problem of the unknown control directions and unknown nonlinear functions existing in the system. Moreover, by introducing the compensation and prediction mechanism to controller design, the adaptive controllers, and adaptive laws are constructed to ensure that all the signals of the controlled systems are bounded. Finally, two examples are given to show the validity of the developed control method.

This article investigates the issue of neuro-fuzzy-based adaptive dynamic surface control (DSC) for uncertain fractional-order (FO) nonlinear systems in strict-feedback form where input constraint is considered in the systems. In the recursive steps, the neuro-fuzzy network systems are employed to deal with the unknown nonlinear terms existing in systems. Furthermore, based on a DSC scheme, a modified FO filter is constructed to overcome the problem of explosion of complexity caused by the traditional backstepping design. Moreover, according to the FO Lyapunov stability theory, a neuro-fuzzy-based adaptive controller is designed to guarantee all the signals of FO closed-loop systems tend to be bounded. Finally, the three examples are provided to verify the validity and superiority of the presented control scheme.

This article focuses on the asynchronous output-feedback control design for a class of nonlinear Markov jump distributed parameter systems based on a hidden Markov model. Initially, the considered systems are represented by a Takagi-Sugeno fuzzy model via a sector nonlinearity approach. Furthermore, asynchronous quantizers are introduced to save the limited communication resource in engineering applications. Then, based on the Lyapunov direct method and some inequality techniques, a series of novel stability criteria, which guarantee the finite-time boundedness and H∞disturbance attenuation performance of the target plants, is established in the form of spatial differential linear matrix inequalities. Finally, a simulation study is provided to verify the viability of the developed approach.

A fractional-order integral fuzzy sliding mode control scheme is proposed for a class of uncertain fractional order nonlinear systems subject to uncertainties and external disturbances. First, in each step, a neuro-fuzzy network system is developed to approximate the uncertain nonlinear function existing in fractional-subsystem and a fractional sliding mode surface is presented. Second, based on the fractional Lyapunov stability theory and the finite-time stability theory, a fractional adaptive backstepping neuro-fuzzy sliding mode controller is designed to drive the state trajectories of fractional-order systems to the prescribed sliding mode surface. Meanwhile, the finite-time stability of the fractional-order closed-loop system is proved. At last, three numerical examples are given to illustrate the effectiveness of the proposed control method.