Supervise-Assisted Self-Supervised Deep-Learning Method for Hyperspectral Image Restoration.

Hyperspectral image (HSI) restoration is a challenging research area, covering a variety of inverse problems. Previous works have shown the great success of deep learning in HSI restoration. However, facing the problem of distribution gaps between training HSIs and target HSI, those data-driven methods falter in delivering satisfactory outcomes for the target HSIs. In addition, the degradation process of HSIs is usually disturbed by noise, which is not well taken into account in existing restoration methods. The existence of noise further exacerbates the dissimilarities within the data, rendering it challenging to attain desirable results without an appropriate learning approach. To track these issues, in this article, we propose a supervise-assisted self-supervised deep-learning method to restore noisy degraded HSIs. Initially, we facilitate the restoration network to acquire a generalized prior through supervised learning from extensive training datasets. Then, the self-supervised learning stage is employed and utilizes the specific prior of the target HSI. Particularly, to restore clean HSIs during the self-supervised learning stage from noisy degraded HSIs, we introduce a noise-adaptive loss function that leverages inner statistics of noisy degraded HSIs for restoration. The proposed noise-adaptive loss consists of Stein's unbiased risk estimator (SURE) and total variation (TV) regularizer and fine-tunes the network with the presence of noise. We demonstrate through experiments on different HSI tasks, including denoising, compressive sensing, super-resolution, and inpainting, that our method outperforms state-of-the-art methods on benchmarks under quantitative metrics and visual quality. The code is available at https://github.com/ying-fu/SSDL-HSI.

Intelligent Sensing, Control and Optimization of Networks.

The development of many modern critical infrastructures calls for the integration of advanced technologies and algorithms to enhance the performance, efficiency, and reliability of network systems [...].

Distributed Discrete-Time Convex Optimization With Closed Convex Set Constraints: Linearly Convergent Algorithm Design.

The convergence rate and applicability to directed graphs with interaction topologies are two important features for practical applications of distributed optimization algorithms. In this article, a new kind of fast distributed discrete-time algorithms is developed for solving convex optimization problems with closed convex set constraints over directed interaction networks. Under the gradient tracking framework, two distributed algorithms are, respectively, designed over balanced and unbalanced graphs, where momentum terms and two time-scales are involved. Furthermore, it is demonstrated that the designed distributed algorithms attain linear speedup convergence rates provided that the momentum coefficients and the step size are appropriately selected. Finally, numerical simulations verify the effectiveness and the global accelerated effect of the designed algorithms.

Robust Collision-Avoidance Formation Navigation of Velocity and Input-Constrained Multirobot Systems.

In this work, we consider the safe deployment problem of multiple robots in an obstacle-rich complex environment. When a team of velocity and input-constrained robots is required to move from one area to another, a robust collision-avoidance formation navigation method is needed to achieve safe transferring. The constrained dynamics and the external disturbances make the safe formation navigation a challenging problem. A novel robust control barrier function-based method is proposed which enables collision avoidance under globally bounded control input. First, a nominal velocity and input-constrained formation navigation controller is designed which uses only the relative position information based on a predefined-time convergent observer. Then, new robust safety barrier conditions are derived for collision avoidance. Finally, a local quadratic optimization problem-based safe formation navigation controller is proposed for each robot. Simulation examples and comparison with existing results are provided to demonstrate the effectiveness of the proposed controller.

Graph Soft Actor-Critic Reinforcement Learning for Large-Scale Distributed Multirobot Coordination.

Learning distributed cooperative policies for large-scale multirobot systems remains a challenging task in the multiagent reinforcement learning (MARL) context. In this work, we model the interactions among the robots as a graph and propose a novel off-policy actor-critic MARL algorithm to train distributed coordination policies on the graph by leveraging the ability of information extraction of graph neural networks (GNNs). First, a new type of Gaussian policy parameterized by the GNNs is designed for distributed decision-making in continuous action spaces. Second, a scalable centralized value function network is designed based on a novel GNN-based value function decomposition technique. Then, based on the designed actor and the critic networks, a GNN-based MARL algorithm named graph soft actor-critic (G-SAC) is proposed and utilized to train the distributed policies in an effective and centralized fashion. Finally, two custom multirobot coordination environments are built, under which the simulation results are performed to empirically demonstrate both the sample efficiency and the scalability of G-SAC as well as the strong zero-shot generalization ability of the trained policy in large-scale multirobot coordination problems.

Two Novel Noise-Suppression Projection Neural Networks With Fixed-Time Convergence for Variational Inequalities and Applications.

This article proposes two novel projection neural networks (PNNs) with fixed-time ( FIXt ) convergence to deal with variational inequality problems (VIPs). The remarkable features of the proposed PNNs are FIXt convergence and more accurate upper bounds for arbitrary initial conditions. The robustness of the proposed PNNs under bounded noises is further studied. In addition, the proposed PNNs are applied to deal with absolute value equations (AVEs), noncooperative games, and sparse signal reconstruction problems (SSRPs). The upper bounds of the settling time for the proposed PNNs are tighter than the bounds in the existing neural networks. The effectiveness and advantages of the proposed PNNs are confirmed by numerical examples.

Sparse Actuator Attack Detection and Identification: A Data-Driven Approach.

This article aims to investigate the data-driven attack detection and identification problem for cyber-physical systems under sparse actuator attacks, by developing tools from subspace identification and compressive sensing theories. First, two sparse actuator attack models (additive and multiplicative) are formulated and the definitions of I/O sequence and data models are presented. Then, the attack detector is designed by identifying the stable kernel representation of cyber-physical systems, followed by the security analysis of data-driven attack detection. Moreover, two sparse recovery-based attack identification policies are proposed, with respect to sparse additive and multiplicative actuator attack models. These attack identification policies are realized by the convex optimization methods. Furthermore, the identifiability conditions of the presented identification algorithms are analyzed to evaluate the vulnerability of cyber-physical systems. Finally, the proposed methods are verified by the simulations on a flight vehicle system.

Distributed Multiagent Reinforcement Learning With Action Networks for Dynamic Economic Dispatch.

A new class of distributed multiagent reinforcement learning (MARL) algorithm suitable for problems with coupling constraints is proposed in this article to address the dynamic economic dispatch problem (DEDP) in smart grids. Specifically, the assumption made commonly in most existing results on the DEDP that the cost functions are known and/or convex is removed in this article. A distributed projection optimization algorithm is designed for the generation units to find the feasible power outputs satisfying the coupling constraints. By using a quadratic function to approximate the state-action value function of each generation unit, the approximate optimal solution of the original DEDP can be obtained by solving a convex optimization problem. Then, each action network utilizes a neural network (NN) to learn the relationship between the total power demand and the optimal power output of each generation unit, such that the algorithm obtains the generalization ability to predict the optimal power output distribution on an unseen total power demand. Furthermore, an improved experience replay mechanism is introduced into the action networks to improve the stability of the training process. Finally, the effectiveness and robustness of the proposed MARL algorithm are verified by simulation.

Fixed-Time Cooperative Tracking Control for Double-Integrator Multiagent Systems: A Time-Based Generator Approach.

In this article, both the fixed-time distributed consensus tracking and the fixed-time distributed average tracking problems for double-integrator-type multiagent systems with bounded input disturbances are studied. First, a new practical robust fixed-time sliding-mode control method based on the time-based generator is proposed. Second, two fixed-time distributed consensus tracking observers for double-integrator-type multiagent systems are designed to estimate the state disagreement between the leader and the followers under undirected and directed communication, respectively. Third, a fixed-time distributed average tracking observer for double-integrator-type multiagent systems is designed to measure the average value of multiple reference signals under undirected communication. Note that all the proposed observers are constructed with time-based generators and can be trivially extended to that for high-order integrator-type multiagent systems. Furthermore, by combining the proposed fixed-time sliding-mode control method with the information provided by the fixed-time observers, the fixed-time controllers are designed to solve the fixed-time distributed consensus tracking and the distributed average tracking problems. Finally, a few numerical simulations are shown to verify the results.

Practical Output Containment of Heterogeneous Nonlinear Multiagent Systems Under External Disturbances.

The practical output containment problem for heterogeneous nonlinear multiagent systems under external disturbances generated by an exosystem is investigated in this article. It is required that the outputs of followers converge to the predefined convex combination of leaders' outputs. One of the major challenges in solving such a problem lies in dealing with the coupling among different nonlinearities, state dimensions, and system matrices of heterogeneous agents. To overcome the aforementioned challenge, a distributed observer-based control protocol is developed and employed. First, an adaptive state observer for estimating the states of all the leaders is constructed based on the neighboring interactions. Second, two new classes of observers are constructed for each follower exploiting the output information of the follower, in which the adaptive neural networks (NNs)-based approximation is exploited to compensate for the unknown nonlinearity in the followers' dynamics. A practical output containment control protocol is then generated by the proposed observers, where the control parameters are determined by an algorithm including two steps. Furthermore, with the help of the Lyapunov stability theory and the output regulation method, the practical output containment criteria for the considered closed-loop system under the influences of external disturbances are derived on the basis of the presented control protocol. Finally, the derived theoretical results are illustrated by a simulation example.

Asymptotical Neuro-Adaptive Consensus of Multi-Agent Systems With a High Dimensional Leader and Directed Switching Topology.

We study the asymptotical consensus problem for multi-agent systems (MASs) consisting of a high-dimensional leader and multiple followers with unknown nonlinear dynamics under directed switching topology by using a neural network (NN) adaptive control approach. First, we design an observer for each follower to reconstruct the states of the leader. Second, by using the idea of discontinuous control, we design a discontinuous consensus controller together with an NN adaptive law. Finally, by using the average dwell time (ADT) method and the Barbǎlat's lemma, we show that asymptotical neuroadaptive consensus can be achieved in the considered MAS if the ADT is larger than a positive threshold. Moreover, we study the asymptotical neuroadaptive consensus problem for MASs with intermittent topology. Finally, we perform two simulation examples to validate the obtained theoretical results. In contrast to the existing works, the asymptotical neuroadaptive consensus problem for MASs is firstly solved under directed switching topology.

Distributed Nash Equilibrium Seeking in Consistency-Constrained Multicoalition Games.

The distributed Nash equilibrium (NE) seeking problem for multicoalition games has attracted increasing attention in recent years, but the research mainly focuses on the case without agreement demand within coalitions. This article considers a class of networked games among multiple coalitions where each coalition contains multiple agents that cooperate to minimize the sum of their costs, subject to the demand of reaching an agreement on their state values. Furthermore, the underlying network topology among the agents does not need to be balanced. To achieve the goal of NE seeking within such a context, two estimates are constructed for each agent, namely, an estimate of partial derivatives of the cost function and an estimate of global state values, based on which, an iterative state updating law is elaborately designed. Linear convergence of the proposed algorithm is demonstrated. It is shown that the consistency-constrained multicoalition games investigated in this article put the well-studied networked games among individual players and distributed optimization in a unified framework, and the proposed algorithm can easily degenerate into solutions to these problems.

Event-Triggered Distributed Average Tracking Control for Lipschitz-Type Nonlinear Multiagent Systems.

This article investigates the event-triggered distributed average tracking (ETDAT) control problems for the Lipschitz-type nonlinear multiagent systems with bounded time-varying reference signals. By using the state-dependent gain design approach and event-triggered mechanism, two types of ETDAT algorithms called: 1) static and 2) adaptive-gain ETDAT algorithms are developed. It is the first time to introduce the event-triggered strategy into DAT control algorithms and investigate the ETDAT problem for multiagent systems with Lipschitz nonlinearities, which is more practical in real physical systems and can better meet the needs of practical engineering applications. Besides, the adaptive-gain ETDAT algorithms do not need any global information of the network topology and are fully distributed. Finally, a simulation example of the Watts-Strogatz small-world network is presented to illustrate the effectiveness of the adaptive-gain ETDAT algorithms.

Resilient Consensus of Multiagent Systems Under Collusive Attacks on Communication Links.

This article addresses the resilient consensus problem of multiagent systems subject to cyber attacks on communication links, where the attacks on different links may collude to maintain undetectable. For the case with noncollusive attacks on links, a distributed fixed-time observer is designed so that the attack on each link can be detected by the two associated agents. A necessary and sufficient condition is derived to ensure the isolation of attacked links and no mistaken isolation of normal ones. For the case with collusive attacks on links, a novel attack isolation algorithm is proposed by constructing extra observers on the basis of the previous designed distributed fixed-time observer via sequentially removing the information associated with one of the links. Based on the isolation of the attacked links, a control algorithm is designed, and a necessary and sufficient condition is provided to achieve resilient consensus. Numerical examples corroborate the effectiveness of the proposed strategies.

Distributed Formation Navigation of Constrained Second-Order Multiagent Systems With Collision Avoidance and Connectivity Maintenance.

In this article, we consider the distributed formation navigation problem of second-order multiagent systems subject to both velocity and input constraints. Both collision avoidance and connectivity maintenance of the network are considered in the controller design. A control barrier function method is employed to achieve multiple control objectives simultaneously while satisfying the velocity and input constraints. First, a nominal distributed leader-following formation controller is proposed which satisfies the velocity and input constraints uniformly and handles switching communication graphs. A nonsmooth analysis is employed to prove the global convergence of the controller. Then, a topology-based connectivity maintenance strategy using a new notion of the formation-guided minimum cost spanning tree is proposed and the corresponding barrier function-based constraints are derived. The barrier function-based collision-avoidance conditions are also developed. All barrier function-based constraints are then combined to formulate a quadratic programming problem which modifies the nominal controller when necessary to achieve both collision avoidance and connectivity maintenance. Simulation results demonstrate the effectiveness of the proposed control strategy.

Observer-Based Consensus Protocol for Directed Switching Networks With a Leader of Nonzero Inputs.

We aim to address the consensus tracking problem for multiple-input-multiple-output (MIMO) linear networked systems under directed switching topologies, where the leader is subject to some nonzero but norm bounded inputs. First, based on the relative outputs, a full-order unknown input observer (UIO) is designed for each agent to track the full states' error among neighboring agents. With the aid of such an observer, a discontinuous feedback protocol is subtly designed. And it is proven that consensus tracking can be achieved in the closed-loop networked system if the average dwell time (ADT) for switching among different interaction graph candidates is larger than a given positive threshold. By using the boundary layer technique, a continuous feedback protocol is skillfully designed and employed. It is shown that the consensus error converges into a bounded set under the designed continuous protocol. Second, as part of the full states' error can be constructed via the agents' outputs, a reduced-order UIO is thus designed based on which discontinuous and continuous feedback protocols are, respectively, proposed. By using the stability theory of the switched systems, it is proven that the consensus error converges asymptotically to 0 under the designed discontinuous protocol, and converges into a bounded set under the designed continuous protocol. Finally, the obtained theoretical results are validated through simulations.

A Distributed Lyapunov-Based Redesign Approach for Heterogeneous Uncertain Agents With Cooperation-Competition Interactions.

A swarming behavior problem is investigated in this article for heterogeneous uncertain agents with cooperation-competition interactions. In such a problem, the agents are described by second-order continuous systems with different intrinsic nonlinear terms, which satisfies the "linearity-in-parameters" condition, and the agents' models are coupled together through a distributed protocol containing the information of competitive neighbors. Then, for four different types of cooperation-competition networks, a distributed Lyapunov-based redesign approach is proposed for the heterogeneous uncertain agents, where the distributed controller and the estimation laws of unknown parameters are obtained. Under their joint actions, the heterogeneous uncertain multiagent system can achieve distributed stabilization for structurally unbalanced networks and output bipartite consensus for structurally balanced networks. In particular, the concept of coherent networks is proposed for structurally unbalanced directed networks, which is beneficial to the design of distributed controllers. Finally, four illustrative examples are given to show the effectiveness of the designed distributed controller.

Consensus of Linear MIMO Multiagent Systems: Appointed-Time Reduced-Order Observer-Based Protocols.

This article is devoted to designing distributed adaptive attack-free protocols for the consensus of linear multi-input multioutput multiagent systems under directed graphs, where the appointed-time reduced-order observers are proposed based only upon the relative output information among neighboring agents. One of the distinguishing features of the attack-free protocols lies in the prohibition on information transmission via the communication channel. By viewing the relative control input as the unknown input on the dynamics of each agent, a class of new unknown input observers is introduced with only the relative output measurement involved. The appointed-time estimation of the consensus error is achieved by utilizing jump discontinuity in the observer design and employing the property of the nilpotent matrix. Moreover, a linear transformation is made on the system of consensus error to realize the observer order reduction. Both theoretical analysis and simulation illustration are presented to reveal the effectiveness of the proposed attack-free protocols.

Designing Event-Triggered Observers for Distributed Tracking Consensus of Higher-Order Multiagent Systems.

In this article, the asymptotic tracking consensus problem of higher-order multiagent systems (MASs) with general directed communication graphs is addressed via designing event-triggered control strategies. One common assumption utilized in most existing results on such tracking consensus problem that the inherent dynamics of the leader are the same as those of the followers is removed in this article. In particular, two cases that the dynamics of the leader are subjected, respectively, to bounded input and unknown nonlinearity are considered. To do this, distributed event-triggered observers are first constructed to estimate the state information of the leader. Then, local event-triggered tracking control protocols are designed for each follower to complete the goal of tracking consensus. One distinguishing feature of the present distributed observers lies in the fact that they could avoid the continuous monitoring for the states of the neighbors' observer states. It is also worth pointing out that the present tracking consensus control strategies are fully distributed as no global information related to the directed communication graph is involved in designing the strategies. Two simulation examples are finally presented to verify the efficiency of the theoretical results.

Output-Feedback Self-Synchronization of Directed Lur'e Networks via Global Connectivity.

In this article, we generalize the results on self-synchronization of Lur'e networks diffusively interconnected through dynamic relative output-feedback from the undirected graph case in Zhang et al. 2016 to the general directed graph case. A linear dynamic self-synchronization protocol of the same structure is adopted as the one proposed in Zhang et al. 2016. That is, the Lur'e-type nonlinearity is not involved in our self-synchronization protocol. It is in fact unknown and only assumed to be incrementally sector bounded within a given sector. In the absence of a leader Lur'e system defining the synchronization trajectory, we construct a novel self-synchronization manifold in order to derive the self-synchronization error dynamics. Meanwhile, the connectivity of the general directed graph having a directed spanning tree is quantified by the global connectivity, instead of the so-called general algebraic connectivity used in the directed graph case under static relative state feedback. The global connectivity plays a crucial role in handling self-synchronization problems of directed nonlinear networks via dynamic relative output feedback, including directed networks with the Lipschitz nonlinear node dynamics, which is also discussed in this article. The protocol parameter matrix design is performed by solving the obtained LMI conditions in sequence. In addition, some discussions are complemented on the important technical details in our self-synchronization protocol design along with extensions. Finally, our theoretical results are illustrated through numerical simulations over a directed nonlinear dynamical network.