This work proposes a jointly optimized trajectory generation and camera control approach, enabling an autonomous agent, such as an unmanned aerial vehicle (UAV) operating in 3D environments, to plan and execute coverage trajectories that maximally cover the surface area of a 3D object of interest. Specifically, the UAV's kinematic and camera control inputs are jointly optimized over a rolling planning horizon to achieve complete 3D coverage of the object. The proposed controller incorporates ray-tracing into the planning process to simulate the propagation of light rays, thereby determining the visible parts of the object through the UAV's camera. This integration enables the generation of precise look-ahead coverage trajectories. The coverage planning problem is formulated as a rolling finite-horizon optimal control problem and solved using mixed-integer programming techniques. Extensive real-world and synthetic experiments validate the performance of the proposed approach.

Supervised online learning relies on the assumption that ground truth information is available for model updates at each time step.As this is not realistic in every setting, alternatives such as active online learning, or online learning with verification latency have been proposed.In this work, we assume that no label information is available after intitial training.We argue that provided we can characterize the expected concept drift as incremental drift, we can rely on a self-labeling strategy to keep updated models.We derive a k-NN-based self-labeling online learner implementing the presented self-supervised scheme and experimentally show that this is an option for learning from incrementally drifting data streams in the absence of label information.

In the contemporary digital landscape, the continuous generation of extensive streaming data across diverse domains has become pervasive. Yet, a significant portion of this data remains unlabeled, posing a challenge in identifying infrequent events such as anomalies. This challenge is further amplified in non-stationary environments, where the performance of models can degrade over time due to concept drift. To address these challenges, this paper introduces a new method referred to as VAE4AS (Variational Autoencoder for Anomalous Sequences). VAE4AS integrates incremental learning with dual drift detection mechanisms, employing both a statistical test and a distance-based test. The anomaly detection is facilitated by a Variational Autoencoder. To demonstrate the effectiveness of VAE4AS, a comprehensive experimental study is conducted using real-world and synthetic datasets characterized by anomalous rates below 10% and recurrent drift. The results show that the proposed method surpasses both robust baselines and state-of-the-art techniques, providing compelling evidence for their efficacy in effectively addressing some of the challenges associated with anomalous sequence detection in non-stationary streaming data.

Data stream mining aims at extracting meaningful knowledge from continually evolving data streams, addressing the challenges posed by nonstationary environments, particularly, concept drift which refers to a change in the underlying data distribution over time. Graph structures offer a powerful modelling tool to represent complex systems, such as, critical infrastructure systems and social networks. Learning from graph streams becomes a necessity to understand the dynamics of graph structures and to facilitate informed decision-making. This work introduces a novel method for graph stream classification which operates under the general setting where a data generating process produces graphs with varying nodes and edges over time. The method uses incremental learning for continual model adaptation, selecting representative graphs (prototypes) for each class, and creating graph embeddings. Additionally, it incorporates a loss-based concept drift detection mechanism to recalculate graph prototypes when drift is detected.

In the rapidly changing environments of disaster response, planning and decision-making for autonomous agents involve complex and interdependent choices. Although recent advancements have improved traditional artificial intelligence (AI) approaches, they often struggle in such settings, particularly when applied to agents operating outside their well-defined training parameters. To address these challenges, we propose an attention-based cognitive architecture inspired by Dual Process Theory (DPT). This framework integrates, in an online fashion, rapid yet heuristic (human-like) responses (System 1) with the slow but optimized planning capabilities of machine intelligence (System 2). We illustrate how a supervisory controller can dynamically determine in real-time the engagement of either system to optimize mission objectives by assessing their performance across a number of distinct attributes. Evaluated for trajectory planning in dynamic environments, our framework demonstrates that this synergistic integration effectively manages complex tasks by optimizing multiple mission objectives.

Quantized signal-driven control for nonlinear systems is of special interest in practice. However, it is nontrivial in the presence of mismatched uncertainties and intermittent denial of service (DoS) attacks. The underlying problem becomes even more complicated when both the input and output signals are attacked, rendering the state variables and the input signal inaccessible or unavailable for the control design. Only the quantized (and thus nondifferentiable) output signal is available in the absence of attack, making regular backstepping design inapplicable. This article introduces a novel adaptive output feedback control method to tackle the aforementioned challenges. First, we design a gain-switched quantized observer to estimate the unmeasurable state variables. Second, by employing a first-order dynamic filtering technique, we circumvent the nondifferentiability issue of virtual controller arising from the signal quantization. Third, we establish design conditions for the controller parameters. Fourth, we utilize a more comprehensive sector quantizer and develop adaptive estimators to deal with the unknown quantization parameters. Finally, we demonstrate that with the proposed control method, all the closed-loop signals are semiglobally uniformly ultimately bounded (SUUB), and the regulation error can be made small enough by appropriately tuning the design parameters. Numerical simulations confirm the efficacy of the proposed approach.

This article presents a novel dual-phase based approach for distributed event-triggered control of uncertain Euler-Lagrange (EL) multiagent systems (MASs) with guaranteed performance under a directed topology. First, a fully distributed robust filter is designed to estimate the reference signal for each agent with guaranteed observation performance under continuous state feedback, which transforms the distributed event-triggered control problem into a centralized one for multiple single systems. Second, an event-triggered controller is constructed via intermittent state feedback, making the output of each agent follow the corresponding estimated signal with guaranteed tracking performance. The proposed co-design scheme is of relatively low complexity in structure and cheap in computation since a priori knowledge of system nonlinearities or estimation of their bounds is not required in building the control scheme, and yet neither approximating structures nor adaptive online updating algorithms are needed. It is shown that the output tracking error of each agent is ensured to shrink into a prescribed precision set at an arbitrarily assignable convergence rate, although the plant states and the actuation signal are triggered simultaneously. All the internal signals are uniformly bounded and the occurrence of Zeno behavior is precluded. The efficiency of the proposed method is verified via numerical simulation.

Control of a platoon of connected vehicles with nonlinear longitudinal dynamics subject to failure in receiving communicated and radio data is addressed in this paper. We consider a scenario when due to malfunction of communication and radio devices, required data for cooperative adaptive cruise control may be stochastically unavailable. We develop a control scheme such that under certain conditions, the regulation of the intervehicle distances in desired values can be guaranteed. Specifically, we rigorously show that if the probability of receiving the required data for each vehicle is not zero, then under the proposed control strategy, the intervehicle distances almost surely converge to the desired values. Accurate performance of radars is a key assumption in the existing results in the literature on cooperative adaptive cruise control. Hence, the main contribution of this paper is that under the proposed control strategy, the robustness of the platoon against stochastic data loss in both communication network and vehicles radars is guaranteed. Simulation results verify the acceptable performance of the proposed control strategy.

In this article, a distributed learning-based fault accommodation scheme is proposed for a class of nonlinear interconnected systems under event-triggered communication of control and measurement signals. Process faults occurring in the local dynamics and/or propagated from interconnected neighboring subsystems are considered. An event-triggered nominal control law is used for each subsystem before detecting any fault occurrence in its dynamics. After fault detection, the corresponding event-triggered fault accommodation law is utilized to reconfigure the nominal control law with a neural-network-based adaptive learning scheme employed to estimate an ideal fault-tolerant control function online. Under the asynchronous controller reconfiguration mechanism for each subsystem, the closed-loop stability of the interconnected systems in different operating modes with the proposed event-triggered learning-based fault accommodation scheme is rigorously analyzed with the explicit stabilization condition and state upper bound derived in terms of event-triggering parameters, and the Zeno behavior is shown to be excluded. An interconnected inverted pendulum system is used to illustrate the proposed fault accommodation scheme.

In our digital universe nowadays, enormous amount of data are produced in a streaming manner in a variety of application areas. These data are often unlabelled. In this case, identifying infrequent events, such as anomalies, poses a great challenge. This problem becomes even more difficult in non-stationary environments, which can cause deterioration of the predictive performance of a model. To address the above challenges, the paper proposes an autoencoder-based incremen-tal learning method with drift detection (strAEm++DD). Our proposed method strAEm++DD leverages on the advantages of both incremental learning and drift detection. We conduct an experimental study using real-world and synthetic datasets with severe or extreme class imbalance, and provide an empirical analysis of strAEm++DD. We further conduct a comparative study, showing that the proposed method significantly outper-forms existing baseline and advanced methods.

Emergency situations encompassing natural and human-made disasters, as well as their cascading effects, pose serious threats to society at large. Machine learning (ML) algorithms are highly suitable for handling the large volumes of spatiotemporal data that are generated during such situations. Hence, over the years, they have been utilized in emergency management to aid first responders and decision-makers in such situations and ultimately improve disaster prevention, preparedness, response, and recovery. In this survey article, we highlight relevant work in this area by first focusing on the commonalities of emergency management applications and key challenges that ML algorithms need to address. Then, we present a categorization of relevant works across all the emergency management phases and operations, highlighting the main algorithms used. Based on our review, we conclude that ML algorithms can provide the basis for tackling different activities across the emergency management phases with a unified algorithmic framework that can solve a large set of problems. Finally, through the systematic literature review, we provide promising future directions for utilizing ML algorithms more effectively in emergency management applications. More importantly, we identify the need for better generalization of algorithms, improved explainability, and trustworthiness of ML algorithms with respect to the emergency management personnel, as well as more efficient ways of addressing the challenges associated with building appropriate datasets.

In this work, a novel distributed search-planning framework is proposed, where a dynamically varying team of autonomous agents cooperate in order to search multiple objects of interest in three-dimension (3-D). It is assumed that the agents can enter and exit the mission space at any point in time, and as a result the number of agents that actively participate in the mission varies over time. The proposed distributed search-planning framework takes into account the agent dynamical and sensing model, and the dynamically varying number of agents, and utilizes model predictive control (MPC) to generate cooperative search trajectories over a finite rolling planning horizon. This enables the agents to adapt their decisions on-line while considering the plans of their peers, maximizing their search planning performance, and reducing the duplication of work.

Electric vehicle routing problems are challenging variations of the traditional vehicle routing problem which incorporate the possibility of electric vehicle (EV) recharging at any station, while satisfying the delivery demands of customers. This work addresses the recently formulated capacitated vehicle routing problem (E-CVRP) with variable energy consumption rate. In particular, the cargo weight, which is one of the main factors affecting the energy consumption rate of EVs, is considered (i.e., the heavier the EV the higher the rate). As a solution method, an ant colony optimization algorithm with a local search heuristic is developed. Experiments are conducted on a recently generated benchmark set of E-CVRP instances demonstrating that the performance of the proposed technique improves on the best known so far solutions.

In this article, we propose a data-driven iterative learning control (ILC) framework for unknown nonlinear nonaffine repetitive discrete-time single-input-single-output systems by applying the dynamic linearization (DL) technique. The ILC law is constructed based on the equivalent DL expression of an unknown ideal learning controller in the iteration and time domains. The learning control gain vector is adaptively updated by using a Newton-type optimization method. The monotonic convergence on the tracking errors of the controlled plant is theoretically guaranteed with respect to the 2-norm under some conditions. In the proposed ILC framework, existing proportional, integral, and derivative type ILC, and high-order ILC can be considered as special cases. The proposed ILC framework is a pure data-driven ILC, that is, the ILC law is independent of the physical dynamics of the controlled plant, and the learning control gain updating algorithm is formulated using only the measured input-output data of the nonlinear system. The proposed ILC framework is effectively verified by two illustrative examples on a complicated unknown nonlinear system and on a linear time-varying system.

In this article a novel data-driven iterative learning control (ILC) approach is proposed for unknown nonlinear nonaffine repetitive discrete-time systems, where the dynamic linearization (DL) technique in the iteration domain is applied both on the controlled nonlinear system and on the unknown nonlinear ideal learning controller. Through updating the weight matrix of a radial basis function neural network (RBFNN), the learning control gain of the obtained iterative learning law is automatically tuned in reaching the optimal learning controller using only the input-output data of the nonlinear system. The uniformly ultimately bounded property is established for the tracking error of the proposed ILC scheme in the iteration domain through rigorous theoretical analysis. The effectiveness and applicability are validated by a simulation example and further demonstrated by simulation on a high-speed train model.

There is currently a rapid evolution of technologies enabling the “Internet-of-Things” paradigm, which leads to the design of systems with augmented sensing, analysis, and actuation capabilities. The intelligent control research community is beginning to recognize the challenge of designing flexible and adaptable control systems that will take advantage of the online evolution of the number and types of “things” in a large-scale system. Responding to this challenge, in a previous article, we designed and presented a semantically enhanced control system supervisor that integrates a knowledge graph and deductive inference capabilities, to achieve the online (re)configuration of feedback control schemes. In this article, we show that by exploiting the capabilities of this supervisor, we facilitate the automatic synthesis and plugging of model-based controllers for the space heating problem in multizone buildings. The supervisor retrieves stored knowledge about the building and the available control system components and uses it to configure online a scheme of distributed feedback controllers, one per building zone. The controllers are designed to utilize information online and optimally allocate the control signal to multiple heating devices in each building zone.

An enormous and ever-growing volume of data is nowadays becoming available in a sequential fashion in various real-world applications. Learning in nonstationary environments constitutes a major challenge, and this problem becomes orders of magnitude more complex in the presence of class imbalance. We provide new insights into learning from nonstationary and imbalanced data in online learning, a largely unexplored area. We propose the novel Adaptive REBAlancing (AREBA) algorithm that selectively includes in the training set a subset of the majority and minority examples that appeared so far, while at its heart lies an adaptive mechanism to continually maintain the class balance between the selected examples. We compare AREBA with strong baselines and other state-of-the-art algorithms and perform extensive experimental work in scenarios with various class imbalance rates and different concept drift types on both synthetic and real-world data. AREBA significantly outperforms the rest with respect to both learning speed and learning quality. Our code is made publicly available to the scientific community.

This article considers the tracking control of unknown nonlinear nonaffine repetitive discrete-time multi-input multi-output systems. Two data-driven iterative learning control (ILC) schemes are designed based on two equivalent dynamic linearization data models of an unknown ideal learning controller, which exists theoretically in the iteration domain. The two control schemes provide ways of selecting learning controllers based on the complexity of the controlled nonlinear systems. The learning control gain matrixes of the two learning controllers are optimized through the steepest descent method using only the measured input-output data of the nonlinear systems. The proposed ILC approaches are pure data-driven since no model information of the controlled systems is involved. The stability and convergence of the proposed ILC approaches are rigorously analyzed under reasonable conditions. Numerical simulation and an experiment based on a Gantry-type linear motor drive system are conducted to verify the effectiveness of the proposed data-driven ILC approaches.

Severa1 logistic companies started utilizing electric vehicles (EVs) in their daily operations to reduce greenhouse gas pollution. However, the limited driving range of EVs may require visits to recharging stations during their operation. These potential visits have to be addressed, avoiding unnecessary long detours. We formulate the electric capacitated vehicle routing problem (E-CVRP), which incorporates the possibility of EVs visiting a recharging station while satisfying the delivery demands of customers. The energy consumption of the EVs is proportional to their cargo load which is an important constraint in real-world logistics applications. A new set of benchmark instances is proposed for the E-CVRP. As solution methods to these new benchmarks, we apply the ant colony optimization metaheuristic method and an exact method. Experimental results on the ECVRP demonstrate the high complexity of the problem and the efficiency of the applied metaheuristic solution method.

An ever increasing volume of data is nowadays becoming available in a streaming manner in many application areas, such as, in critical infrastructure systems, finance and banking, security and crime and web analytics. To meet this new demand, predictive models need to be built online where learning occurs on-the-fly. Online learning poses important challenges that affect the deployment of online classification systems to real-life problems. In this paper we investigate learning from limited labelled, nonstationary and imbalanced data in online classification. We propose a learning method that synergistically combines siamese neural networks and active learning. The proposed method uses a multi-sliding window approach to store data, and maintains separate and balanced queues for each class. Our study shows that the proposed method is robust to data nonstationarity and imbalance, and significantly outperforms baselines and state-of-the-art algorithms in terms of both learning speed and performance. Importantly, it is effective even when only 1% of the labels of the arriving instances are available.

In this paper, the distributed fault accommodation problem is studied for a class of interconnected nonlinear systems with event-triggered control and inter-subsystem communications. Each subsystem is subject to potential faults resulting from the local dynamics and/or transmitted from neighboring subsystems. The time periods before and after the fault detection in each subsystem are considered and corresponding event-triggered controllers are proposed, where the neural network based adaptive approximation technique is used to estimate the fault effect online. The closed-loop stability of the interconnected system with the proposed event-triggered fault accommodation controllers is rigorously analyzed.

This work investigates the problem of simultaneous tracking and jamming of a rogue drone in 3D space with a team of cooperative unmanned aerial vehicles (UAVs). We propose a decentralized estimation, decision and control framework in which a team of UAVs cooperate in order to a) optimally choose their mobility control actions that result in accurate target tracking and b) select the desired transmit power levels which cause uninterrupted radio jamming and thus ultimately disrupt the operation of the rogue drone. The proposed decision and control framework allows the UAVs to reconfigure themselves in 3D space such that the cooperative simultaneous tracking and jamming (CSTJ) objective is achieved; while at the same time ensures that the unwanted inter-UAV jamming interference caused during CSTJ is kept below a specified critical threshold. Finally, we formulate this problem under challenging conditions i.e., uncertain dynamics, noisy measurements and false alarms. Extensive simulation experiments illustrate the performance of the proposed approach.

In this paper, we investigate the problem of joint searching and tracking of multiple mobile targets by a group of mobile agents. The targets appear and disappear at random times inside a surveillance region and their positions are random and unknown. The agents have limited sensing range and receive noisy measurements from the targets. A decision and control problem arises, where the mode of operation (i.e., search or track) as well as the mobility control action for each agent, at each time instance, must be determined so that the collective goal of searching and tracking is achieved. We build our approach upon the theory of random finite sets (RFS) and we use Bayesian multi-object stochastic filtering to simultaneously estimate the time-varying number of targets and their states from a sequence of noisy measurements. We formulate the above problem as a non-linear binary program (NLBP) and show that it can be approximated by a genetic algorithm. Finally, to study the effectiveness and performance of the proposed approach we have conducted extensive simulation experiments.

This paper focuses on developing a distributed leader-following fault-tolerant tracking control scheme for a class of high-order nonlinear uncertain multiagent systems. Neural network-based adaptive learning algorithms are developed to learn unknown fault functions, guaranteeing the system stability and cooperative tracking even in the presence of multiple simultaneous process and actuator faults in the distributed agents. The time-varying leader's command is only communicated to a small portion of follower agents through directed links, and each follower agent exchanges local measurement information only with its neighbors through a bidirectional but asymmetric topology. Adaptive fault-tolerant algorithms are developed for two cases, i.e., with full-state measurement and with only limited output measurement, respectively. Under certain assumptions, the closed-loop stability and asymptotic leader-follower tracking properties are rigorously established.

In this article, a new deep reinforcement learning (RL) method, called asynchronous advantage actor-critic (A3C) method, is developed to solve the optimal control problem of elevator group control systems (EGCSs). The main contribution of this article is that the optimal control law of EGCSs is designed via a new deep RL method, such that the elevator system sends passengers to the desired destination floors as soon as possible. Deep convolutional and recurrent neural networks, which can update themselves during applications, are designed to dispatch elevators. Then, the structure of the A3C method is developed, and the training phase for the learning optimal law is discussed. Finally, simulation results illustrate that the developed method effectively reduces the average waiting time in a complex building environment. Comparisons with traditional algorithms further verify the effectiveness of the developed method.

Ant colony optimization (ACO) algorithms have proved to be suitable for solving dynamic optimization problems (DOPs). The integration of local search operators with ACO has also proved to significantly improve the output of ACO algorithms. However, almost all previous works of ACO in DOPs do not utilize local search operators. In this work, the MAX-MIN Ant System (MMAS), one of the best ACO variations, is integrated with advanced and effective local search operators, i.e., the Lin-Kernighan and the Unstringing and Stringing heuristics, resulting in powerful memetic algorithms. The best solution constructed by ACO is passed to the operator for local search improvements. The proposed memetic algorithms aim to combine the adaptation capabilities of ACO for DOPs and the superior performance of the local search operators. The travelling salesperson problem is used as the base problem to generate both symmetric and asymmetric dynamic test cases. Experimental results show that the MMAS is able to provide good initial solutions to the local search operators especially in the asymmetric dynamic test cases.

In this work we consider the scheduling problem for charging a fleet of electric vehicles (EVs) within a station such that the total tardiness of the problem is minimized. The generation of a feasible and efficient schedule is a difficult task due to the physical and power constraints of the charging station, i.e., the maximum contracted power and the maximum power imbalance between the lines of the electric feeder. The ant colony optimization (ACO) metaheuristic is applied to coordinate the charging process of the EVs within the charging station by generating efficient schedules. The behaviour and performance of ACO is analyzed and compared against state-of-the-art approaches on a benchmark set inspired by real-world scenarios. The experimental results show that the application of ACO is highly effective and outperforms other approaches.

In today's “smart era” there is a growing ecosystem of Internet of Things (IoT)-enabled devices, which exploit (wireless) Internet connectivity and use standard communication protocols to interact with each other and the environment. As various IoT components are becoming widely available in the marketplace, a key challenge from a feedback control viewpoint is the ability to seamlessly integrate new IoT components or modify existing configurations in feedback control settings without having to halt the operation of the system and redesign the overall feedback control scheme. This paper exploits technologies from the semantic Web domain, for the design of a novel semantically enhanced IoT-enabled intelligent control system (SEMIoTICS) architecture. The proposed SEMIoTICS scheme incorporates a supervisor module able to facilitate the semantic modeling of IoT components and the subsequent online composition/reconfiguration of feedback control loops. We demonstrate the applicability of the SEMIoTICS architecture through illustrative scenarios from the smart buildings domain.

This paper addresses the fault estimation (FE) and accommodation issues of interconnected systems by using two new concepts namely interconnected separation principle and constrained interconnected separation principle that allow for the separate design not only between diagnostic observer and fault tolerant controller for each subsystem, but also between observer/controller of each subsystem and those of other ones. Sufficient fault recoverability conditions are established, under which both distributed and decentralized FE and accommodation schemes are provided. The new results help to provide a framework for observer-based fault diagnosis and fault tolerant control of interconnected systems, and are further applied to the meta aircraft configuration that consists of multiple aircraft joined together to illustrate their efficiency.

In this paper, we investigate a problem associated with transferring a set of containers from the storage to the loading area of a warehouse using autonomous robots. In addition to assigning robots to containers, the special topology considered in this paper requires coordinated planning of the robots' movement to avoid conflicts. We formulate the joint problem of robot assignment and movement coordination with the objective of minimizing the time required for all robots to carry their assigned containers to the destination, subject to conflict-free movement of all robots. We use the concept of abstract time windows (ATWs) to represent the movement of robots. The conditions for detecting conflicts in the ATW representation are introduced along with the necessary operations for resolving conflicts. For the solution of the problem, two approaches are developed. The first is a mathematical programming approach that formulates the problem as a mixed-integer linear program that allows optimal solution using appropriate solvers, while the second is a heuristic approach that allows fast, close-to-optimal solutions. Even though the proposed approaches focus on the case where the number of robots is equal to the number of containers, we also discuss how to solve the problem when having unequal number of robots and containers. Simulation results show that the heuristic approach provides a solution within 5% of the optimal solution with the minimum time of completion of all tasks being the performance metric, and executes six orders of magnitude faster than a state-of-the-art mathematical programming solver.

Networks of smart cameras, equipped with on-board processing and communication infrastructure, are increasingly being deployed in a variety of different application fields, such as security and surveillance, traffic monitoring, industrial monitoring, and critical infrastructure protection. The task(s) that a network of smart cameras executes in these applications, e.g., activity monitoring and object identification, can be severely degraded due to errors in the detection module. However, in most cases, higher level tasks and decision making processes in smart camera networks (SCNs) assume ideal detection capabilities for the cameras, which is often not the case due to the probabilistic nature of the detection process, especially for low-cost cameras with limited capabilities. Realizing that it is necessary to introduce robustness in the decision process, this paper presents results toward uncertainty-aware SCNs. Specifically, we introduce a flexible uncertainty model that can be used to characterize the detection behavior in a camera network. We also show how to utilize the model to formulate detection-aware optimization algorithms that can be used to reconfigure the network in order to improve the overall detection efficiency and thus increase the effective number of detected targets. We evaluate our proposed model and algorithms using a network of Raspberry-Pi-based smart cameras that reconfigure in order to improve the detection performance based on the position of targets in the area. The experimental results in the laboratory as well as in a human monitoring application and extensive simulation results indicate that the proposed solutions are able to improve the robustness and reliability of SCNs.

Recent progress toward the realization of the "Internet of Things" has improved the ability of physical and soft/cyber entities to operate effectively within large-scale, heterogeneous systems. It is important that such capacity be accompanied by feedback control capabilities sufficient to ensure that the overall systems behave according to their specifications and meet their functional objectives. To achieve this, such systems require new architectures that facilitate the online deployment, composition, interoperability, and scalability of control system components. Most current control systems lack scalability and interoperability because their design is based on a fixed configuration of specific components, with knowledge of their individual characteristics only implicitly passed through the design. This paper addresses the need for flexibility when replacing components or installing new components, which might occur when an existing component is upgraded or when a new application requires a new component, without the need to readjust or redesign the overall system. A semantically enhanced feedback control architecture is introduced for a class of systems, aimed at accommodating new components into a closed-loop control framework by exploiting the semantic inference capabilities of an ontology-based knowledge model. This architecture supports continuous operation of the control system, a crucial property for large-scale systems for which interruptions have negative impact on key performance metrics that may include human comfort and welfare or economy costs. A case-study example from the smart buildings domain is used to illustrate the proposed architecture and semantic inference mechanisms.

This paper develops an integrated filtering and adaptive approximation-based approach for fault diagnosis of process and sensor faults in a class of continuous-time nonlinear systems with modeling uncertainties and measurement noise. The proposed approach integrates learning with filtering techniques to derive tight detection thresholds, which is accomplished in two ways: 1) by learning the modeling uncertainty through adaptive approximation methods and 2) by using filtering for dampening measurement noise. Upon the detection of a fault, two estimation models, one for process and the other for sensor faults, are initiated in order to identify the type of fault. Each estimation model utilizes learning to estimate the potential fault that has occurred, and adaptive isolation thresholds for each estimation model are designed. The fault type is deduced based on an exclusion-based logic, and fault detectability and identification conditions are rigorously derived, characterizing quantitatively the class of faults that can be detected and identified by the proposed scheme. Finally, simulation results are used to demonstrate the effectiveness of the proposed approach.

There has been continuously increasing interest in applying neural networks (NNs) to identification and adaptive control of practical systems that are characterized by nonlinearity, uncertainty, communication constraints, and complexity. The past few years have witnessed a variety of new developments in NN-based approaches for behavior learning, information processing, autonomous decision, and system control. Biologically inspired NN structures can significantly enhance the capabilities of information processing, control, and computational performance. New discoveries in neurocognitive psychology, sociology, and elsewhere reveal new neurological learning structures with more powerful capabilities in complex problem solving and fast decision in dynamic environments. The goal of the special issue is to consolidate recent new developments in NN structures for signal processing, autonomous decision, and adaptive control with application to complex systems. It includes contributions from a wide range of research aspects relevant to the topic, ranging from neural computing, adaptive control, cooperative control, autonomous decision systems, mathematical and computational models, neuropsychology decision and control, algorithms and simulation, to applications and/or case studies. This issue contains 24 papers and the contents of which are summarized below.

Intelligent buildings are responsible for ensuring the indoor air quality for their occupants under normal operation as well as under possibly harmful contaminant events due to accidental or malicious actions. An emerging environmental control application is monitoring the intelligent buildings against the presence of such events, by incorporating various sensing technologies and distributed detection and isolation algorithms. The needed simplicity, the improved scalability and fault tolerance are some of the main reasons for choosing distributed approaches over centralized ones. Hence, the effective partitioning of buildings into smaller sections for contaminant detection and isolation approaches is of great importance. In this paper, we present an exact Mixed Integer Linear Programming (MILP) formulation for partitioning the building into smaller sections. The building is transformed into a graph which is partitioned into subgraphs indicating the groups of zones in each section while ensuring (i) maximum decoupling between the various subgraphs, (ii) strong connectivity between the zones of a subgraph and (iii) control of the number of allocated zones in each subgraph. The main contribution of this work is the automatic partitioning of the building into sections, which enables the distributed simulation, modeling, analysis and management of the intelligent building in real time, while ensuring the effective detection and isolation of contaminants in the building interior.

This paper presents a novel architecture for the design of fault-detection schemes, aiming to automate the cognitive process performed by human experts when designing fault detection schemes for certain systems. The work starts with the identification of types of cyber-physical components participating in a fault-detection scheme. These are semantically characterized, adopting a model driven by previous efforts of the World Wide Web Consortium on the semantic composition of Web services. The semantic characterizations of the components are then exploited by a Cognitive Agent with semantic reasoning capabilities, to achieve the configuration of a fault-detection scheme, given a set of specifications and available components. The Cognitive Agent has access to a knowledge representation model and is able to interact with human operators and with the components to enrich its knowledge for making and enforcing decisions about the configuration. The applicability of the architecture and the reasoning steps are demonstrated through the configuration of a water contamination event-detection scheme with learning capabilities within a smart water distribution network.

Event-triggering (ET) is an up-and-coming technological paradigm for monitoring, optimization, and control in the Internet of Things (IoT) that achieves improved levels of operational efficiency. This paper first defines the envisioned ET architecture for the IoT domain. It then classifies and reviews the various different ET approaches obtained from the available literature for the three phases of ET, namely behavior modeling, event detection, and event handling. Thereafter, a novel data-driven technique is developed to address all three phases of ET in an efficient and reliable manner. Finally, the applicability of the proposed data-driven technique is showcased in a real-world public transport scenario, demonstrating a substantial improvement in energy and spectrum efficiency compared to existing periodic techniques.

Cascade support vector machines (SVMs) are optimized to efficiently handle problems, where the majority of the data belong to one of the two classes, such as image object classification, and hence can provide speedups over monolithic (single) SVM classifiers. However, SVM classification is a computationally demanding task and existing hardware architectures for SVMs only consider monolithic classifiers. This paper proposes the acceleration of cascade SVMs through a hybrid processing hardware architecture optimized for the cascade SVM classification flow, accompanied by a method to reduce the required hardware resources for its implementation, and a method to improve the classification speed utilizing cascade information to further discard data samples. The proposed SVM cascade architecture is implemented on a Spartan-6 field-programmable gate array (FPGA) platform and evaluated for object detection on 800×600 (Super Video Graphics Array) resolution images. The proposed architecture, boosted by a neural network that processes cascade information, achieves a real-time processing rate of 40 frames/s for the benchmark face detection application. Furthermore, the hardware-reduction method results in the utilization of 25% less FPGA custom-logic resources and 20% peak power reduction compared with a baseline implementation.

Camera Sensor Networks (CSN) are becoming increasingly popular in a variety of security and safety-critical applications including public space surveillance, monitoring of attack-sensitive facilities, and critical infrastructure protection. Cameras in such networks are equipped with high-resolution visual sensors and on-board processors, while featuring wireless communication capabilities. These features enable the execution of various tasks, such as area coverage, activity recognition and target tracking, in a cooperative fashion. However, the performance of CSN may be compromised when faults occur, either due to unintentional software and hardware faults or as the result of a malicious attack. Paving the way for fault tolerance in CSN-based target tracking, we introduce a flexible fault model that can be used to generate different types of erroneous behaviour, thus simulating realistic faults in CSN. We also propose a fault-tolerant decentralized solution for tracking a target that passes through the area monitored by the CSN. Our simulation results indicate that the proposed solution is able to track the target reliably despite the presence of faults.

Traffic signal control is a key ingredient in intelligent transportation systems to increase the capacity of existing urban transportation infrastructure. However, to achieve optimal system-wide operation, it is essential to coordinate traffic signals at various intersections. In this paper, we model the multiple-intersection traffic signal control problem using the cell transmission model as a mixed-integer linear program. The solution of the problem is facilitated by its special structure, which allows both temporal and spatial decomposition. Temporal decomposition is employed to reduce the problem size by solving subproblems of a smaller time window compared to the original problem. Temporal subproblems can be further spatially decomposed into subproblems associated with different intersections, which are jointly solved by exchanging messages between neighboring intersections. The proposed distributed solution strategy is comprised of two phases. First, the relaxed linear problem is reformulated and distributedly solved via the alternating direction method of multipliers. Second, two distributed rounding schemes are developed to solve the original problem. Simulation results indicate that the proposed solution strategy is scalable to large transportation topologies, which is suitable for online execution, and provides close-to-optimal results.

In this work we present the problem of contamination event detection in drinking water distribution networks using real-time learning approaches and a model-based event detection scheme. By using chlorine concentration measurements a contamination event detection algorithm is developed with the aim of detecting the occurrence of contaminant injection into a water tank by monitoring the change of the chlorine concentration. The proposed methodology is comprised of two steps: a) learn in real-time the unknown chlorine reaction dynamics using a Radial-Basis Function network; b) activate a contamination-event detection methodology which uses an adaptive detection threshold. A contamination event detection alarm is activated when the magnitude of the estimation error exceeds the detection threshold. To demonstrate the proposed methodology realistic case study is evaluated with Monte-Carlo simulations of contamination events of different magnitudes occurrence times and environmental characteristics. The results demonstrate the improvement in the contamination event detection performance when using the real-time learning approach.

This paper presents the design of a methodology for diagnosing sensor faults in heating, ventilation and air-conditioning (HVAC) systems, and compensating their effects on the distributed control architecture. The proposed methodology is developed in a distributed framework, considering a multi-zone HVAC system as a set of interconnected, nonlinear subsystems. For each of the interconnected subsystems, we design a local virtual sensor agent that can detect and isolate faults in its monitored sensors and provide sensor fault estimations for correcting the faulty measurements. Adaptive estimation schemes are implemented in each local virtual sensor agent, using adaptive approximation models for learning the unknown fault function. Simulation results are used for illustrating the effectiveness of the proposed methodology applied to a two-zone HVAC system.

This paper presents an adaptive approximation-based design methodology and analytical results for distributed detection and isolation of multiple sensor faults in a class of nonlinear uncertain systems. During the initial stage of the nonlinear system operation, adaptive approximation is used for online learning of the modeling uncertainty. Then, local sensor fault detection and isolation (SFDI) modules are designed using a dedicated nonlinear observer scheme. The multiple sensor fault isolation process is enhanced by deriving a combinatorial decision logic that integrates information from local SFDI modules. The performance of the proposed diagnostic scheme is analyzed in terms of conditions for ensuring fault detectability and isolability. A simulation example of a single-link robotic arm is used to illustrate the application of the adaptive approximation-based SFDI methodology and its effectiveness in detecting and isolating multiple sensor faults.

In this paper, we present a distributed fault tolerant control methodology for interconnected nonlinear uncertain systems. Linearly parameterized neural networks are used to adaptively approximate the unknown interconnections and fault functions, based on local state information, as well as communicated information from other subsystems. The exchange of state information between subsystems is based on a coordinated communication scheme. The stability of the distributed fault tolerant control scheme is established through a rigorous Lyapunov analysis.

This paper presents a design methodology and some analytical results for distributed sensor fault detection and isolation (SFDI) of a class of nonlinear uncertain systems. During the initial stage of the nonlinear system operation, an adaptive approximation technique is used for learning online the modeling uncertainty. Then, local SFDI modules are designed using a dedicated nonlinear observer scheme. The fault isolation process is enhanced by deriving a combinatorial decision logic that integrates information from local SFDI modules. The performance of the proposed diagnostic scheme is analyzed in terms of its robustness with respect to the modeling uncertainties and conditions for ensuring fault detectability and isolability.

Next generation multiprocessor systems-on-chip (MPSoCs) are expected to contain numerous processing elements, interconnected via on-chip networks, executing real-time applications. It is anticipated that runtime optimization algorithms which dynamically adjust system parameters with the purpose of optimizing the system's operation, will be embedded in the system software and/or hardware. In this paper, we present a methodology for simulating and evaluating system-level optimization algorithms, demonstrated by the case of on-chip dynamic task allocation applied to generic MPSoC architectures. Through this methodology, we are able to show that dynamic, system-level bidding-based task allocation can improve system performance, when compared to a round robin allocation, in popular MPSoC applications.

This paper presents a novel fuzzy-logic based switching and tuning supervisor for an intelligent multiple-controller framework. The fuzzy logic based supervisor operates at the highest level of the system and makes a switching decision, on the basis of the required performance measure, between two non-linear fixed structure controllers, namely a conventional Proportional-Integral-Derivative (PID) controller, or a PID structure based zero and pole placement controller. The fuzzy supervisor also adaptively tunes the parameters of the controllers. The proposed methodology is used to simultaneously control the throttle and brake systems of a validated nonlinear vehicle model. Sample simulation results are used to demonstrate the effectiveness of the multiple-controller with respect to tracking desired vehicle speed changes and achieving the desired speed of response, whilst penalising excessive control action.

This paper considers a heterogeneous team of cooperating unmanned aerial vehicles (UAVs) drawn from several distinct classes and engaged in a search and action mission over a spatially extended battlefield with targets of several types. During the mission, the UAVs seek to confirm and verifiably destroy suspected targets and discover, confirm, and verifiably destroy unknown targets. The locations of some (or all) targets are unknown a priori, requiring them to be located using cooperative search. In addition, the tasks to be performed at each target location by the team of cooperative UAVs need to be coordinated. The tasks must, therefore, be allocated to UAVs in real time as they arise, while ensuring that appropriate vehicles are assigned to each task. Each class of UAVs has its own sensing and attack capabilities, so the need for appropriate assignment is paramount. In this paper, an extensive dynamic model that captures the stochastic nature of the cooperative search and task assignment problems is developed, and algorithms for achieving a high level of performance are designed. The paper focuses on investigating the value of predictive task assignment as a function of the number of unknown targets and number of UAVs. In particular, it is shown that there is a tradeoff between search and task response in the context of prediction. Based on the results, a hybrid algorithm for switching the use of prediction is proposed, which balances the search and task response. The performance of the proposed algorithms is evaluated through Monte Carlo simulations.

A feedback control methodology is presented for online approximation based backstepping control of non-linear dynamical systems subject to magnitude, rate, and bandwidth constraints on the state and the actuators. The robustness issue with respect to functional approximation errors is addressed in a rigorous manner. The stability properties of the proposed design methodology are derived.

This paper presents a new active queue management scheme, fuzzy explicit marking (FEM), implemented within the differentiated services (Diffserv) framework to provide the congestion control using a fuzzy logic control approach. Network congestion control remains a critical and high priority issue. The rapid growth of the Internet and increased demand to use the Internet for time-sensitive voice and video applications necessitate the design and utilization of effective congestion control algorithms, especially for new architectures, such as Diffserv. As a result, a number of researchers are now looking at alternatively schemes to TCP congestion control. RED (random early detection) and its variants are one of these alternatives to provide quality of service (QoS) in TCP/IP Diffserv networks. The proposed fuzzy logic approach for congestion control allows the use of linguistic knowledge to capture the dynamics of nonlinear probability marking functions and offer effective implementation, use of multiple inputs to capture the (dynamic) state of the network more accurately, enable finer tuning for packet marking behaviors (either dropping a packet or setting its ECN - explicit congestion notification - bit) for aggravated flows, and thus provide better QoS to different types of data streams, such as TCP/FTP traffic or TCP/Web-like traffic, whilst maintaining high utilization.

Slow learning of neural-network function approximators can frequently be attributed to interference, which occurs when learning in one area of the input space causes unlearning in another area. To mitigate the effect of unlearning, this paper develops an algorithm that adjusts the weights of an arbitrary, nonlinearly parameterized network such that the potential for future interference during learning is reduced. This is accomplished by the reduction of a biobjective cost function that combines the approximation error and a term that measures interference. An analysis of the algorithm's convergence properties shows that learning with this algorithm reduces future unlearning. The algorithm can be used either during online learning or can be used to condition a network to have immunity from interference during a future learning stage. A simple example demonstrates how interference manifests itself in a network and how less interference can lead to more efficient learning. Simulations demonstrate how this new learning algorithm speeds up the training in various situations due to the extra cost function term.

A large class of engineering systems are modeled by coupled differential and algebraic equations (DAE). Due to the singular nature of the algebraic equations, DAE systems do not satisfy the standard state-space description and require special techniques. So far, the literature has concentrated mostly on the numerical analysis and control of DAE systems. This paper investigates the problem of health monitoring and robust fault diagnosis of DAE systems. The main contributions are the design and analysis of a numerically feasible learning scheme for robust and stable fault diagnosis of DAE systems. The proposed fault diagnosis architecture monitors the physical system for any off-nominal behavior using nonlinear modeling techniques and learning algorithms. Online approximators, in the form of neural networks, are utilized in the detection of faults and in the derivation of models for the fault function, which can be used for fault isolation, fault identification, and fault accommodation. The stability and robustness properties of the fault diagnosis scheme are investigated. A simulation example illustrating the ability of the proposed fault diagnosis architecture to detect faults in a chemical reactive flash is presented.

The paper presents a robust fault diagnosis scheme for detecting and approximating state and output faults occurring in a class of nonlinear multiinput-multioutput dynamical systems. Changes in the system dynamics due to a fault are modeled as nonlinear functions of the control input and measured output variables. Both state and output faults can be modeled as slowly developing (incipient) or abrupt, with each component of the state/output fault vector being represented by a separate time profile. The robust fault diagnosis scheme utilizes on-line approximators and adaptive nonlinear filtering techniques to obtain estimates of the fault functions. Robustness with respect to modeling uncertainties, fault sensitivity and stability properties of the learning scheme are rigorously derived and the theoretical results are illustrated by a simulation example of a fourth-order satellite model.

Interference in neural networks occurs when learning in one area of the input space causes unlearning in another area. Networks that are less susceptible to interference are referred to as spatially local networks. To obtain a better understanding of these properties, a theoretical framework, consisting of a measure of interference and a measure of network localization, is developed. These measures incorporate not only the network weights and architecture but also the learning algorithm. Using this framework to analyze sigmoidal, multilayer perceptron (MLP) networks that employ the backpropagation learning algorithm on the quadratic cost function, we address a familiar misconception that single-hidden-layer sigmoidal networks are inherently nonlocal by demonstrating that given a sufficiently large number of adjustable weights, single-hidden-layer sigmoidal MLP's exist that are arbitrarily local and retain the ability to approximate any continuous function on a compact domain.

Fault detection, diagnosis, and accommodation play a key role in the operation of autonomous and intelligent robotic systems. System faults, which typically result in changes in critical system parameters or even system dynamics, may lead to degradation in performance and unsafe operating: conditions. This paper investigates the problem of fault diagnosis in rigid-link robotic manipulators. A learning architecture, with neural networks as online approximators of the off-nominal system behaviour, is used for monitoring the robotic system for faults. The approximation (by the neural network) of the off-nominal behaviour provides a model of the fault characteristics which can be used for detection and isolation of faults. The stability and performance properties of the proposed fault detection scheme in the presence of system failure are rigorously established, simulation examples are presented to illustrate the ability of the neural network based fault diagnosis methodology described in this paper to detect and accommodate faults in a simple two-link robotic system.

Fault diagnosis plays an important role in the operation of modern robotic systems. A number of researchers have proposed fault diagnosis architectures for robotic manipulators using the model-based analytical redundancy approach. One of the key issues in the design of such fault diagnosis schemes is the effect of modeling uncertainties on their performance. This paper investigates the problem of fault diagnosis in rigid-link robotic manipulators with modeling uncertainties. A learning architecture with sigmoidal neural networks is used to monitor the robotic system for any off-nominal behavior due to faults. The robustness and stability properties of the fault diagnosis scheme are rigorously established. Simulation examples are presented to illustrate the ability of the neural-network-based robust fault diagnosis scheme to detect and accommodate faults in a two-link robotic manipulator.

Several continuous-time and discrete-time recurrent neural network models have been developed and applied to various engineering problems. One of the difficulties encountered in the application of recurrent networks is the derivation of efficient learning algorithms that also guarantee the stability of the overall system. This paper studies the approximation and learning properties of one class of recurrent networks, known as high-order neural networks; and applies these architectures to the identification of dynamical systems. In recurrent high-order neural networks, the dynamic components are distributed throughout the network in the form of dynamic neurons. It is shown that if enough high-order connections are allowed then this network is capable of approximating arbitrary dynamical systems. Identification schemes based on high-order network architectures are designed and analyzed.

The detection, diagnosis, and accommodation of system failures or degradations are becoming increasingly more important in modern engineering problems. A system failure often causes changes in critical system parameters, or even, changes in the nonlinear dynamics of the system. This paper presents a general framework for constructing automated fault diagnosis and accommodation architectures using on-line approximators and adaptation/learning schemes. In this framework, neural network models constitute an important class of on-line approximators. Changes in the system dynamics are monitored by an on-line approximation model, which is used not only for detecting but also for accommodating failures. A systematic procedure for constructing nonlinear estimation algorithms is developed, and a stable learning scheme is derived using Lyapunov theory. Simulation studies are used to illustrate the results and to gain intuition into the selection of design parameters.>

A class of feedforward neural networks, structured networks, has recently been introduced as a method for solving matrix algebra problems in an inherently parallel formulation. A convergence analysis for the training of structured networks is presented. Since the learning techniques used in structured networks are also employed in the training of neural networks, the issue of convergence is discussed not only from a numerical algebra perspective but also as a means of deriving insight into connectionist learning. Bounds on the learning rate are developed under which exponential convergence of the weights to their correct values is proved for a class of matrix algebra problems that includes linear equation solving, matrix inversion, and Lyapunov equation solving. For a special class of problems, the orthogonalized back-propagation algorithm, an optimal recursive update law for minimizing a least-squares cost functional, is introduced. It guarantees exact convergence in one epoch. Several learning issues are investigated.