A Robust Road Vanishing Point Detection Adapted to the Real-world Driving Scenes.

Vanishing point (VP) provides extremely useful information related to roads in driving scenes for advanced driver assistance systems (ADAS) and autonomous vehicles. Existing VP detection methods for driving scenes still have not achieved sufficiently high accuracy and robustness to apply for real-world driving scenes. This paper proposes a robust motion-based road VP detection method to compensate for the deficiencies. For such purposes, three main processing steps often used in the existing road VP detection methods are carefully examined. Based on the analysis, stable motion detection, stationary point-based motion vector selection, and angle-based RANSAC (RANdom SAmple Consensus) voting are proposed. A ground-truth driving dataset including various objects and illuminations is used to verify the robustness and real-time capability of the proposed method. The experimental results show that the proposed method outperforms the existing motion-based and edge-based road VP detection methods for various illumination conditioned driving scenes.

Asymmetric Encoder-Decoder Structured FCN Based LiDAR to Color Image Generation.

In this paper, we propose a method of generating a color image from light detection and ranging (LiDAR) 3D reflection intensity. The proposed method is composed of two steps: projection of LiDAR 3D reflection intensity into 2D intensity, and color image generation from the projected intensity by using a fully convolutional network (FCN). The color image should be generated from a very sparse projected intensity image. For this reason, the FCN is designed to have an asymmetric network structure, i.e., the layer depth of the decoder in the FCN is deeper than that of the encoder. The well-known KITTI dataset for various scenarios is used for the proposed FCN training and performance evaluation. Performance of the asymmetric network structures are empirically analyzed for various depth combinations for the encoder and decoder. Through simulations, it is shown that the proposed method generates fairly good visual quality of images while maintaining almost the same color as the ground truth image. Moreover, the proposed FCN has much higher performance than conventional interpolation methods and generative adversarial network based Pix2Pix. One interesting result is that the proposed FCN produces shadow-free and daylight color images. This result is caused by the fact that the LiDAR sensor data is produced by the light reflection and is, therefore, not affected by sunlight and shadow.

Traffic Light Recognition Based on Binary Semantic Segmentation Network.

A traffic light recognition system is a very important building block in an advanced driving assistance system and an autonomous vehicle system. In this paper, we propose a two-staged deep-learning-based traffic light recognition method that consists of a pixel-wise semantic segmentation technique and a novel fully convolutional network. For candidate detection, we employ a binary-semantic segmentation network that is suitable for detecting small objects such as traffic lights. Connected components labeling with an eight-connected neighborhood is applied to obtain bounding boxes of candidate regions, instead of the computationally demanding region proposal and regression processes of conventional methods. A fully convolutional network including a convolution layer with three filters of (1 × 1) at the beginning is designed and implemented for traffic light classification, as traffic lights have only a set number of colors. The simulation results show that the proposed traffic light recognition method outperforms the conventional two-staged object detection method in terms of recognition performance, and remarkably reduces the computational complexity and hardware requirements. This framework can be a useful network design guideline for the detection and recognition of small objects, including traffic lights.

Average Accumulative Based Time Variant Model for Early Diagnosis and Prognosis of Slowly Varying Faults.

Early detection of slowly varying small faults is an essential step for fault prognosis. In this paper, we first propose an average accumulative (AA) based time varying principal component analysis (PCA) model for early detection of slowly varying faults. The AA based method can increase the fault size as well as decrease the noise energy. Then, designated component analysis (DCA) is introduced for developing an AA-DCA method to diagnose the root cause of the fault, which is helpful for the operator to make maintenance decisions. Combining the advantage of the cumulative sum (CUSUM) based method and the AA based method, a CUSUM-AA based method is developed to detect faults at earlier times. Finally, the remaining useful life (RUL) prediction model with error correction is established by nonlinear fitting. Once online fault size defined by detection statistics is obtained by an early diagnosis algorithm, real-time RUL prediction can be directly estimated without extra recursive regression.

Practical Event-Triggered Finite-Time Second-Order Sliding Mode Controller Design.

This article proposes a novel event-triggered second-order sliding mode (SOSM) control algorithm using the small-gain theorems. The developed algorithm has global event property in aspects of the triggering time intervals. First, an SOSM controller is designed related to the sampling error of states, and it is proved that the closed-loop system is finite-time input-to-state stable (FTISS) with the sampling error via utilizing the small-gain theorems. Second, combined with the constructed SOSM controller, a new triggering mechanism is proposed depending on the sampling error by designing the appropriate FTISS gain condition. Third, the practical finite-time stability of the closed-loop system is verified. It is shown that the minimum triggering time interval is always a positive value in the whole state space. Finally, the simulation results demonstrate the effectiveness of the developed control method.

MPC-Based Asynchronous Attack Tolerant Control for Uncertain Markov Jump Cyber-Physical Systems.

The model predictive control (MPC)-based asynchronous attack tolerant control scheme is investigated in this article for uncertain Markov jump cyber-physical systems (MJCPSs) under the Denial-of-Service (DoS) attack. To tackle the problem of the system running mode may not be observed in the control center, an asynchronous model predictive controller is proposed. Specifically, a dynamic controller, which can tune the performance online, is designed besides a traditional state feedback one. Even though such a combination may cause possible degradation of system performance, it can expand the initial feasible region and relieve the online computation burden efficiently. In addition, a decision variable is introduced to alleviate limitations on the feasible region generated by the constraints in the traditional MPC method. A series of solvable optimal problems are further constructed to achieve the desired performances. Finally, an application of the proposed method is given to demonstrate its effectiveness.

Periodic self-triggered strategy for highly non-linear hybrid stochastic delayed networks based on impulsive control.

This article investigates the stabilization issue of highly non-linear hybrid stochastic delayed networks (HSDNs) via periodic self-triggered control under impulse (PS-TCI). Firstly, the existence of a unique global solution for highly non-linear HSDNs under PS-TCI is studied. Then, a stabilization criterion for highly non-linear HSDNs is established, by combining a graph-theoretic approach with a novel Lyapunov-based analysis, based on a 'genuine' Lyapunov function defined by introducing an auxiliary timer. Therein, the less conservative polynomial growth condition and local Lipschitz condition for the drift and diffusion coefficients are used than the linear growth condition and global Lipschitz condition. Meanwhile, the design idea of PS-TCI is based on the evolution of an upper bound of the mathematical expectation for Lyapunov function (not directly Lyapunov function or system state), which implies that the triggered instant of PS-TCI is not a random variable. Finally the theoretical results are employed to study the stability of a class of FitzHugh-Nagumo circuits networks and the central pattern generators networks of a hexapod robot, and correlative numerical simulations are provided for demonstration.

Integral BLF-Based Adaptive Dynamic Event-Triggered Boundary Control for a Flexible Riser System.

For the flexible riser systems modeled with partial differential equations (PDEs), this article explores the boundary control problem in depth for the first time using a dynamic event-triggered mechanism (DETM). Given the intrinsic time-space coupling characteristic inherent in PDE computations, implementing a state-dependent DETM for PDE-based flexible risers presents a significant challenge. To overcome this difficulty, a novel dynamic event-triggered control method is introduced for flexible riser systems, focusing on optimizing available control inputs. In order to save computational costs from the controller to the actuator, a dynamic event-triggered adaptive boundary controller is designed to effectively reduce boundary position vibrations. Additionally, considering external disturbances, an adaptive bounded compensation term is incorporated to counteract the influence of external disturbances on the system. Addressing boundary position constraints, a new integral barrier Lyapunov function (iBLF) tailored specifically for flexible riser systems is introduced, thereby alleviating conservatism in the controller design of flexible risers modeled by PDEs. At last, the validity of the proposed method is demonstrated through a simulation example.

Quantization-Based Adaptive Fuzzy Consensus for Multiagent Systems Under Sensor Deception Attacks: A Novel Compensation Mechanism.

This study mainly investigates the adaptive leader-following consensus tracking control problem for a class of nonlinear multiagent systems (MASs) subjected to unknown control directions, external disturbances, and sensor deception attacks. To start with, an equivalent MAS with known control directions is obtained by introducing a linear state transformation. For the purpose of estimating the unavailable system states caused by malicious attacks, a quantization-based fuzzy state observer is designed, and the fuzzy-logic system (FLS) is utilized to approximate nonlinear functions. Moreover, a dynamic uniform quantizer with scaling function is established to reduce information transmission. With the help of coordinate transformation and available compromised states, a novel compensation mechanism is designed to offset the influence of filter errors while avoiding the problem of "explosion of complexity" in the backstepping design process. In addition, the Nussbaum-type function is considered to eliminate the design obstacle of unknown control gains resulting from the attacks. Under the constructed consensus protocol, it is proved theoretically that the consensus tracking error converges to an adjustable small neighborhood of the origin, and all signals in the closed-loop system are bounded. Finally, the feasibility of the provided secure control scheme is verified through two simulation examples.

Reinforcement Learning-Based Predefined-Time Tracking Control for Nonlinear Systems Under Identifier-Critic-Actor Structure.

A novel reinforcement learning-based predefined-time tracking control scheme with prescribed performance is presented in this article for nonlinear systems in the presence of external disturbances. First, by employing the backstepping strategy, an adaptive optimized controller is developed under the identifier-critic-actor framework. Therein, the unknown nonlinear dynamics and the system control behavior can be learned effectively through neural networks. Moreover, aiming at obtaining the preset tracking performance, the prescribed performance control is integrated with the predefined-time control. In contrast to previous studies, the proposed scheme can not only constrain the tracking error rapidly to a prearranged vicinity of origin, but also ensure that the upper bound of convergence time can be adjusted in advance via a separate control parameter. In terms of the predefined-time stability theory, the boundedness of all system states can be proven within a predefined time. Finally, the availability and improved performances of the proposed control scheme are demonstrated by a numerical example and a single-link manipulator example.

Source-Storage-Load Coordinated Master-Slave Control Strategy for Islanded Microgrid Considering Load Disturbance and Communication Interruption.

When there is a sudden load disturbance in an islanded microgrid, the peer-to-peer control model requires the energy resource to maintain a margin of generation, resulting in a relatively limited regulation range, that is, voltage/frequency sometimes requires additional control to maintain stability. A "source-storage-load" coordinated master-slave control strategy is proposed in this study to address the aforementioned issues. The system voltage and frequency will be stable as long as the output frequency and voltage of the master resource are stable. Furthermore, it can fully utilize the power supply capacity of resources to support the supply-demand balance. The following tasks are included in the proposed strategy: 1) to improve the operational security in the face of load disruption, a source-storage-load coordinated control method based on the "ramping speed" ratio is proposed, which can quickly restore the balance of supply and demand; 2) to improve the communication reliability in the face of interruption, a channel planning method is proposed, which can address the communication interruption problem by constructing an internal network among source-storage-load; and 3) to improve the mode switching stability of resources subjected to external disturbance, the external disturbance suppression and stability analysis involved in the regulation process are completed using sliding-mode control and small signal model methods. Related case studies are carried out to verify the effectiveness of the proposed strategies.

Sliding mode control for uncertain fractional-order reaction-diffusion memristor neural networks with time delays.

This paper investigates a sliding mode control method for a class of uncertain delayed fractional-order reaction-diffusion memristor neural networks. Different from most existing literature on sliding mode control for fractional-order reaction-diffusion systems, this study constructs a linear sliding mode switching function and designs the corresponding sliding mode control law. The sufficient theory for the globally asymptotic stability of the sliding mode dynamics are provided, and it is proven that the sliding mode surface is finite-time reachable under the proposed control law, with an estimate of the maximum reaching time. Finally, a numerical test is presented to validate the effectiveness of the theoretical analysis.

Neural Preassigned Performance Control for State-Constrained Nonlinear Systems Subject to Disturbances.

This article addresses the finite-time neural predefined performance control (PPC) issue for state-constrained nonlinear systems (NSs) with exogenous disturbances. By integrating the predefined-time performance function (PTPF) and the conventional barrier Lyapunov function (BLF), a new set of time-varying BLFs is designed to constrain the error variables. This establishes conditions for satisfying full-state constraints while ensuring that the tracking error meets the predefined performance indicators (PPIs) within a predefined time. Additionally, the incorporation of the nonlinear disturbance observer technique (NDOT) in the control design significantly enhances the ability of the system to reject disturbances and improves overall robustness. Leveraging recursive design based on dynamic surface control (DSC), a finite-time neural adaptive PPC strategy is devised to ensure that the closed-loop system is semi-globally practically finite-time stable (SPFS) and achieves the desired PPIs. Finally, the simulation results of two practical examples validate the efficacy and viability of the proposed approach.

Memory-Event-Triggered Fault Detection of Networked IT2 T-S Fuzzy Systems.

In this article, a networked fault detection (FD) problem is investigated for interval type-2 T-S fuzzy systems. A novel adaptive memory-event-triggered mechanism (METM) is proposed by introducing historical information of the measured output in a prescribed sliding window. The current measured output in the traditional event-triggered mechanism is replaced by a weighting function-based historical information. As a result, the data releasing rate can be effectively reduced and maltriggering events aroused by unknown abrupt disturbance or measurement noise can be avoided as well. Meanwhile, an adaptive threshold depending on the historical information is utilized to further adjust the data releasing rate. The FD filter is designed and derived in terms of linear matrix inequalities to guarantee the H∞ performance of fault detected systems. Finally, a hardware-in-loop simulation experiment platform is built to manifest the effectiveness of the proposed METM-based FD method.

Hybrid Dynamic Event-Triggered Load Frequency Control for Power Systems With Unreliable Transmission Networks.

In this article, we consider the load frequency control problem for a class of power systems based on the dynamic event-triggered control (ETC) approach. The transmission networks are unreliable in the sense that malicious denial-of-service (DoS) attacks may arise in the power system. First, a model-based feedback controller is designed, which utilizes estimated states, and thus can compensate the error between plant states and the feedback data. Then, a dynamic event-triggered mechanism (DETM) is proposed by introducing an internal dynamic variable and a timer variable with jump dynamics. The proposed (DETM) can exclude Zeno behavior by regularizing a prescribed strictly positive triggering interval. Incorporated in the ETC scheme, a novel hybrid model is established to describe the flow and jump dynamics of the power system in the presence of DoS attacks. Based on the hybrid dynamic ETC scheme, the power system stability can be preserved if the attacks frequency and duration sustain within an explicit range. In addition, the explicit range is further maximized based on the measurement trigger-resetting property. Finally, a numerical example is presented to show the effectiveness of our results.

Reduced-Order Observer-Based Output-Feedback Tracking Control for Nonlinear Time-Delay Systems With Global Prescribed Performance.

In this article, the output-feedback tracking control problem is considered for a class of nonlinear time-delay systems in a strict-feedback form. Based on a state observer with reduced order, a novel output-feedback control scheme is proposed using the backstepping approach, which is able to guarantee the system transient and steady-state performance within a prescribed region. Different from existing works on prescribed performance control (PPC), the present method can relax the restriction that the initial value must be given within a predefined region, say, PPC semiglobally. In the case that the upper bound functions for nonlinear time-delay functions are unknown, based on the approximate capacity of fuzzy-logic systems, an adaptive fuzzy approximation control strategy is proposed. When the upper bound functions are known in prior, or in a product form with unknown parameters and known functions, an output-feedback tracking controller is designed, under which the closed-loop signals are globally ultimately uniformly bounded, and tracking control with global prescribed performance can be achieved. Simulation results are given to substantiate our method.

Output-Feedback Control for Fuzzy Singularly Perturbed Systems: A Nonhomogeneous Stochastic Communication Protocol Approach.

In this study, the output-feedback control (OFC) strategy design problem is explored for a type of Takagi-Sugeno fuzzy singular perturbed system. To alleviate the communication load and improve the reliability of signal transmission, a novel stochastic communication protocol (SCP) is proposed. In particular, the SCP is scheduled based on a nonhomogeneous Markov chain, where the time-varying transition probability matrix is characterized by a polytope-structure-based set. Different from the existing homogeneous Markov SCP, a nonhomogeneous Markov SCP depicts the data transmission in a more reasonable manner. To detect the actual network mode, a hidden Markov process observer is addressed. By virtue of the hidden Markov model with partly unidentified detection probabilities, an asynchronous OFC law is formulated. By establishing a novel Lyapunov-Krasovskii functional with a singular perturbation parameter and a nonhomogeneous Markov process, a sufficient condition is exploited to guarantee the stochastic stability of the resulting system, and the solution for the asynchronous controller is portrayed. Eventually, the validity of the attained methodology is expressed through a practical example.

The Optimization of Control Parameters: Finite-Time Bipartite Synchronization of Memristive Neural Networks With Multiple Time Delays via Saturation Function.

This article studies the memristive neural networks with multiple time delays (MNNsMTDs). The topology of networks is signed, which contains both cooperative and competitive relationships. Two controllers without time delays are designed to achieve finite-time bipartite synchronization (FTBS) and practical FTBS (PFTBS) of MNNsMTDs. A novel controller with a saturation function rather than a sign function is proposed to avoid chattering. Along with the Lyapunov function method, some mathematical techniques, and scaling inequalities, some sufficient conditions for FTBS and PFTBS of MNNsMTDs are attained. Besides, this article also concerns fixed-time bipartite synchronization (FXBS) and practical FXBS (PFXBS) of MNNsMTDs. An optimization model is designed to obtain some optimal control parameters. An algorithm based on particle swarm optimization (PSO) is provided to solve this model. Some numerical examples are included to demonstrate the correctness and applicability of the approaches.

Aperiodically intermittent event-triggered pinning control on cluster synchronization of directed complex networks.

This paper is dedicated to investigating the exponential cluster synchronization in a class of nonlinearly coupled complex networks with non-identical nodes and an asymmetrical coupling matrix. A novel aperiodically intermittent pinning control (APIPC) protocol is presented, which takes full account of the cluster-tree topology structure of the networks and pins only the nodes in the current cluster that have directional links to neighboring clusters. Since it is difficult to precisely determine the intermittent control instants and rest instants of APIPC in advance, the event-triggered mechanism (ETM) is thus proposed. Based on the concept of the minimal control ratio and the segmentation analysis method, sufficient requirements for realizing the exponential cluster synchronization are derived. Moreover, the Zeno behavior of ETM is excluded by rigorous analysis. Eventually, the effectiveness and advantages of the established theorems and control strategies are demonstrated by two numerical simulations.

Sampled Memory-Event-Triggered Fuzzy Load Frequency Control for Wind Power Systems Subject to Outliers and Transmission Delays.

This study is devoted to event-triggered fuzzy load frequency control (LFC) for wind power systems (WPSs) with measurement outliers and transmission delays. Due to the integration of wind turbine (WT) with nonlinearity, the T-S fuzzy model of WPS is established for stability analysis and controller design. To mitigate the network burden, a new sampled memory-event-triggered mechanism (SMETM) related to historical system information is presented. It has the following two merits: 1) the utilization of continuous memory outputs over a given interval is useful to reduce the information loss in the period of samples and the redundant triggering events induced by disturbances and noises and 2) an extra upper constraint is added in the triggering condition to generate a new event only when the error signal belongs to a bounded range, thus, the false events caused by measurement outliers can be differentiated out and then be dropped. By representing the memory signal with transmission delay as a time-varying distributed delay term, a T-S fuzzy time-varying distributed delay system is built up to model the H∞ LFC WPS. With the help of the Lyapunov method and the integral inequality relying on distributed delay, some criteria are derived to solve the triggering matrix and fuzzy controllers. Finally, the merits of the proposed SMETM are tested by simulation results.