Bird’s-Eye-View (BEV) semantic segmentation provides comprehensive environmental perception for autonomous driving, but suffers from multimodal misalignment and sensor noise. We propose RESAR-BEV, a progressive refinement framework that advances beyond single-step end-to-end approaches: 1) an inherently interpretable, coarse-to-fine refinement using a residual autoregressive learning paradigm implemented by our Drive-Transformer and Modifier-Transformer cascade, where each stage is responsible for a specific semantic scale (from road topology to lane boundaries); 2) robust BEV representation combining ground-proximity voxels with adaptive height offsets and dual-path voxel feature encoding (max+attention pooling) for efficient feature extraction; and 3) decoupled supervision with offline Ground Truth decomposition and online joint optimization, which prevent overfitting while ensuring structural coherence. Experiments on nuScenes demonstrate RESAR-BEV achieves state-of-the-art performance with 54.0% mIoU across 7 essential driving-scene categories while maintaining real-time capability at 14.6 FPS. The framework exhibits robustness in challenging scenarios of long-range perception and adverse weather conditions.

Conversational recommendation is one system that can extract the user's preferences and recommend suitable items in a similar way to human-like responses. Existing methods often use the feature extraction combined with the Transformer model to extract user preferences and make recommendations. However, these methods have two limitations. First, they do not consider the order in which entities appear, thus affecting the extraction of user preferences. Second, the generated responses lack diversity that affects the users’ experience to the system. To this end, we propose a conversational recommendation model with User Entity focus and Multi-Granularity latent variable enhancement (UEMG). In UEMG, we design a novel neural network that utilizes Bi-GRU to capture the appearing orders of entities in dialogues, and leverages Transformer to capture the global dependencies of entities, and then combines them to extract user preferences. For the second issue, to improve the diversity of dialogue generation, we propose a multi-granularity latent variable mechanism, which can extract more entities from the context information and the knowledge graphs, respectively. We conducted extensive experiments on publicly available dialogue generation datasets. Experimental results demonstrate that compared to current state-of-the-art methods, UEMG achieves 9.7% improvements in recommendation performance and 23% improvements in dialogue generation.

Object detection is a fundamental task that usually requires the optimization of two sub-tasks (i.e., localization and classification). However, there exists a lack of understanding regarding the changing pattern of their preferred interest locations. Existing work adopts alternating detection head designs in terms of handling task-interactive and task-specific features. To tackle this issue, we conduct a thorough analysis to investigate the contradicting focus-shifting patterns of these sub-tasks. Specifically, we first collect data points on the MS-COCO dataset and conduct numerical analysis to pinpoint the optimal branching point by evaluating the effect size metrics of feature similarity and by calculating the 2-D inter-cluster distances between features among potential branching points. Then, qualitative analysis regarding the feature representation is carried out to further justify the results. At last, we demonstrate the potential generalizability of our analysis pipelines across various architectures, label assignment methods, training techniques, and datasets. In light of the above finding, we propose the opportune branching head that leverages the conflict between task-interactive and task-specific features by decoupling the sub-tasks at the condign point to maximize the preference. We further extend the concept of opportune branching and propose the adaptive attention mechanism to enable more effective attention allocation in a laconic manner, magnifying the effect of opportune branching. We conduct extensive experiments on the MS-COCO benchmark, the PASCAL VOC benchmark, and the Cityscape benchmark, where our method achieves competitive results. We achieve 50.0 AP with the ResNeXt-101-4d-64 backbone and 59.8 AP with the Swin-L transformer backbone on the MS-COCO benchmark, representing the best performance among nontransformer-based methods while also outperforming many state-of-the-art transformer-based methods by a clear margin.

Medical image registration is mainly used for 3D reconstruction of images, which has important clinical research significance. Therefore, accurate medical image registration is an important and highly challenging research topic. Current state-of-the-art methods employ pyramid registration neural network models to learn the anatomical relationship between moving images and fixed images, achieving breakthrough progress. However, these methods overlook the spatial relationship between non-adjacent elements in the images, leading to a small receptive field problem. To address this problem, we propose a self-attention enhanced 3D convolution dual-stream pyramid registration neural network model based on Transformer-ConvNet, named TransPyramid++. In TransPyramid++, Self-attention Blocks based on attention mechanisms and PatchMerging based on image block fusion are exploited to capture the anatomical relationship between moving images and fixed images, considering the non-adjacent elements. Then, by utilizing the upsampling and skip connections to decode this relationship step by step, while maintaining the residual relationship between the encoder and decoder. Finally, we propose the PR++ Module based on 3D convolution operations to calculate correlations between feature maps at different positions, which is an enhancement for the relation between non-adjacent elements. As a result, the problem of small receptive fields is alleviated. We conducted extensive experiments on the publicly available brain image registration datasets, Mindboggle101 and LPBA40. The experimental results show that compared to state-of-the-art methods, the performance of our model exceeds that of existing models, with an average improvement of 6.7% on the ASSD (Average Symmetric Surface Distance) index.

The intelligent chatbot takes dialogue sentiment prediction as the core, and it has to tackle long dialogue sentiment prediction problems in many real-world applications. Current state-of-the-art methods usually employ attention-based dialogue sentiment prediction models. However, as the conversation progresses, more topics are involved and the changes in sentiments become more frequent, which leads to a sharp decline in the accuracy and efficiency of the current methods. Therefore, we propose a Multi-round Long Dialogue Sentiment Prediction based on Multidimensional Attention (MLDSP-MA), which can focus on different topics. In particular, MLSDP-MA leverages a sliding window to capture different topics and traverses all historical dialogues. In each sliding window, the contextual dependency, sentiment persistence, and sentiment infectivity are characterized, and local attention cross fusion is performed. To learn dialogue sentiment globally, global attention is proposed to iteratively learn comprehensive sentiments from historical dialogues, and finally integrate with local attention. We conducted extensive experimental research on publicly available dialogue datasets. The experimental results show that, compared to the current state-of-the-art methods, our model improves by 3.5% in accuracy and 5.7% in Micro-F1 score.

To overcome the heterogeneous dynamics and unreliable communication which adversely effect the stable control for connected and automated vehicle platoons, a new intelligent control approach, named virtual order-degradation interconnection and damping assignment (VO-IDA), is proposed in this article. First, the internal stability of vehicle platoons is abstracted into a class of tracking control problems for general chained integral systems. By converting the chained integral system into standard closed-loop port-controlled Hamiltonian form, VO-IDA achieves asymptotic tracking through the integration of backstepping order degradation and virtual stabilization control techniques. This conversion effectively eliminates the dependence on preceding vehicular acceleration as well. Second, under heterogeneous dynamics, explicit stable domains of control parameters are provided to ensure the attenuation of string stability for vehicle platoons via Laplace transform. Furthermore, a linear-proportional relationship between heterogeneous and homogeneous dynamics regarding spacing error ratio is uncovered. Leveraging this relationship, a modified multiobjective genetic algorithm is employed to online explore target locations within stable domains, enabling VO-IDA to conduct stable and precise control under heterogeneous dynamics. Comparative experiments verify the superiority of this approach.

In this article, on the basis of an existing dual layer nested (DLN) adaptive sliding-mode control (ASMC) strategy, an observer-based sliding-mode control strategy with an improved DLN adaptive tuning mechanism (IDLN-ASMC) is proposed for a three-level neutral-point-clamped converter. The proposed controller not only ensures good system performance but also mitigates two problems of the existing DLN-ASMC strategy. Meanwhile, three objectives are achieved. First, an adaptive supertwisting algorithm is utilized in the power tracking loop to converge power tracking errors to bounded regions in finite time. Next, a disturbance observer-based IDLN-ASMC strategy is proposed in the dc-link voltage regulation loop to regulate the dc-link voltage to its reference value. Finally, a simple proportional-integral controller is used in the dc-link voltage-balancing loop to reduce the voltage difference between the two dc-link capacitors. The results of simulation and experiment demonstrate the effectiveness and superiority of the proposed strategy.

Reliable control schemes are critical to ensuring converter operation in microgrids. This work proposes a robust adaptive sliding mode control for the three-level neutral-point-clamped power converter with multidisturbances. Specifically, an adaptive observer-based proportional (P) voltage controller is proposed to accurately and quickly regulate dc-voltage in real-time identifying unknown equivalent dc-loads, compensating for the active power reference. To track the reference, a disturbance observer-based integral sliding mode controller (ISMC) is adopted to dramatically enhance the power tracking performance in case of parameter mismatches and bias caused by current path changes and switch mode noise. In addition, a sliding mode observer coupled withPcontrol is established to balance dc-link (two) capacitors, rejecting harmonic injection and power ripple behaviors. Experimental data confirm that the proposed control scheme outperforms super-twisting observer-based ISMC, super-twisting algorithm, and proportional–integral control schemes in the transient/steady state operations in terms of dynamic response, grid current harmonic distortions, and robustness.

High penetration of power converters may lead to power ripple, voltage swings, and weak antidisturbances for microgrids. Confronting these issues, this work proposes a robust control scheme, discrete-time super-twisting observer (DSTO)-embedded quasi-integral sliding-mode control (QISMC), for a three-level neutral-point-clamped power converter system, dramatically enhancing power/voltage regulation performance and antidisturbance capability. A fast convergence DSTO is deployed to offset multidisturbances caused by parameter mismatches, unknown loads, current path changes, switch mode noise, and self-compensating power/voltage tracking biases in QISMC. To further mitigate power/voltage steady-state error and boost system robustness, a new quasi-integral sliding-mode surface is built, inherently improving power/voltage tracking performance. Experimental data confirm that the proposed control outperforms the discrete-time extended-state-observer-based QISMC, DSTO-based quasi-sliding mode control, and discrete-time proportional–integral control in power/voltage, grid current harmonics, and robustness.

Lane detection is a vital task in the field of autonomous driving for it provides valuable information on drivable locations. However, complex scenarios like severe occlusion, discontinuous lane appearance, and illumination variation still hinder the accurate detection of lanes. This paper presents FlipNet, a novel and efficient neural network that detects lanes in complex environments by taking advantage of feature flip fusion and attention mechanism. First, a hierarchical feature flip fusion module (HFFF) is developed to utilize spatial information and aggregate global content. HFFF constructs a hierarchical structure consisting of multiple scales of sub-feature maps and uses flip fusion to pass spatial information in a two-way manner. Then, a double-layer attention enhancement mechanism (DAEM) and a dual-pooling coordinate attention (DCA) are proposed to enhance the features extracted by the encoder backbone. DAEM highlights valuable features and reduces background noise, which helps the network better capture the long-range dependent lane structure and be more robust in challenging scenarios. Experiments show our method achieves state-of-the-art performance and obtains new best results among segmentation-based methods in three popular lane detection benchmarks: CULane, Tusimple, and LLAMAS.

In realistic conversations, “responses” are closely related to persona and context. However, current personalized dialogue generation methods only focus on the consistency of the persona of responses and yet ignore context coherence, as may produce low-quality responses. To address the issue, we propose a novel model, named PCF (Persona and Context Fusion), which builds two decoders for understanding personality consistency and context coherence respectively on a common encoder-decoder architecture. In this model, an inter-layer attention fusion mechanism is designed for the two decoders to effectively fuse persona and context, and a decoupled way of training is conducted on an additional large-scale non-dialogue inference dataset to enhance the consistent understanding ability of the two decoders. Furthermore, considering that generating responses may be tedious, the ScaleGrad loss function is applied to enhance the diversity of responses. Experimental results on two publicly available datasets show that the dialogues generated by our PCF are significantly higher in quality than strong baselines.

Three-level neutral-point-clamped (3L-NPC) power converters are necessary interfaces to form micro-energy systems. Naturally, designing a suitable control scheme, featuring superior dynamics, strong robustness, and simple structure, is a promising solution to guarantee more efficient operation of the converter. This article proposes a robust high-quality current control strategy for the 3L-NPC power converter in the stationary$\alpha \beta$frame. A super-twisting algorithm coupled with a Luenberger observer current controller is proposed to deal with the poor sinusoidal current tracking issue due to the existing inductance/grid frequency deviations and the disturbance of the sinusoidal dynamic nature. Additionally, an extended sliding mode disturbance observer-based proportional control is built to dramatically enhance the voltage regulation performance, in the case of capacitance deviations and unknown dc-loads. Experimental data confirm the effectiveness of the proposed solution outperforms the conventional proportional-resonant/-integral control in terms of accurate tracking current/voltage, antidisturbance, and grid current total harmonic distortion.

Lane detection is critical for intelligent vehicles to sense drivable areas. Compared to general objects, lane lines are slender-shaped, easily occluded, or defaced. Therefore, the lane detection network requires a more robust ability for local detail extraction and global semantic information modeling. In this paper, we propose a novel lane detection network (FLAMNet) with a flexible line anchor mechanism, which constantly corrects the position of line anchors to improve detection performance and computational efficiency. Specifically, we utilize the Patch Pooling Aggregation Module (PPAM) to aggregate multi-scale semantic features extracted by the backbone network. The multi-scale features are subsequently inputted into DSAformer, which utilizes decomposed self-attention to establish global long-distance dependencies. The detection head leverages fused features of multi-scale global and local details to accurately fit the lane line by correcting the anchor position. Moreover, we propose the Horizontal Information Aggregation Module (HIAM) to expand the receptive field of line anchors horizontally, enhancing the line anchor representation ability to the topological structure of complex lane lines. The experimental results on mainstream lane detection benchmark datasets demonstrate that the proposed FLAMNet outperforms existing methods. We have uploaded the code and demo of FLAMNet on GitHub at:https://github.com/RanHao-cq/FLAMNet.

In the recommendation system, click-through rate (CTR) prediction is a popular research direction. Aiming at the problem of excessive compression of features in Factorization Machine (FM) and its variant models, a recommendation model that combines feature interaction enhancement and multi-head self-attention is proposed. Hadamard product, feature vector splicing and multi-layer perception network methods are used for low-level feature vector interactive processing in this paper, and multi-head self-attention mechanism and residual network model for high-level feature interactive processing are used. By designing the fusion mechanism, the parallel low-order feature interaction network and the high-order feature interaction network are merged. The experimental results on the four benchmark data sets show that the multi-head self-attention model based on high-order feature interaction enhancement proposed in this paper outperforms existing models in terms of click-through rate prediction accuracy.

Conversational recommender system (CRS) allows agent to understand the conversation with user and give recommendations after multi-turn dialogues. However, there are still two limitations in existing CRS: (1) improper words or items may be chosen for the given topic in the generation, and (2) the contextual information of items in the recommendation is not rationally explored. To solve these issues, we proposed a Keyword-guided Topic-oriented CRS model (KGTO), which captures more accurate topic by extracting keywords through the hierarchical attention mechanism, and enriches the contextual information of items by fusing the co-occurrence graph with the knowledge graph. Moreover, a generative module can select words or items supplemented topic information to generate proper responses. Extensive experiments on the task-oriented dialogue dataset prove that our model performs well in recommendation effectiveness and dialogue informativeness.

Dialogue has received a lot of research. But there is very little research on dialogue sentiment forecasting, which aims to forecast the sentimental polarity of what the interlocutor is about to say and provides sentimental guidance for empathic dialogue generation. Since the sentence has not been spoken, the vector of the sentence can't be directly obtained. And according to cognitive science, emotions are different from sentiment, but there is an internal connection. Therefore, our paper proposes an Emotion-Assisted Sentiment Forecasting (EASF) model based on attention to integrating these goals. Our model uses attention to capture the significant content of emotions and sentiment, and emotion assistance can obtain the emotional change, then this change is used to assist in the analysis of the polarity of the sentiment. Experimental results show that EASF significantly outperforms all baselines.

In order to obtain a simple and efficient control strategy for three-phase two-level grid-connected power converters with improved system performance including reduced computation and communication burdens, an event-triggered continuous control set-model predictive control (CCS-MPC) is proposed in this paper. In the DC-link voltage regulation loop, a simple but efficient controller is designed to track the DC-link voltage to its reference value. In the power tracking loop, a simple event-triggered CCS-MPC is utilized to ensure that the active power and reactive power also track their reference values. The control signals to the converter are updated and transmitted only when the triggering condition is satisfied. Compared with periodic sampling control strategies, which require the calculation and transmission of control signals in each sampling period, the proposed controller reduces the utilization of limited computation and communication resources while maintaining good tracking performance. By comparing with the periodic sampling proportional-integral strategy, the effectiveness and superiority of the proposed strategy are shown through simulation results.

Recommender systems based on collaborative filtering has always suffered from sparsity and cold start problems. Therefore, researchers attempt to address the issues with various side information such as user profiles and item attributes. In this paper, we proposed Graph-aware Collaborative Filtering (GCF), an end-to-end framework, in which user-item bipartite graph and the knowledge graph of items (side information) are integrated to improve recommendation performance. In GCF, we aggregate the neighbors in the candidate item knowledge graph to refine the item representation. Similarly, we aggregate the user interaction neighbors in the user-item bipartite graph to refine the user representation. The collaborative signals in the knowledge graph and user-item bipartite graph are successfully captured through the neighborhood aggregation operation. Experimental results on three real datasets indicate that the proposed GCF is superior to the existing models in terms of accuracy and can also effectively solve the data sparsity problem of the recommender system.

This paper presents voltage regulation and current tracking control strategies for three phase two-level grid-connected power converters. By using power-invariant Park's transformation, an averaged mathematical model of power converters is obtained in dq synchronous reference frame. Then a novel control strategy using adaptive control and H∞technique is proposed to regulate the dc-link output voltage as well as track a desired current reference for three-phase power rectifiers. More specifically, an efficient adaptive controller is established in the external loop for regulating dc-link output voltage in the presence of external disturbances. A set of H∞controllers are designed in the internal loop to force the input currents track their desired values. Finally, simulation results obtained from the proposed control method are presented, analyzed, and compared with that of sliding mode control, and the superiority of the proposed control laws is verified.

In view of the problems of supervised machine learning methods, such as low accuracy, long training time, complicated models, and poor versatility, this paper proposes a method for discovering ECG patterns based on local repeatability. By using the sliding window technique, the patterns contained in the ECG time series data are mined; by using the pattern matching technique, a method for improving the similarity of the ECG time series is explored. The paper implements an ECG pattern discovery algorithm based on local repeatability, accurately calculates the similarity between two ECG patterns, and performs clustering and labeling based on these similarities. Experimental results show that the method proposed in this paper is superior to the existing methods in terms of accuracy of pattern discovery and stability of pattern discovery.

Customer service question similarity calculation is a key technology in the development of intelligent electronic customer service system, and its main challenge comes from how to find the correlation between words. In response to this challenge, the paper proposes a weighted text similarity calculation method based self-attention. The paper uses deep neural network BiLSTM and self-attention vectors to carry out text similarity research, and explores the problem of deep neural network and self-attention vectors describing the semantic relationship between words. The research of this paper is of great significance to improve the service quality of the intelligent electronic customer service system, and provides new ideas for the accurate comparison of text semantics. The paper takes the semantically vague and complex Chinese text as the research object, and uses the deep neural network structure design, self-attention vector calculation, dynamic weighting, and synchronization comparison as processing methods. Combined with the development of the Weizhong bank intelligent electronic customer service system, an intelligent electronic Customer service question matching experiment platform is constructed. Experimental results show that the dynamic weighted self-attention text similarity calculation model is superior to the existing models in terms of calculation accuracy and running time. It has certain reference value for the development of similar intelligent electronic customer service systems.

Coordination and control of actions using sensors on the robot is the key technology for robots to become intelligent. Aiming at the communication and control problems of existing sensor robots, an object-oriented data communication framework based on OIO middleware is proposed. Through the research of serialization and deserialization of communication data, the problems of coordinated advancement, climbing, and turning of sensor robot clusters are explored, and the law of object data and intelligent control instruction transmission is revealed. The research in the paper provides new ideas for the development of sensor robot motion coordination and control modules, and promotes the intelligentization of sensor robots. The paper designs OIO middleware that can be used for sensor robot cluster communication and control, and regards the sensor robot as an object that encapsulates attributes and methods, and performs intelligent control based on object-oriented data. Experimental research on dual-robot and multi-robot collaborative climbing, collaborative turning, and collaborative obstacle avoidance based on OIO middleware was carried out. The experimental results show that this method simplifies the communication and control of the robot cluster and improves the control effect.

This paper presents an adaptive sliding mode observer (ASMO) to estimate three-phase grid voltage parameters, including both positive and negative sequences of voltage and grid frequency under unbalanced grid faults. First, the dynamic of three-phase voltage is reformulated as the second-order uncertain system, which can transform the traditional phase locked loop problem to the observer design problem. Based on the obtained dynamic system, an ASMO is constructed to estimate three-phase grid voltage parameters, using the adaptive and sliding mode techniques. The stability of the overall system including the observer estimation errors, sliding variable and adaptive estimation errors is rigorously proved by Lyapunov stability theory. The performance of proposed observer is assessed for estimation of three-phase grid voltage parameters by simulation in which two types of faults, i.e., the amplitude of voltage and grid frequency variations. are considered.

In this paper, a current sensor-less control strategy for boost dc/dc converter is proposed. A switched observer is first designed for switched model of boost converter to estimate the inductor current and output voltage under arbitrary switching. Then based on the estimation of inductor current and output voltage, a two-loop control structure is employed for the average model of boost converter which consists of voltage loop (outer loop) and current loop (inner loop). In the inner loop, a second order sliding mode (SOSM) controller based on a super-twisting algorithm (STA) is established to drive the estimated inductor current towards its reference. The proportional-integral (PI) controller is applied in the outer loop to regulate the output voltage. Finally simulation results are provided to testify the effectiveness of the presented approach.

This paper presents a novel control scheme for DC-DC boost converter, maintaining the desirable voltage regulation performance under high load variation and large change of voltage reference. The model of converter is reformulated, in which the unknown equivalent load, input voltage, model uncertainties and unmodeled dynamics are lumped as external disturbance. The control strategy is designed with backstepping control technology, similar to the cascade control method in which the intermediate variable is introduced to fast respond the control demand, effectively dealing with the nonlinearity of the boost converter dynamics. The disturbance observers are established to estimate the lumped disturbances, rejecting disturbances and removing steady-state errors to improve the closed-loop performance. The simulation results demonstrate that the proposed control strategy, backstepping control combined with disturbance observer, provides lots of advantages superior to the conventional PI control such as faster dynamic response and less output voltage drop.

A new approach to the control of three-phase two-level grid-connected power converters is proposed in this paper. The proposed control is an extended state observer (ESO)based second order sliding mode (SOSM), which comprises two control loops: the outer loop is a voltage regulation loop, as well as inner loop is an instantaneous power tracking loop. The outer loop is accomplished by an H∞controller plus an ESO, which is designed to regulate dc-link capacitor voltage of the converter and asymptotically reject external disturbances and parameter perturbations. The SOSM strategy is employed in the inner loop to drive the active and reactive power convergence to their desired values. Control objectives of nearly unity power factor and dc-link capacitor voltage regulation are simultaneously satisfied. Availability of the ESO-based SOSM is compared with the classic proportional-integral control in simulations, and the comparison implies that the proposed strategy not merely achieves an almost perfect tracking performance, but also provides a complete robustness against resistance load variation.

In this paper, a novel scheme of disturbance observer based second order sliding mode (SOSM) control for DC-DC buck converters is proposed. A cascade-control structure is established to regulate the output voltage and force the inductor current to track its reference, which comprises two control loops. The voltage regulation loop which is based on an SOSM controller combined with extended state observer (ESO) is the external loop. The current tracking loop also accomplished by SOSM controller is the internal loop. The fast motion is dominated by the dynamics of the current tracking loop whereas the slow motion stems from the dynamics of the output voltage. In addition, the load resistance that influences significantly the dynamics of whole system is regarded as the external disturbance in this papper. A disturbance observer, ESO, aims at asymptotically rejecting disturbances to converter. The proposed control strategy is verified using simulation test.

In this paper, the problem of switching stabilization for a class of switched nonlinear systems is studied by using average dwell time (ADT) switching, where the subsystems are possibly all unstable. First, a new concept of ADT is given, which is different from the traditional definition of ADT. Based on the new proposed switching signals, a sufficient condition of stabilization for switched nonlinear systems with unstable subsystems is derived. Then, the T-S fuzzy modeling approach is applied to represent the underlying nonlinear system to make the obtained condition easily verified. A novel multiple quadratic Lyapunov function approach is also proposed, by which some conditions are provided in terms of a set of linear matrix inequalities to guarantee the derived T-S fuzzy system to be asymptotically stable. Finally, a numerical example is given to demonstrate the effectiveness of our developed results.

This paper is concerned with the control problem for a class of switched nonlinear systems possibly composed of all unstable modes by using time-controlled switching signals. To tackle the problem, a new mode-dependent average dwell time (MDADT) switching property is proposed, which is different from the existing one in the literature. Then, the stabilization condition under such MDADT switching signals is established for the switched nonlinear systems with possibly all unstable subsystems. By proposing a class of time-scheduled multiple quadratic Lyapunov function and applying T–S fuzzy models to represent the underlying nonlinear subsystems, numerically easily verified stabilization conditions are further derived in the form of linear matrix inequalities. A numerical example is finally provided to illustrate the effectiveness of the obtained theoretical results.