IEEE Transactions on Cybernetics最新文献_第4页

Flexible Performance Control Under Constrained Actuation for Nonsquare Nonlinear Systems With Controllability Relaxation. 具有可控性松弛的非平方非线性系统约束驱动下的柔性性能控制。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-22 DOI: 10.1109/TCYB.2026.3731177

Bing Zhou, Kai Zhao, Yongduan Song, Lihua Xie

{"title":"Flexible Performance Control Under Constrained Actuation for Nonsquare Nonlinear Systems With Controllability Relaxation.","authors":"Bing Zhou, Kai Zhao, Yongduan Song, Lihua Xie","doi":"10.1109/TCYB.2026.3731177","DOIUrl":"https://doi.org/10.1109/TCYB.2026.3731177","url":null,"abstract":"Prescribed performance control (PPC) for nonsquare nonlinear systems with unknown time-varying control gains and actuator constraints remains largely unexplored. This article addresses this problem by integrating a relaxed controllability condition with a flexible performance control framework based on saturation deficiency. Specifically, a refined matrix decomposition and transformation are employed to relax the controllability conditions for uncertain nonsquare nonlinear systems. Subsequently, the original system is augmented with constructed saturation auxiliary systems, which not only alleviate the effects of nonsmooth saturated inputs but also facilitate the backstepping control design under actuator saturation. To balance actuator constraints and performance requirements, we design a tunnel-shaped prescribed-time performance function (PTPF) equipped with saturation awareness capability. This function flexibly extends the performance boundaries during saturation, ensuring that the tracking error remains within the prescribed constraints while placing no restrictions on the saturation level. Both theoretical analysis and over-actuated spacecraft simulations confirm the proposed strategy's capability to achieve flexible prescribed tracking performance under actuator constraints.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149038424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Secure Asynchronous Impulsive Control of Nonlinear Multiagent Systems Under Deception Attacks. 欺骗攻击下非线性多智能体系统的安全异步脉冲控制。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-21 DOI: 10.1109/TCYB.2026.3731803

Yufan Chen, Yuchao Xiong, Mengqi Xue, Yue Song

引用次数: 0

Practical Prescribed-Time Fully Actuated Tracking Control for 2-DOF Pneumatic Parallel Mechanism With Input Saturation. 具有输入饱和的2自由度气动并联机构的实用规定时间全驱动跟踪控制。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-21 DOI: 10.1109/TCYB.2026.3732042

Yipeng Cao, Li Li, Changchun Hua, Jiaping Qiang

引用次数: 0

Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding. 基于视觉的机器人解布六自由度抓取姿态估计。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-21 DOI: 10.1109/TCYB.2026.3732543

Domen Tabernik, Peter Nimac, Jan Jericevic, Danijel Skocaj, Andrej Gams

{"title":"Vision-Based 6-DoF Grasp Pose Estimation for Robot Cloth Unfolding.","authors":"Domen Tabernik, Peter Nimac, Jan Jericevic, Danijel Skocaj, Andrej Gams","doi":"10.1109/TCYB.2026.3732543","DOIUrl":"10.1109/TCYB.2026.3732543","url":null,"abstract":"Cloth manipulation is a challenging task due to the deformable and high-dimensional nature of cloth, which leads to complex interaction dynamics and perceptual ambiguity arising from frequent occlusions of critical visual cues, such as folds, edges, and grasp points. In this work, we tackle cloth unfolding using a regrasping-in-the-air strategy, where one manipulator holds the cloth while the other grasps it at an optimally selected point to unfold it. To this end, we propose center direction regression network (CeDiRNet)-6DoF, a deep learning framework that jointly predicts effective grasp points and the complete 6-DoF grasp pose from the observed cloth configuration. By integrating dense 3-D grasp regression with segmentation and sine-cosine-encoded Euler angles, the proposed method reliably estimates the grasp configuration that maximizes the unfolded cloth area. We extensively evaluated CeDiRNet-6DoF on a bimanual robotic setup within the ICRA 2024 Cloth Competition framework, achieving state-of-the-art performance. An ablation study further validates the benefits of key design components, including joint segmentation, background randomization, and image cropping. These results establish CeDiRNet-6DoF as a robust and versatile foundation for reliable robotic cloth manipulation in unstructured environments.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149030280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Fast Node Communication Protocol With Local Leader Selection for Community Detection in Large-Scale Complex Networks. 大规模复杂网络社区检测中一种具有本地Leader选择的快速节点通信协议。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-17 DOI: 10.1109/TCYB.2026.3732323

Mohamed Amine Midoun, Djamel Eddine Mekkaoui, Sen Qiu, Mohamed Zakariya Talhaoui, Abdelkarim Smaili, Ling-Ping Cen

{"title":"A Fast Node Communication Protocol With Local Leader Selection for Community Detection in Large-Scale Complex Networks.","authors":"Mohamed Amine Midoun, Djamel Eddine Mekkaoui, Sen Qiu, Mohamed Zakariya Talhaoui, Abdelkarim Smaili, Ling-Ping Cen","doi":"10.1109/TCYB.2026.3732323","DOIUrl":"10.1109/TCYB.2026.3732323","url":null,"abstract":"In the field of cybernetics, understanding the structural intricacies of complex networks is essential for advancing computational intelligence and networked systems. One of the biggest challenges in this domain is the accurate detection of community structures, which help reveal the underlying organization and functionality of these networks. However, community detection (CD) algorithms usually suffer from the accuracy-time tradeoff, where high accuracy often comes at the cost of high computational time, while faster algorithms often lose precision. Moreover, most of the current methods lack stability, ignore information flow beyond neighbors, and are limited to unweighted networks. Motivated by routing approaches, communication protocols, and principles of graph theory, this article addresses the above limitations by introducing a fast node communication protocol for CD (NCP-CD). To achieve stability, we propose a novel local leader selection (LLS) technique that identifies key nodes without requiring predefined parameters. Moreover, this article proposes a new connectivity strength (CS) metric to accurately measure the connectivity between both adjacent and nonadjacent nodes in weighted networks. Using LLS and CS, NCP-CD detects high-quality community structures by establishing a new packet exchange mechanism between nodes in a distributed architecture. This mechanism, combined with an innovative port-specific optimization technique, enables NCP-CD to achieve a fast execution speed, even in large-scale networks. Extensive experiments on both synthetic and real-world networks show that NCP-CD significantly outperforms several baseline and state-of-the-art algorithms with respect to both accuracy and computational speed.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149030609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A SAGE-GAT Hybrid Network With Dynamic Node Interaction for Fault Diagnosis of Civil Aircraft Landing Gear System. 基于动态节点交互的SAGE-GAT混合网络用于民用飞机起落架系统故障诊断。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-17 DOI: 10.1109/TCYB.2026.3731823

Tingqian Tu, Mengjie Zeng, Ningyun Lu, Jiayi Huang, Bin Jiang

{"title":"A SAGE-GAT Hybrid Network With Dynamic Node Interaction for Fault Diagnosis of Civil Aircraft Landing Gear System.","authors":"Tingqian Tu, Mengjie Zeng, Ningyun Lu, Jiayi Huang, Bin Jiang","doi":"10.1109/TCYB.2026.3731823","DOIUrl":"10.1109/TCYB.2026.3731823","url":null,"abstract":"Fault diagnosis of civil aircraft landing gear systems is critically hindered by high-dimensional electromechanical coupling, which leads to confusing faults where distinct failures manifest similar sensor patterns. While graph neural networks (GNNs) can model system topology, standard approaches rely on static or local attention and fail to capture the higher order dynamic interactions essential for distinguishing such faults. We propose a novel SAGE-GAT Hybrid Network enhanced with a dynamic node interaction attention (DNIA) mechanism. This core innovation explicitly integrates domain-informed confusion nodes, allowing the model to dynamically recalibrate attention weights based on fault-specific topological signatures. The method is rigorously validated using a comprehensive evaluation framework comprising a high-fidelity simulation testbed driven by real flight data across multiple runway conditions and two real-world datasets from operational civil aircraft fleets. The proposed network demonstrates superior performance over state-of-the-art (SOTA) baselines, achieving high accuracy in disambiguating confusing faults while maintaining practical training efficiency, thereby offering a robust and applicable solution for aviation maintenance.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148989772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Periodic Event-Triggered SMC for Unknown Linear Systems Under Dual-Channel FDI Attacks: A Data-Based Method. 双通道FDI攻击下未知线性系统的周期事件触发SMC：基于数据的方法。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-17 DOI: 10.1109/TCYB.2026.3732376

Ning Zhang, Yugang Niu, Jun Song

{"title":"Periodic Event-Triggered SMC for Unknown Linear Systems Under Dual-Channel FDI Attacks: A Data-Based Method.","authors":"Ning Zhang, Yugang Niu, Jun Song","doi":"10.1109/TCYB.2026.3732376","DOIUrl":"10.1109/TCYB.2026.3732376","url":null,"abstract":"This work considers the problem of event-triggered sliding mode secure control for unknown linear systems, in which the transmission of sampled states is regulated via a periodic event-triggered mechanism (ETM); meanwhile, the false data injection (FDI) attack may occur in the dual channels (S/C and C/A channels). First, an event-triggered sliding mode controller is designed, and the model-based sufficient conditions are derived to guarantee the boundedness of the closed-loop system and the reachability of the sliding surface. Since the actual system parameters may not be completely known/available for the controller, this work shall further focus on the following cases: the system parameters are completely unknown or partially unknown. By introducing the data-based representations for various cases (i.e., the system parameters are completely unknown and partially unknown), the above model-based sufficient conditions are transformed into the data-based forms or the combination forms of data and partially known parameters, under which the designed secure controller and ETM can be implemented via system data and partially known system parameters. Compared with traditional model-based methods, the core advantage of the proposed data-based control scheme lies in completely eliminating the reliance on precise mathematical models and designing the controller solely using offline collected input/state data and partially available parameters. Finally, simulation results are provided to illustrate the proposed data-based control scheme.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149038440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FK-Net: Frequency-Aware and Kernelizable Mamba-Transformer for Multispectral and Hyperspectral Image Fusion. 用于多光谱和高光谱图像融合的频率感知和可核化曼巴变换。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-16 DOI: 10.1109/TCYB.2026.3723099

Mingjin Zhang, Zhongkai Yang, Jie Guo, Yunsong Li, Xinbo Gao

{"title":"FK-Net: Frequency-Aware and Kernelizable Mamba-Transformer for Multispectral and Hyperspectral Image Fusion.","authors":"Mingjin Zhang, Zhongkai Yang, Jie Guo, Yunsong Li, Xinbo Gao","doi":"10.1109/TCYB.2026.3723099","DOIUrl":"10.1109/TCYB.2026.3723099","url":null,"abstract":"Multispectral and hyperspectral image fusion (MHIF) is dedicated to fusing high-resolution multispectral images and low-resolution hyperspectral images (LR-HSIs) for conversion into high-resolution hyperspectral images. Nevertheless, the prevalent methods exhibit limitations in capturing the interactions between spatial and spectral features. This inadequacy results in the suboptimal utilization of spatial-spectral information from high-resolution multispectral image (HR-MSI) and LR-HSI, as well as the ineffective preservation of their distinctive characteristics. To address this issue, we propose a frequency-aware and kernelizable mamba-transformer network (FK-Net) for MHIF. Specifically, we first design a frequency-aware dual-mamba (FADM) fusion module, which uses the frequency information of two images dynamically extracted by Fourier transform to supervise and guide the scanning process and effectively realizes the cross-modal information fusion of HR-MSI and LR-HSI. Furthermore, we introduce a robust and spectral-friendly similarity metric, i.e., the spectral correlation coefficient (SCC) of the spectrum, to replace the original attention matrix and incorporate inductive biases into the model to facilitate training. Built upon it, we further utilize the kernelizable attention technique with theoretical support to form a novel efficient SCC-kernel-based self-attention (ESSA) and reduce attention computation to linear complexity. The proposed FK-Net effectively integrates the complementary spatial-spectral information from both modalities while preserving their inherent uniqueness, enabling the generation of more natural high-resolution images without significantly increasing computational complexity. The qualitative and quantitative experiments demonstrate the superiority of the proposed method over the state-of-the-art (SOTA) approaches.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149038287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scalable Adaptive Fuzzy Voltage Control for DC Microgrids With Plug-and-Play Operations and Constant Power Loads. 即插即用和恒负荷直流微电网的可扩展自适应模糊电压控制。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-16 DOI: 10.1109/TCYB.2026.3732087

Aimin Wang, Minrui Fei, Dajun Du, Dakui Wu, Chen Peng, Kang Li

{"title":"Scalable Adaptive Fuzzy Voltage Control for DC Microgrids With Plug-and-Play Operations and Constant Power Loads.","authors":"Aimin Wang, Minrui Fei, Dajun Du, Dakui Wu, Chen Peng, Kang Li","doi":"10.1109/TCYB.2026.3732087","DOIUrl":"10.1109/TCYB.2026.3732087","url":null,"abstract":"Voltage stability in DC microgrids (DCMGs) is challenged by the concurrent effects of topological variations arising from plug-and-play (PnP) operations of distributed generation units (DGUs) and nonlinear destabilization induced by constant power loads (CPLs). This article proposes a scalable adaptive fuzzy voltage control (SAFVC) strategy for multibus DCMGs with unknown CPL dynamics and changing electrical interconnection configurations. Afuzzy logic system (FLS) approximates the physical CPL current online without requiring prior CPL information. Because the CPL and converter-voltage input act through unmatched channels, a command-filtered adaptive backstepping architecture first constructs a virtual filter-current command and then realizes it through the converter voltage. Acommon voltage-energy weighting decomposes the aggregate line contribution into a nonpositive Laplacian term and an explicit bounded bias induced by nonuniform voltage references while preserving fully decentralized implementation. Explicit local gain and filter conditions provide an admissibility test for PnP requests and guarantee practical finite-time stability without redesigning unaffected controllers. Numerical simulations demonstrate the performance of the proposed strategy.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149038366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Event-Triggered Probability-Guaranteed State Estimation for Uncertain Complex Networks: A Compression-Decompression Framework. 不确定复杂网络的事件触发概率保证状态估计：一个压缩-解压缩框架。

IF 11.3 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2026-09-16 DOI: 10.1109/TCYB.2026.3730969

Yuhang Jin, Zidong Wang, Weihao Song, Yun Chen

{"title":"Event-Triggered Probability-Guaranteed State Estimation for Uncertain Complex Networks: A Compression-Decompression Framework.","authors":"Yuhang Jin, Zidong Wang, Weihao Song, Yun Chen","doi":"10.1109/TCYB.2026.3730969","DOIUrl":"10.1109/TCYB.2026.3730969","url":null,"abstract":"The probability-guaranteed event-triggered state estimation problem is studied for a class of complex networks (CNs) with uncertain inner coupling strengths under compression-decompression mechanisms (CDMs). An event-triggered transmission scheme (ETTS) is introduced to regulate data exchange, while compression-induced distortions are explicitly incorporated into the estimation model. The theoretical objective is to establish probability-guaranteed boundedness of the estimation error over a finite horizon in the presence of stochastic coupling uncertainties. To this end, a truncated hyper-rectangle is constructed to characterize the uncertain parameters with a prescribed confidence level, thereby enabling a probabilistic reformulation of the performance requirement. By employing matrix inequality techniques, sufficient conditions are derived to ensure the boundedness of the estimation error in a probabilistic sense. The resulting conditions lead to a recursive estimator synthesis expressed in terms of linear matrix inequalities (LMIs). A numerical example is finally presented to verify the theoretical results.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":11.3,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149038333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0