This article presents a double-channel (sensor-to-controller channel and controller-to-actuator channel) event triggered control method for nonlinear interconnected systems subject to sensor and actuator faults via the backstepping technique. It should be emphasized that the utilization of triggering mechanism at the sensor side poses a challenge to the design of backstepping control, as it leads to nondifferentiable virtual control signals due to the discontinuous nature of the state/output signals received at the controller side. In contrast to existing methods, the proposed event triggering mechanism eliminates the need for computing virtual control signals at the sensor side before transmitting them to the controller side. By establishing the relationships of the corresponding variables in two communication scenarios (namely, without and with event triggering) and introducing dynamic filtering technique, the problem of nondifferentiable virtual control signals in backstepping design is solved. We present a numerical case study to validate the effectiveness and advantages of the proposed decentralized event triggered control approach.
{"title":"Output-Based Decentralized Adaptive Event-Triggered Control of Interconnected Systems With Sensor/Actuator Failures","authors":"Zhirong Zhang;Changyun Wen;Long Chen;Yongduan Song;Bowen Peng;Gang Feng","doi":"10.1109/TCYB.2024.3498071","DOIUrl":"10.1109/TCYB.2024.3498071","url":null,"abstract":"This article presents a double-channel (sensor-to-controller channel and controller-to-actuator channel) event triggered control method for nonlinear interconnected systems subject to sensor and actuator faults via the backstepping technique. It should be emphasized that the utilization of triggering mechanism at the sensor side poses a challenge to the design of backstepping control, as it leads to nondifferentiable virtual control signals due to the discontinuous nature of the state/output signals received at the controller side. In contrast to existing methods, the proposed event triggering mechanism eliminates the need for computing virtual control signals at the sensor side before transmitting them to the controller side. By establishing the relationships of the corresponding variables in two communication scenarios (namely, without and with event triggering) and introducing dynamic filtering technique, the problem of nondifferentiable virtual control signals in backstepping design is solved. We present a numerical case study to validate the effectiveness and advantages of the proposed decentralized event triggered control approach.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 2","pages":"550-561"},"PeriodicalIF":9.4,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142753016","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}
Pub Date : 2024-11-26DOI: 10.1109/TCYB.2024.3489605
Hang Yu;Jiahao Wen;Yiping Sun;Xiao Wei;Jie Lu
One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN’s parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.
{"title":"CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data","authors":"Hang Yu;Jiahao Wen;Yiping Sun;Xiao Wei;Jie Lu","doi":"10.1109/TCYB.2024.3489605","DOIUrl":"10.1109/TCYB.2024.3489605","url":null,"abstract":"One challenge of learning from streaming data is that only a limited number of labeled examples are available, making semi-supervised learning (SSL) algorithms becoming an efficient tool for streaming data mining. Recently, the graph-based SSL algorithms have been proposed to improve SSL performance because the graph structure can utilize the interactivity between surrounding nodes. However, graph-based SSL algorithms have two main limitations when applied to streaming data. First, not all the labels of the data in the streaming data may be reliable, and direct classification using a graph can lead to suboptimal performance. Second, graph-based SSL algorithms assume the structure of the graph is static, but the learning environment of streaming data is dynamic. Hence, we propose a competence-aware graph neural network (CA-GNN) to deal with these two limitations. Unlike other models, CA-GNN does not directly rely on graph information that could include mislabeled nodes. Instead, a competence model is used to explore latent semantic correlations in the streaming data and capture the reliability for each data. A streaming learning strategy then evolves CA-GNN’s parameters to capture the dynamism of the graph sequences. We conducted experiments using seven real datasets and four synthetic datasets, respectively, and compared the outcomes across various methods. The results demonstrate that CA-GNN classifies streaming data more effectively than the state-of-the-art (SOTA) methods.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 2","pages":"684-697"},"PeriodicalIF":9.4,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142718279","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}
This work investigates the time-varying formation-tracking problem of multiagent systems under hybrid attacks, including denial-of-service (DoS) attacks and actuation attacks. State estimators are designed for each node of the swarm leveraging relative information from neighboring estimators to generate the desired positional states for formation tracking. The direct use of corrupted consensus control inputs is avoided, thereby defending against actuation attacks targeted at node input signals. Furthermore, we propose an event-triggered protocol with a sampling mechanism to enhance resilience against DoS attacks on communication with neighboring estimators equipped with a topology recovery policy. This resilient protocol against DoS attacks is fully distributed and does not require prior knowledge of network topology, making it scalable to large networks. Finally, an adaptive attack-resilient control scheme is introduced to counteract potential unbounded actuation attacks via output feedback, enabling each follower to track the positional states provided by the distributed estimators. The tracking error is proven to be uniformly ultimately bounded. The proposed event-triggered hierarchical control scheme is validated through its application to spacecraft formation.
{"title":"Resilient Time-Varying Formation-Tracking of Multiagent Systems Against Hybrid Attacks With Applications to Spacecraft Formation","authors":"Yukang Cui;Yihui Huang;Qin Zhao;Xian Yu;Tingwen Huang","doi":"10.1109/TCYB.2024.3492035","DOIUrl":"10.1109/TCYB.2024.3492035","url":null,"abstract":"This work investigates the time-varying formation-tracking problem of multiagent systems under hybrid attacks, including denial-of-service (DoS) attacks and actuation attacks. State estimators are designed for each node of the swarm leveraging relative information from neighboring estimators to generate the desired positional states for formation tracking. The direct use of corrupted consensus control inputs is avoided, thereby defending against actuation attacks targeted at node input signals. Furthermore, we propose an event-triggered protocol with a sampling mechanism to enhance resilience against DoS attacks on communication with neighboring estimators equipped with a topology recovery policy. This resilient protocol against DoS attacks is fully distributed and does not require prior knowledge of network topology, making it scalable to large networks. Finally, an adaptive attack-resilient control scheme is introduced to counteract potential unbounded actuation attacks via output feedback, enabling each follower to track the positional states provided by the distributed estimators. The tracking error is proven to be uniformly ultimately bounded. The proposed event-triggered hierarchical control scheme is validated through its application to spacecraft formation.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 2","pages":"625-637"},"PeriodicalIF":9.4,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142718307","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}
Pub Date : 2024-11-22DOI: 10.1109/TCYB.2024.3492075
Dejun Xu;Kai Ye;Zimo Zheng;Tao Zhou;Gary G. Yen;Min Jiang
Bilevel optimization problems (BLOPs) are characterized by an interactive hierarchical structure, where the upper level seeks to optimize its strategy while simultaneously considering the response of the lower level. Evolutionary algorithms are commonly used to solve complex bilevel problems in practical scenarios, but they face significant resource consumption challenges due to the nested structure imposed by the implicit lower-level optimality condition. This challenge becomes even more pronounced as problem dimensions increase. Although recent methods have enhanced bilevel convergence through task-level knowledge sharing, further efficiency improvements are still hindered by redundant lower-level iterations that consume excessive resources while generating unpromising solutions. To overcome this challenge, this article proposes an efficient dynamic resource allocation framework for evolutionary bilevel optimization, named DRC-BLEA. Compared to existing approaches, DRC-BLEA introduces a novel competitive quasi-parallel paradigm, in which multiple lower-level optimization tasks, derived from different upper-level individuals, compete for resources. A continuously updated selection probability is used to prioritize execution opportunities to promising tasks. Additionally, a cooperation mechanism is integrated within the competitive framework to further enhance efficiency and prevent premature convergence. Experimental results compared with chosen state-of-the-art algorithms demonstrate the effectiveness of the proposed method. Specifically, DRC-BLEA achieves competitive accuracy across diverse problem sets and real-world scenarios, while significantly reducing the number of function evaluations and overall running time.
{"title":"An Efficient Dynamic Resource Allocation Framework for Evolutionary Bilevel Optimization","authors":"Dejun Xu;Kai Ye;Zimo Zheng;Tao Zhou;Gary G. Yen;Min Jiang","doi":"10.1109/TCYB.2024.3492075","DOIUrl":"10.1109/TCYB.2024.3492075","url":null,"abstract":"Bilevel optimization problems (BLOPs) are characterized by an interactive hierarchical structure, where the upper level seeks to optimize its strategy while simultaneously considering the response of the lower level. Evolutionary algorithms are commonly used to solve complex bilevel problems in practical scenarios, but they face significant resource consumption challenges due to the nested structure imposed by the implicit lower-level optimality condition. This challenge becomes even more pronounced as problem dimensions increase. Although recent methods have enhanced bilevel convergence through task-level knowledge sharing, further efficiency improvements are still hindered by redundant lower-level iterations that consume excessive resources while generating unpromising solutions. To overcome this challenge, this article proposes an efficient dynamic resource allocation framework for evolutionary bilevel optimization, named DRC-BLEA. Compared to existing approaches, DRC-BLEA introduces a novel competitive quasi-parallel paradigm, in which multiple lower-level optimization tasks, derived from different upper-level individuals, compete for resources. A continuously updated selection probability is used to prioritize execution opportunities to promising tasks. Additionally, a cooperation mechanism is integrated within the competitive framework to further enhance efficiency and prevent premature convergence. Experimental results compared with chosen state-of-the-art algorithms demonstrate the effectiveness of the proposed method. Specifically, DRC-BLEA achieves competitive accuracy across diverse problem sets and real-world scenarios, while significantly reducing the number of function evaluations and overall running time.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 2","pages":"726-739"},"PeriodicalIF":9.4,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142690982","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}
Pub Date : 2024-11-22DOI: 10.1109/TCYB.2024.3491177
Kun Li;Yujuan Wang;Gangshan Jing;Yongduan Song;Lihua Xie
Angle-constrained formation control has garnered significant attention owing to the advantage of interedge angles invariant under translation, rotation, and scaling. However, most existing approaches addressing this problem are applicable only to single- or double-integrator dynamics, which are often impractical in real-world scenarios. In this article, an angle rigidity-based adaptive formation control framework is introduced for nonlinear multiagent systems subject to mismatched uncertainties. The proposed control framework integrates a prescribed performance control approach with a recursive backstepping procedure, offering several key advantages: the capability to handle unmatched system uncertainties, the preservation of angle rigidity throughout the formation process, and the assurance that the triangulated formation shape is asymptotically achieved without risking collisions between neighboring agents. Furthermore, since the control input of each agent only requires local information related to its neighbors, which can be obtained locally from its own sensors, the proposed control method can be deployed in a communication-free environment. The effectiveness of the proposed control algorithms is validated by extensive numerical simulation.
{"title":"Angle Rigidity-Based Communication-Free Adaptive Formation Control for Nonlinear Multiagent Systems With Prescribed Performance","authors":"Kun Li;Yujuan Wang;Gangshan Jing;Yongduan Song;Lihua Xie","doi":"10.1109/TCYB.2024.3491177","DOIUrl":"10.1109/TCYB.2024.3491177","url":null,"abstract":"Angle-constrained formation control has garnered significant attention owing to the advantage of interedge angles invariant under translation, rotation, and scaling. However, most existing approaches addressing this problem are applicable only to single- or double-integrator dynamics, which are often impractical in real-world scenarios. In this article, an angle rigidity-based adaptive formation control framework is introduced for nonlinear multiagent systems subject to mismatched uncertainties. The proposed control framework integrates a prescribed performance control approach with a recursive backstepping procedure, offering several key advantages: the capability to handle unmatched system uncertainties, the preservation of angle rigidity throughout the formation process, and the assurance that the triangulated formation shape is asymptotically achieved without risking collisions between neighboring agents. Furthermore, since the control input of each agent only requires local information related to its neighbors, which can be obtained locally from its own sensors, the proposed control method can be deployed in a communication-free environment. The effectiveness of the proposed control algorithms is validated by extensive numerical simulation.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 2","pages":"500-511"},"PeriodicalIF":9.4,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142690983","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}
Pub Date : 2024-11-21DOI: 10.1109/TCYB.2024.3487220
Zhiyuan Yang;Yunjiao Zhou;Lihua Xie;Jianfei Yang
The 3-D point cloud has been widely used in many mobile application scenarios, including autonomous driving and 3-D sensing on mobile devices. However, existing 3-D point cloud models tend to be large and cumbersome, making them hard to deploy on edged devices due to their high memory requirements and nonreal-time latency. There has been a lack of research on how to compress 3-D point cloud models into lightweight models. In this article, we propose a method called T3DNet (tiny 3-D network with augmentation and distillation) to address this issue. We find that the tiny model after network augmentation is much easier for a teacher to distill. Instead of gradually reducing the parameters through techniques, such as pruning or quantization, we predefine a tiny model and improve its performance through auxiliary supervision from augmented networks and the original model. We evaluate our method on several public datasets, including ModelNet40, ShapeNet, and ScanObjectNN. Our method can achieve high compression rates without significant accuracy sacrifice, achieving state-of-the-art performances on three datasets against existing methods. Amazingly, our T3DNet is $58times $ smaller and $54times $ faster than the original model yet with only 1.4% accuracy descent on the ModelNet40 dataset. Our code is available at https://github.com/Zhiyuan002/T3DNet.
{"title":"T3DNet: Compressing Point Cloud Models for Lightweight 3-D Recognition","authors":"Zhiyuan Yang;Yunjiao Zhou;Lihua Xie;Jianfei Yang","doi":"10.1109/TCYB.2024.3487220","DOIUrl":"10.1109/TCYB.2024.3487220","url":null,"abstract":"The 3-D point cloud has been widely used in many mobile application scenarios, including autonomous driving and 3-D sensing on mobile devices. However, existing 3-D point cloud models tend to be large and cumbersome, making them hard to deploy on edged devices due to their high memory requirements and nonreal-time latency. There has been a lack of research on how to compress 3-D point cloud models into lightweight models. In this article, we propose a method called T3DNet (tiny 3-D network with augmentation and distillation) to address this issue. We find that the tiny model after network augmentation is much easier for a teacher to distill. Instead of gradually reducing the parameters through techniques, such as pruning or quantization, we predefine a tiny model and improve its performance through auxiliary supervision from augmented networks and the original model. We evaluate our method on several public datasets, including ModelNet40, ShapeNet, and ScanObjectNN. Our method can achieve high compression rates without significant accuracy sacrifice, achieving state-of-the-art performances on three datasets against existing methods. Amazingly, our T3DNet is <inline-formula> <tex-math>$58times $ </tex-math></inline-formula> smaller and <inline-formula> <tex-math>$54times $ </tex-math></inline-formula> faster than the original model yet with only 1.4% accuracy descent on the ModelNet40 dataset. Our code is available at <uri>https://github.com/Zhiyuan002/T3DNet</uri>.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 2","pages":"526-536"},"PeriodicalIF":9.4,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142684449","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}
{"title":"Interval Secure Event-Triggered Mechanism for Load Frequency Control Active Defense Against DoS Attack","authors":"Zihao Cheng, Songlin Hu, Dong Yue, Xuhui Bu, Xiaolong Ruan, Chenggang Xu","doi":"10.1109/tcyb.2024.3488208","DOIUrl":"https://doi.org/10.1109/tcyb.2024.3488208","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"23 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142673349","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}
Pub Date : 2024-11-18DOI: 10.1109/TCYB.2024.3491756
Lei Zhang;Binglu Wang;Yongqiang Zhao;Yuan Yuan;Tianfei Zhou;Zhijun Li
With the increasing popularity of autonomous driving systems and their applications in complex transportation scenarios, collaborative perception among multiple intelligent agents has become an important research direction. Existing single-agent multimodal fusion approaches are limited by their inability to leverage additional sensory data from nearby agents. In this article, we present the collaborative multimodal fusion network (CMMFNet) for distributed perception in multiagent systems. CMMFNet first extracts modality-specific features from LiDAR point clouds and camera images for each agent using dual-stream neural networks. To overcome the ambiguity in-depth prediction, we introduce a collaborative depth supervision module that projects dense fused point clouds onto image planes to generate more accurate depth ground truths. We then present modality-aware fusion strategies to aggregate homogeneous features across agents while preserving their distinctive properties. To align heterogeneous LiDAR and camera features, we introduce a modality consistency learning method. Finally, a transformer-based fusion module dynamically captures cross-modal correlations to produce a unified representation. Comprehensive evaluations on two extensive multiagent perception datasets, OPV2V and V2XSet, affirm the superiority of CMMFNet in detection performance, establishing a new benchmark in the field.
{"title":"Collaborative Multimodal Fusion Network for Multiagent Perception","authors":"Lei Zhang;Binglu Wang;Yongqiang Zhao;Yuan Yuan;Tianfei Zhou;Zhijun Li","doi":"10.1109/TCYB.2024.3491756","DOIUrl":"10.1109/TCYB.2024.3491756","url":null,"abstract":"With the increasing popularity of autonomous driving systems and their applications in complex transportation scenarios, collaborative perception among multiple intelligent agents has become an important research direction. Existing single-agent multimodal fusion approaches are limited by their inability to leverage additional sensory data from nearby agents. In this article, we present the collaborative multimodal fusion network (CMMFNet) for distributed perception in multiagent systems. CMMFNet first extracts modality-specific features from LiDAR point clouds and camera images for each agent using dual-stream neural networks. To overcome the ambiguity in-depth prediction, we introduce a collaborative depth supervision module that projects dense fused point clouds onto image planes to generate more accurate depth ground truths. We then present modality-aware fusion strategies to aggregate homogeneous features across agents while preserving their distinctive properties. To align heterogeneous LiDAR and camera features, we introduce a modality consistency learning method. Finally, a transformer-based fusion module dynamically captures cross-modal correlations to produce a unified representation. Comprehensive evaluations on two extensive multiagent perception datasets, OPV2V and V2XSet, affirm the superiority of CMMFNet in detection performance, establishing a new benchmark in the field.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 1","pages":"486-498"},"PeriodicalIF":9.4,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142670652","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：