IEEE/CAA Journal of Automatica Sinica

Hazard-Aware Weighted Advantage Combination for UAV Target Tracking and Obstacle Avoidance

Lele Xu, Jian Liu, Xiaoguang Chang, Xuping Liu, Changyin Sun

, Available online , doi: 10.1109/JAS.2024.124920

[Abstract](140) [FullText HTML] (0) [PDF 4200KB](35)

Abstract:
In recent years, the rapid evolution of unmanned aerial vehicles (UAVs) has brought about transformative changes across various industries. However, addressing fundamental challenges in UAV technology, particularly target tracking and obstacle avoidance, remains crucial for wildlife protection, military industry security, etc. Many existing methods based on reinforcement learning to solve UAV multi-tasks need to be redesigned and retrained, and cannot be quickly and effectively extended to other scenarios. To this end, we propose a novel solution based on a hazard-aware weighted advantage combination for UAV target tracking and obstacle avoidance. First, we independently trained the UAV target tracking and obstacle avoidance using the dueling double deep Q-network reinforcement learning algorithm. Subsequently, in a multitasking scenario, we introduce the two pre-trained networks. Meanwhile, we design a weight determined by the present risk level encountered by the UAV. This weight is utilized to perform a weighted summation of the advantage values from both networks, eliminating the need for retraining to obtain the final action. We validate our approach through extensive simulation experiments in the robotics simulator known as CoppeliaSim. The results demonstrate that our method outperforms current state-of-the-art techniques, achieving superior performance in both tracking accuracy and avoidance of collisions.

Optimization Algorithms Based on Double-Integral Coevolutionary Neurodynamics in Deep Learning

Dan Su, Jie Han, Chunhua Yang, Weihua Gui

, Available online , doi: 10.1109/JAS.2025.125210

[Abstract](63) [FullText HTML] (0) [PDF 4136KB](18)

Abstract:
Deep neural networks are increasingly exposed to attack threats, and at the same time, the need for privacy protection is growing. As a result, the challenge of developing neural networks that are both robust and capable of strong generalization while maintaining privacy becomes pressing. Training neural networks under privacy constraints is one way to minimize privacy leakage, and one way to do this is to add noise to the data or model. However, noise may cause gradient directions to deviate from the optimal trajectory during training, leading to unstable parameter updates, slow convergence, and reduced model generalization capability. To overcome these challenges, we propose an optimization algorithm based on double-integral coevolutionary neurodynamics (DICND), designed to accelerate convergence and improve generalization in noisy conditions. Theoretical analysis proves the global convergence of the DICND algorithm and demonstrates its ability to converge to near-global minima efficiently under noisy conditions. Numerical simulations and image classification experiments further confirm the DICND algorithm’s significant advantages in enhancing generalization performance.

Self-Cumulative Contrastive Graph Clustering

Xiaoqiang Yan, Kun Deng, Quan Zou, Zhen Tian, Hui Yu

, Available online , doi: 10.1109/JAS.2024.125025

[Abstract](99) [FullText HTML] (1) [PDF 1464KB](29)

Abstract:
Contrastive graph clustering (CGC) has become a prominent method for self-supervised representation learning by contrasting augmented graph data pairs. However, the performance of CGC methods critically depends on the choice of data augmentation, which usually limits the capacity of network generalization. Besides, most existing methods characterize positive and negative samples based on the nodes themselves, ignoring the influence of neighbors with different hop numbers on the node. In this study, a novel self-cumulative contrastive graph clustering (SC-CGC) method is devised, which is capable of dynamically adjusting the influence of neighbors with different hops. Our intuition is that better neighbors are closer and distant ones are further away in their feature space, thus we can perform neighbor contrasting without data augmentation. To be specific, SC-CGC relies on two neural networks, i.e., autoencoder network (AE) and graph autoencoder network (GAE), to encode the node information and graph structure, respectively. To make these two networks interact and learn from each other, a dynamic fusion mechanism is devised to transfer the knowledge learned by AE to the corresponding GAE layer by layer. Then, a self-cumulative contrastive loss function is designed to characterize the structural information by dynamically accumulating the influence of the nodes with different hops. Finally, our approach simultaneously refines the representation learning and clustering assignments in a self-supervised manner. Extensive experiments on 8 realistic datasets demonstrate that SC-CGC consistently performs better over SOTA techniques.

Joint Super-Resolution and Nonuniformity Correction Model for Infrared Light Field Images Based on Frequency Correlation Learning

You Du, Yong Ma, Jun Huang, Xiaoguang Mei, Jinhui Qin, Fan Fan

, Available online , doi: 10.1109/JAS.2024.124881

[Abstract](163) [FullText HTML] (0) [PDF 30170KB](23)

Abstract:
Super-resolution (SR) for the camera array-based infrared light field (IRLF) images aims to reconstruct high-resolution sub-aperture images (SAIs) from their low-resolution counterparts. Existing SR methods mainly focus on exploiting the spatial and angular information of SAIs and have achieved promising results in the visible band. However, they fail to adaptively correct the nonuniform noise in IRLF images, resulting in over-smoothness or artifacts in their results. This study proposes a novel method that reconstructs high-resolution IRLF images while correcting the nonuniformity. The main idea is to decompose the structure and nonuniform noise into high- and low-frequency components and then learn the frequency correlations to help correct the nonuniformity. To learn the frequency correlation, intra- and inter-frequency units are designed. The former learns the correlation of neighboring pixels within each component, aiming to reconstruct the structure and coarsely remove nonuniform noise. The latter models the correlation of contents between different components to reconstruct fine-grained structures and reduce residual noise. Both units are equipped with our designed triple-attention mechanism, which can jointly exploit spatial, angular, and frequency information. Moreover, we collected two real-world IRLF-image datasets with significant nonuniformity, which can be used as a common base in the field. Qualitative and quantitative comparisons demonstrate that our method outperforms state-of-the-art approaches with a clearer structure and fewer artifacts. The code is available at https://github.com/DuYou2023/IRLF-FSR.

Data-Driven Bipartite Consensus Control for Large Workpieces Rotation of Nonlinear Multi-Robot Systems

Haoran Tan, Xueming Zhang, Yaonan Wang, You Wu, Yun Feng, Zhongsheng Hou

, Available online

[Abstract](9) [FullText HTML] (0) [PDF 3890KB](4)

Abstract:
In this paper, a novel data-driven bipartite consensus control scheme is proposed for the rotation problem of large workpieces with multi-robot systems (MRSs) under a directed communication topology. The rotation of a large workpiece is described as the MRSs with cooperation and antagonism interaction. By the signed graph theory, it is further transformed into a bipartite consensus control problem, where all followers are uniformly degenerated into the general nonlinear systems based on the lateral error model. To augment the flexibility of control protocol and improve control performance, a higher-dimensional full form dynamic linearization (FFDL) technique is committed to the MRSs. The control input criterion function consists of the data model based on FFDL and the bipartite consensus error based on the signed graph theory, and the proposed control protocol is given by optimizing this criterion function. In this way, this scheme has a higher degree of freedom and better adaptive adjustment capability while not excessively increasing the control method complexity, and it can also be compatible with other forms of dynamic linearization techniques in MRSs. Further, three matrix norm lemmas are introduced to deal with the challenges of stability analysis caused by higher matrix dimensions and more robots. Finally, the effectiveness of the proposed method is verified by numerical simulations.

DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models

Luolin Xiong, Haofen Wang, Xi Chen, Lu Sheng, Yun Xiong, Jingping Liu, Yanghua Xiao, Huajun Chen, Qing-Long Han, Yang Tang

, Available online , doi: 10.1109/JAS.2025.125495

[Abstract](14) [FullText HTML] (0) [PDF 1157KB](4)

Abstract:
DeepSeek, a Chinese artificial intelligence (AI) startup, has released their V3 and R1 series models, which attracted global attention due to their low cost, high performance, and open-source advantages. This paper begins by reviewing the evolution of large AI models focusing on paradigm shifts, the mainstream large language model (LLM) paradigm, and the DeepSeek paradigm. Subsequently, the paper highlights novel algorithms introduced by DeepSeek, including multi-head latent attention (MLA), mixture-of-experts (MoE), multi-token prediction (MTP), and group relative policy optimization (GRPO). The paper then explores DeepSeek’s engineering breakthroughs in LLM scaling, training, inference, and system-level optimization architecture. Moreover, the impact of DeepSeek models on the competitive AI landscape is analyzed, comparing them to mainstream LLMs across various fields. Finally, the paper reflects on the insights gained from DeepSeek’s innovations and discusses future trends in the technical and engineering development of large AI models, particularly in data, training, and reasoning.

Instance by Instance: An Iterative Framework for Multi-Instance 3D Registration

Jiaqi Yang, Xinyue Cao, Xiyu Zhang, Yuxin Cheng, Zhaoshuai Qi, Siwen Quan

, Available online , doi: 10.1109/JAS.2024.125058

[Abstract](43) [FullText HTML] (0) [PDF 27936KB](4)

Abstract:
Multi-instance registration is a challenging problem in computer vision and robotics, where multiple instances of an object need to be registered in a standard coordinate system. Pioneers followed a non-extensible one-shot framework, which prioritizes the registration of simple and isolated instances, often struggling to accurately register challenging or occluded instances. To address these challenges, we propose the first iterative framework for multi-instance 3D registration (MI-3DReg) in this work, termed instance-by-instance (IBI). It successively registers instances while systematically reducing outliers, starting from the easiest and progressing to more challenging ones. This enhances the likelihood of effectively registering instances that may have been initially overlooked, allowing for successful registration in subsequent iterations. Under the IBI framework, we further propose a sparse-to-dense correspondence-based multi-instance registration method (IBI-S2DC) to enhance the robustness of MI-3DReg. Experiments on both synthetic and real datasets have demonstrated the effectiveness of IBI and suggested the new state-of-the-art performance with IBI-S2DC, e.g., our mean registration F1 score is 12.02%/12.35% higher than the existing state-of-the-art on the synthetic/real datasets. The source codes are availableonline at https://github.com/caoxy01/IBI.

Multi-Phase Degradation Modeling Based on Uncertain Random Process for Remaining Useful Life Prediction Under Triple Uncertainties

Xuerui Cao, Kaixiang Peng, Ruihua Jiao

, Available online

[Abstract](82) [FullText HTML] (0) [PDF 3328KB](16)

Abstract:
Due to abrupt changes in the intrinsic degradation mechanism or shock from external environmental pressure, degradations of some equipment are characterized by multi-phase and jumps. Meanwhile, equipment is subject to inherent fluctuations, limited data and imperfect measurements resulting in aleatory, epistemic and measurement uncertainties of the degradation process. This paper proposes a degradation model and remaining useful life (RUL) prediction method under triple uncertainties for a category of complex equipment with multi-phase degradation and jumps. First, a multi-phase degradation model with random jumps and measurement errors is constructed based on uncertain random processes. Afterward, the analytic expression of RUL prediction considering the heterogeneity is derived by modeling the uncertainty of degradation states at change points under the concept of first hitting time. A stochastic uncertain approach is utilized for the proposed multi-phase degradation model to identify model parameters based on historical data. Furthermore, the implied degradation features are adaptively updated in online stage using similarity-based weighted stochastic uncertain maximum likelihood estimation and Kalman filtering. Finally, the effectiveness of the method is verified by simulation example and practical case.

MFAINet: Multi-receptive Field Feature Fusion with Attention-Integrated for Polyp Segmentation

Guangzu Lv, Bin Wang, Cunlu Xu, Weiping Ding, Jun Liu

, Available online , doi: 10.1109/JAS.2025.125408

[Abstract](12) [FullText HTML] (0) [PDF 29879KB](1)

Abstract:
Colorectal cancer has become a global public health concern. Removing polyps before they become malignant can effectively prevent the onset of colorectal cancer. Currently, multi-receptive field feature extraction and attention mechanisms have achieved significant success in polyp segmentation. However, how to effectively fuse these mechanisms and fully leverage their respective strengths remains an open problem. In this paper, we propose a polyp segmentation network, MFAINet. We design an Attention-Integrated Multi-receptive Field Feature Extraction module (AMFE), which uses layering and multiple weightings to fuse the multi-receptive field feature extraction and attention mechanisms, maximizing the extraction of both global and detailed information from the image. To ensure that the input to AMFE contains richer target feature information, we introduce a Multi-layer Progressive Fusion module (MPF). MPF progressively merges features at each layer, fully integrating contextual information. Finally, we employ the Selective Fusion module (SFM) to combine the high-level features produced by AMFE, resulting in an accurate polyp segmentation map. To evaluate the learning and generalization capabilities of MFAINet, we conduct experiments on five widely-used public polyp datasets using four evaluation metrics. Notably, our model achieves the best results in nearly all cases. The source code is available at: https://github.com/MFAINet.

A Proportional Integral Controller-Enhanced Non-Negative Latent Factor Analysis Model

Ye Yuan, Siyang Lu, Xin Luo

, Available online

[Abstract](7) [FullText HTML] (0) [PDF 1007KB](3)

Abstract:
A non-negative latent factor (NLF) model is able to be built efficiently via a single latent factor-dependent, non-negative and multiplicative update (SLF-NMU) algorithm for performing precise representation to high-dimensional and incomplete (HDI) matrix from many kinds of big-data-related applications. However, an SLF-NMU algorithm updates a latent factor relying on the current update increment only without considering past learning information, making a resultant model suffer from slow convergence. To address this issue, this study proposes a proportional integral (PI) controller-enhanced NLF (PI-NLF) model with two-fold ideas: 1) Designing an increment refinement (IR) mechanism, which formulates the current and past update increments as the proportional and integral terms of a PI controller, thereby assimilating the past update information into the learning scheme smoothly with high efficiency; 2) Deriving an IR-based SLF-NMU (ISN) algorithm, which updates a latent factor following the principle of an IR mechanism, thus significantly accelerating an NLF model’s convergence rate. The simulation results on eight HDI matrices collected by real applications validate that a PI-NLF model outstrips several leading-edge models in both computational efficiency and accuracy when estimating missing data within an HDI matrix. The proposed PI-NLF model can be effectively applied to applications involving HDI matrix like e-commerce system, social network, and cloud service system. The code is available at https://github.com/yuanyeswu/PINLF/blob/main/PINLF-code.zip.

Mixed Motivation Driven Social Multi-Agent Reinforcement Learning for Autonomous Driving

Long Chen, Peng Deng, Lingxi Li, Xuemin Hu

, Available online

[Abstract](15) [FullText HTML] (0) [PDF 2334KB](4)

Abstract:
Despite great achievement has been made in autonomous driving technologies, autonomous vehicles (AVs) still exhibit limitations in intelligence and lack social coordination, which is primarily attributed to their reliance on single-agent technologies, neglecting inter-AV interactions. Current research on multi-agent autonomous driving (MAAD) predominantly focuses on either distributed individual learning or centralized cooperative learning, ignoring the mixed-motive nature of MAAD systems, where each agent is not only self-interested in reaching its own destination but also needs to coordinate with other traffic participants to enhance efficiency and safety. Inspired by the mixed motivation of human driving behavior and their learning process, we propose a novel mixed motivation driven social multi-agent reinforcement learning method for autonomous driving. In our method, a multi-agent reinforcement learning (MARL) algorithm, called Social Learning Policy Optimization (SoLPO), which takes advantage of both the individual and social learning paradigms, is proposed to empower agents to rapidly acquire self-interested policies and effectively learn socially coordinated behavior. Based on the proposed SoLPO, we further develop a mixed-motive MARL method for autonomous driving combined with a social reward integration module that can model the mixed-motive nature of MAAD systems by integrating individual and neighbor rewards into a social learning objective for improved learning speed and effectiveness. Experiments conducted on the MetaDrive simulator show that our proposed method outperforms existing state-of-the-art MARL approaches in metrics including the success rate, safety, and efficiency. Moreover, the AVs trained by our method form coordinated social norms and exhibit human-like driving behavior, demonstrating a high degree of social coordination.

ADAPT: A Model-Free Adaptive Optimal Control for Continuum Robots

Haiyang Fang, Sishen Yuan, Hongliang Ren, Shuping He, Shing Shin Cheng

, Available online , doi: 10.1109/JAS.2025.125183

[Abstract](24) [FullText HTML] (0) [PDF 5337KB](9)

Abstract:
Realizing optimal control performance for continuum robots (CRs) poses huge challenges on traditional model-based optimal control approaches due to their high degrees of freedom, complex nonlinear dynamics and soft continuum morphologies which are difficult to explicitly model. This paper proposes a model-free adaptive optimal control algorithm (ADAPT) for CRs. In our strategy, we consider CRs as a class of nonlinear continuous-time dynamical systems in the state space, wherein the position of the end-effector is considered as the state and the input torque is mapped as the control input. Then, the optimized Hamilton-Jacobi-Bellman (HJB) equation is derived by optimal control principles, and subsequently solved by the proposed ADAPT algorithm without requiring knowledge of the origin system dynamics. Under some mild assumptions, the global stability and convergence of the closed-loop control approach are guaranteed. Several simulation experiments are conducted on a magnetic CR (MCR) to demonstrate the practicality and effectiveness of the ADAPT algorithm.

Environment Modeling for Service Robots From a Task Execution Perspective

Ying Zhang, Guohui Tian, Cui-Hua Zhang, Changchun Hua, Weili Ding, Choon Ki Ahn

, Available online , doi: 10.1109/JAS.2025.125168

[Abstract](20) [FullText HTML] (0) [PDF 15721KB](8)

Abstract:
Service robots are increasingly entering the home to provide domestic tasks for residents. However, when working in an open, dynamic, and unstructured home environment, service robots still face challenges such as low intelligence for task execution and poor long-term autonomy (LTA), which has limited their deployment. As the basis of robotic task execution, environment modeling has attracted significant attention. This integrates core technologies such as environment perception, understanding, and representation to accurately recognize environmental information. This paper presents a comprehensive survey of environmental modeling from a new task-execution-oriented perspective. In particular, guided by the requirements of robots in performing domestic service tasks in the home environment, we systematically review the progress that has been made in task-execution-oriented environmental modeling in four respects: 1) localization, 2) navigation, 3) manipulation, and 4) LTA. Current challenges are discussed, and potential research opportunities are also highlighted.

Learning Laws for Deep Convolutional Neural Networks With Guaranteed Convergence

Sitan Li, Chien Chern CHEAH

, Available online , doi: 10.1109/JAS.2025.125171

[Abstract](50) [FullText HTML] (0) [PDF 1528KB](17)

Abstract:
Convolutional Neural Networks (CNNs) have shown remarkable success across numerous tasks such as image classification, yet the theoretical understanding of their convergence remains underdeveloped compared to their empirical achievements. In this paper, the first filter learning framework with convergence-guaranteed learning laws for End-To-End learning of deep CNNs is proposed. Novel update laws with convergence analysis are formulated based on the mathematical representation of each layer in convolutional neural networks. The proposed learning laws enable concurrent updates of weights across all layers of the deep convolutional neural network and the analysis shows that the training errors converge to certain bounds which are dependent on the approximation errors. Case studies are conducted on benchmark datasets and the results show that the proposed concurrent filter learning framework guarantees the convergence and offers more consistent and reliable results during training with a trade-off in performance compared to stochastic gradient descent methods. This framework represents a significant step towards enhancing the reliability and effectiveness of deep convolutional neural network by developing a theoretical analysis which allows practical implementation of the learning laws with automatic tuning of the learning rate to guarantee the convergence during training.

A Decision Variables Classification-Based Evolutionary Algorithm for Constrained Multi-Objective Optimization Problems

Xuanxuan Ban, Jing Liang, Kangjia Qiao, Kunjie Yu, Yaonan Wang, Jinzhu Peng, Boyang Qu

, Available online , doi: 10.1109/JAS.2025.125276

[Abstract](128) [FullText HTML] (0) [PDF 18219KB](38)

Abstract:
Solving constrained multi-objective optimization problems (CMOPs) is a challenging task due to the presence of multiple conflicting objectives and intricate constraints. In order to better address CMOPs and achieve a balance between objectives and constraints, existing constrained multi-objective evolutionary algorithms (CMOEAs) predominantly focus on devising various strategies by leveraging the relationships between objectives and constraints, and the designed strategies usually are effective for the problems with simple constraints. However, these methods most ignore the relationship between decision variables and constraints. In fact, the essence of optimization is to find appropriate decision variables to meet various complex constraints. Therefore, it is hoped that the problem can be analyzed from the perspective of decision variables, so as to obtain more excellent results. Based on the above motivation, this paper proposes a decision variables classification approach, according to the relationship between decision variables and constraints, variables are divided into constraint-related (CR) variables and constraint-independent (CI) variables. Consequently, by optimizing these two types of variables independently, the population can sustain a favorable balance between feasibility and diversity. Furthermore, specific offspring generation strategies are proposed for the two categories of decision variables in order to achieve rapid convergence while maintaining population diversity. Experimental results on 31 test problems as well as 20 real-world problems demonstrate that the proposed algorithm is competitive compared to some state-of-the-art constrained multi-objective optimization algorithms.

Distributed Gain Scheduling Dynamic Event-Triggered Semi-Global Leader-Following Consensus of Input Constrained MASs Under Fixed/Switching Topologies

Meilin Li, Tieshan Li, Hongjing Liang

, Available online , doi: 10.1109/JAS.2025.125417

[Abstract](20) [FullText HTML] (0) [PDF 2275KB](6)

Abstract:
In this paper, the semi-global leader-following consensus issue of multi-agent systems with constrained input under fixed and switching topologies is investigated via a distributed gain scheduling dynamic event-triggered method. First, a novel distributed gain scheduling consensus protocol is proposed under fixed topology, which integrates time-varying gain and distributed parameter schedulers. This approach enhances the transient performance of consensus tracking by enlarging the gain parameter through the scheduler, while the reliance of the scheduler on global state information is eliminated via a distributed design method. Subsequently, a distributed dynamic event-triggered mechanism is introduced to reduce the controller updates, while the expression of the inter-event times mitigates its explicit reliance on the system matrix. Additionally, to eliminate the need for real-time monitoring of neighboring agents’ states and continuous communication, a distributed dynamic self-triggered mechanism is developed. Next, our approaches are extended to solve the semi-global leader-following consensus problem under switching topologies. The average dwell time technique is employed to alleviate the limitations on the switching rate among multiple topologies. Finally, the theoretical analysis is validated through simulation results.

DKAMFormer: Domain Knowledge-Augmented Multiscale Transformer for Remaining Useful Life Prediction of Aeroengine

Song Fu, Yue Wang, Lin Lin, Minghang Zhao, Lizheng Zu, Yifan Lu, Feng Guo, Shiwei Suo, Yikun Liu, Sihao Zhang, Shisheng Zhong

, Available online , doi: 10.1109/JAS.2025.125126

[Abstract](122) [FullText HTML] (0) [PDF 117826KB](27)

Abstract:
Transformers have achieved promising results on aeroengine remaining useful life (RUL) prediction, but they still have several limitations: 1) Aeroengine domain knowledge, which contains rich information that can reflect the aeroengine’s health statue, is largely ignored in modeling process; 2) Traditional transformer ignores the valuable degradation information from other time scales. To address these issues, a novel domain knowledge-augmented multiscale transformer (DKAMFormer) is developed by integrating domain knowledge and multiscale learning to improve the prognostic performance and reliability. First, to obtain rich and professional aeroengine domain knowledge, multiple detail and complete knowledge graphs (KGs) are established based on the working principle of aeroengine, including aeroengine structure, components working characteristics and sensor parameters. Second, the domain knowledge contained in KGs is convert to embedded vector by KG representative learning, which are then utilized to strengthen and enrich the original multidimensional time-series (MTS) monitoring data, aiming to intergrade domain knowledge and monitoring data to train DKAMFormer. Third, to learn rich and complementary degradation features, a novel multiscale time scale-guided self-attention (MTSGSA) mechanism is designed, which maps original MTS into different time-scale feature spaces, and then employs multiple independent self-attention head to extract the degradation features from different time-scale spaces. Finally, through a series of comparative experiments on the public CMAPSS and N-CMAPSS datasets and compared with 17 SOTA methods, the developed DKAMFormer significantly improves the RUL prediction performance under multiple operation conditions and degradation modes.

Robust Optimization Control for Cyber-Physical Systems Subject to Jamming Attack: A Nested Game Approach

Min Shi, Yuan Yuan Shi

, Available online

[Abstract](12) [FullText HTML] (0) [PDF 1474KB](8)

Abstract:

Data-Driven Adaptive PID Tracking Control of a Class of Nonlinear Systems

Tong Mu, Haibin Guo, Chuandong Bai, Zhong-Hua Pang

, Available online

[Abstract](18) [FullText HTML] (0) [PDF 428KB](15)

Abstract:

Reinforcement Learning-Based Spectral Performance Optimization for UAV-Assisted MIMO Communication System

Lu Dong, Hong-wei Kong, Xin Yuan

, Available online , doi: 10.1109/JAS.2025.125225

[Abstract](62) [FullText HTML] (0) [PDF 1000KB](30)

Abstract:

Adaptive Dual-Loop Disturbance Observer-based Robust Model Predictive Tracking Control for Autonomous Hypersonic Vehicles

Runqi Chai, Tianhao Liu, Shaoming He, Kaiyuan Chen, Yuanqing Xia, Hyo-Sang Shin, Antonios Tsourdos

, Available online , doi: 10.1109/JAS.2025.125291

[Abstract](63) [FullText HTML] (0) [PDF 4076KB](18)

Abstract:
To solve the attitude trajectory tracking problem for hypersonic vehicles in the presence of system constraints and unknown disturbances, this paper designed a nonlinear robust model predictive control (RMPC) scheme, which can produce near-optimal tracking commands. Unlike the existing designs, the proposed scheme is less conservative and successfully prioritizes the solution optimality. The established RMPC follows a dual-loop structure. Specifically, in the outer feedback loop, the reference attitude angle profiles are optimally tracked, while in the inner feedback loop, the control moment commands are produced by optimally tracking the desired angular rate trajectories. Besides, an adaptive disturbance observer (ADO) is designed and embedded in the inner and outer RMPC controllers to alleviate the negative effects caused by unknown external disturbances. The recursive feasibility of the optimization process, together with the input-to-state stability of the proposed RMPC, is theoretically guaranteed by introducing a tightened control constraint and terminal region. The derived property reveals that our proposal can steer the tracking error within a small region of convergence. Finally, the effectiveness of the proposed scheme is demonstrated by performing simulation studies.

Adaptive Sliding Mode Control with Linear Extended State Observer for Active Magnetic Bearing-Rotor Systems

Yaozhong Zheng, Hai-Tao Zhang, Ziheng Yu, Xiang Huang, Haichao Jiao, Han Ding

, Available online , doi: 10.1109/JAS.2024.125037

[Abstract](17) [FullText HTML] (0) [PDF 3873KB](3)

Abstract:

MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification With Zoom-Free Remote Sensing Imagery

Yansheng Li, Yuning Wu, Gong Cheng, Chao Tao, Bo Dang, Yu Wang, Jiahao Zhang, Chuge Zhang, Yiting Liu, Xu Tang, Jiayi Ma, Yongjun Zhang

, Available online , doi: 10.1109/JAS.2025.125324

[Abstract](204) [FullText HTML] (0) [PDF 60931KB](63)

Abstract:
Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the million-scale fine-grained geospatial scene classification dataset (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-in-scene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for fine-grained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the context-aware transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.

Evolutionary Algorithm Based on Surrogate and Inverse Surrogate Models for Expensive Multiobjective Optimization

Qi Deng, Qi Kang, MengChu Zhou, Xiaoling Wang, Shibing Zhao, Siqi Wu, Mohammadhossein Ghahramani

, Available online

[Abstract](123) [FullText HTML] (0) [PDF 1689KB](44)

Abstract:
When dealing with expensive multiobjective optimization problems, majority of existing surrogate-assisted evolutionary algorithms (SAEAs) generate solutions in decision space and screen candidate solutions mostly by using designed surrogate models. The generated solutions exhibit excessive randomness, which tends to reduce the likelihood of generating good-quality solutions and cause a long evolution to the optima. To improve SAEAs greatly, this work proposes an evolutionary algorithm based on surrogate and inverse surrogate models by 1) Employing a surrogate model in lieu of expensive (true) function evaluations; and 2) Proposing and using an inverse surrogate model to generate new solutions. By using the same training data but with its inputs and outputs being reversed, the latter is simple to train. It is then used to generate new vectors in objective space, which are mapped into decision space to obtain their corresponding solutions. Using a particular example, this work shows its advantages over existing SAEAs. The results of comparing it with state-of-the-art algorithms on expensive optimization problems show that it is highly competitive in both solution performance and efficiency.

Switching in Sliding Mode Control: A Spatio-Temporal Perspective

Xinghuo Yu

, Available online , doi: 10.1109/JAS.2025.125423

[Abstract](23) [FullText HTML] (0) [PDF 927KB](8)

Abstract:
Sliding mode control (SMC) is a widely adopted control technology known for its robustness and simplicity. The essence of SMC is to use discontinuous control to drive a system into a pre-defined motion, called the sliding mode, which is designed with desirable dynamical properties. In the sliding mode, the controlled system is insensitive to the matched uncertainties and disturbances. Most SMC theory and methods have been developed based on the dynamical systems in the continuous-time domain, where switching functions play a critical role. Ideal switching is supposed to be instantaneous, activating as soon as the switching condition is met. However, in practice, switching mechanisms are affected by imperfections such as time delays, unmodeled dynamics, defects, digitization effects, and actuation limitations, which can degrade the salient properties of SMC. Understanding these effects and developing mitigation strategies are essential for industrial applications. Furthermore, the advent of networked control environments presents new challenges like limited communication bandwidth, latency and cyberattack, which have seen the emergence of the event-triggered SMC recently. Despite these significant advances, there is a lack of comprehensive studies in particular which examine the commonalities and distinctions of utilizing switching in SMC across the continuous-time and discrete-time domains and beyond.This paper investigates the role of switching in SMC from a spatio-temporal perspective, that is, from both the state-space and time aspects. The aim is to facilitate better understanding of its effects and misbehaviours, and to unlock its full potential for future applications. The interplay between SMC methods in the continuous-time and discrete-time domains is analyzed, and their shared principles and unique challenges are identified. Furthermore, important technical issues relating to switching across these time domains are explored, and several myths and pitfalls in their theory and applications are highlighted. The relationships of SMC with other switching-based control systems such as switched control systems, fuzzy control systems, and event-triggered control systems are discussed. The impact of networked control environments on SMC in the continuous-time and discrete-time domains is also examined. Finally, key challenges and opportunities are outlined for future work in SMC and beyond.

Knowledge Classification-Assisted Evolutionary Multitasking for Two-Task Multiobjective Optimization Problems

Xiaoling Wang, Qi Kang, MengChu Zhou, Qi Deng, Zheng Fan, Haoyue Liu

, Available online , doi: 10.1109/JAS.2024.125070

[Abstract](19) [FullText HTML] (0) [PDF 1352KB](5)

Abstract:
To realize Industry 5.0, manufacturers face various optimization problems that seldom appear in isolation. Evolutionary MultiTasking (EMT) is an effective method to solve multiple related problems by extracting and utilizing common knowledge. Knowledge transfer is the key to the effectiveness of EMT. Existing EMT methods mainly focus on designing effective inter-task learning methods and ignore the fact that provided knowledge’s appropriateness also has a significant effect on EMT’s performance. There is plentiful knowledge in assistant tasks, and knowledge transfer may not work well and even lead to a negative effect if useless knowledge is selected to guide target tasks. EMT is thus confronted with a challenge to find appropriate knowledge. This work proposes an efficient knowledge classification-assisted EMT framework to identify and select valuable knowledge from assistant tasks. During the evolution process, better-performing candidates are supposed to have advantages in exploitation. Therefore, assistant individuals that are similar to better-performing target individuals are used to provide positive knowledge. Specifically, the target sub-population is divided into different levels and then a classifier is trained to divide assistant sub-population. Considering that target and assistant sub-populations have different characteristics, we use domain adaptation to reduce their distribution discrepancies. In this way, the trained classifier can classify assistant individuals more accurately, and truly useful knowledge can be selected for target tasks. The superior performance of our proposed framework over state-of-the-art algorithms is verified via a series of benchmark problems.

A Game-Theoretic Approach to Solving the Roman Domination Problem

Xiuyang Chen, Changbing Tang, Zhao Zhang, Guanrong Chen

, Available online , doi: 10.1109/JAS.2023.123840

[Abstract](79) [FullText HTML] (0) [PDF 2241KB](15)

Abstract:
The Roman domination problem is an important combinatorial optimization problem that is derived from an old story of defending the Roman Empire and now regains new significance in cyber space security, considering backups in the face of a dynamic network security requirement. In this paper, firstly, we propose a Roman domination game (RDG) and prove that every Nash equilibrium (NE) of the game corresponds to a strong minimal Roman dominating function (S-RDF), as well as a Pareto-optimal solution. Secondly, we show that RDG is an exact potential game, which guarantees the existence of an NE. Thirdly, we design a game-based synchronous algorithm (GSA), which can be implemented distributively and converge to an NE in $ O(n)$ rounds, where n is the number of vertices. In GSA, all players make decisions depending on local information. Furthermore, we enhance GSA to be enhanced GSA (EGSA), which converges to a better NE in $ O(n^2)$ rounds. Finally, we present numerical simulations to demonstrate that EGSA can obtain a better approximate solution in promising computation time compared with state-of-the-art algorithms.

Federated Services: A Smart Service Ecology With Federated Security for Aligned Data Supply and Scenario-Oriented Demands

Xiaofeng Jia, Juanjuan Li, Shouwen Wang, Hongwei Qi, Fei-Yue Wang, Rui Qin, Min Zhang, Xiaolong Liang

, Available online

[Abstract](35) [FullText HTML] (0) [PDF 2846KB](10)

Abstract:
This paper introduces federated services as a smart service ecology with federated security to align distributed data supply with diversified service demands spanning digital and societal contexts. It presents the comprehensive researches on the theoretical foundation and technical system of federated services, aiming at advancing our understanding and implementation of this novel service paradigm. First, a thorough examination of the characteristics of federated security within federated services is conducted. Then, a five-layer technical framework is formulated under a decentralized intelligent architecture, ensuring secure, agile, and adaptable service provision. On this basis, the operational mechanisms underlying data federation and service confederation is analyzed, with emphasis on the smart supply-demand matching model. Furthermore, a scenario-oriented taxonomy of federated services accompanied by illustrative examples is proposed. Our work offers actionable insights and roadmap for realizing and advancing federated services, contributing to the refinement and wider adoption of this transformative service paradigm in the digital era.

Optimal Sensor Scheduling for Remote State Estimation With Partial Channel Observation

Bowen Sun, Xianghui Cao

, Available online , doi: 10.1109/JAS.2025.125180

[Abstract](28) [FullText HTML] (0) [PDF 417KB](17)

Abstract:

Data-Driven Two-Stage Robust Optimization Allocation and Loading for Salt Lake Chemical Enterprise Products Under Demand Uncertainty

Yiyin Tang, Yalin Wang, Chenliang Liu, Qingkai Sui, Yishun Liu, Keke Huang, Weihua Gui

, Available online , doi: 10.1109/JAS.2025.125204

[Abstract](50) [FullText HTML] (0) [PDF 4119KB](12)

Abstract:
Most enterprises rely on railway transportation to deliver their products to customers, particularly in the salt lake chemical industry. Notably, allocating products to freight spaces and their assembly on transport vehicles are critical pre-transportation processes. However, due to demand fluctuations from changing product orders and unforeseen railway scheduling delays, manually adjusted allocation and loading may lead to excessive loading and unloading distances and times, ultimately increasing transportation costs for enterprises. To address these issues, this paper proposes a data-driven two-stage robust optimization (TSRO) framework embedding with the gated stacked temporal autoencoder clustering based on the attention mechanism (GSTAC-AM), which aims to overcome demand uncertainty and enhance the efficiency of freight allocation and loading. Specifically, GSTAC-AM is developed to help predict the deviation level of demand uncertainty and mitigate the impact of potential outliers. Then, a robust counterpart model is formulated to ensure computational tractability. In addition, a multi-stage hybrid heuristic algorithm is designed to handle the large scale and complexity inherent in the freight space allocation and loading processes. Finally, the effectiveness and applicability of the proposed framework are validated through a real case study conducted in a large salt lake chemical enterprise.

A Hierarchical Stochastic Network Approach for Fault Diagnosis of Complex Industrial Processes

Mingjie Lv, Yonggang Li, Huanzhi Gao, Bei Sun, Keke Huang, Chunhua Yang, Weihua Gui

, Available online , doi: 10.1109/JAS.2025.125249

[Abstract](39) [FullText HTML] (0) [PDF 39985KB](8)

Abstract:
Complex industrial processes present typical uncertainty due to fluctuations in the composition of raw materials and frequently changing operating conditions. This poses three challenges for precise fault diagnosis, including random noise interference, less distinguishability between multi-class faults, and the new fault emerging. To address these issues, this study formulates fault diagnosis in uncertain industrial processes as a multi-level refined fault diagnosis problem. A hierarchical stochastic network approach is proposed to refine fault diagnosis of multi-class faults. This method considers the augmentation of fault categories as naturally following a hierarchical structure. At each hierarchical stage, stochastic network methods are designed according to the sources of uncertainty. For fault feature extraction, a doubly stochastic attention-based variational graph autoencoder is introduced to suppress noise during the message-passing process, ensuring the extraction of high-quality fault features and providing the provision of differentiated information. Subsequently, multiple stochastic configuration networks are deployed to realize multi-level fault diagnosis from coarse to fine granularity via a hierarchical structure rather than treating all faults equally. This approach effectively enhances the precision of multi-class fault diagnosis and ensures its robust generalization capability. Finally, the feasibility and effectiveness of the proposed method are validated using two industrial processes. The results demonstrate that the proposed method can effectively suppress the random noise interference and adapt to the emergence of small samples and imbalanced extreme fault-type data, achieving a satisfactory fault diagnosis performance.

Event-Triggered Adaptive Control of Noncanonical Nonlinear Systems With Hysteresis Inputs

Guanyu Lai, Kairong Zeng, Yonghua Wang, Tao Zhang, Hanzhen Xiao

, Available online , doi: 10.1109/JAS.2025.125339

[Abstract](29) [FullText HTML] (0) [PDF 1342KB](10)

Abstract:

Nonlinear Frictions Identification in Time-Variant Automotive Systems

Davide Tebaldi, Roberto Zanasi

, Available online , doi: 10.1109/JAS.2025.125294

[Abstract](22) [FullText HTML] (0) [PDF 1487KB](2)

Abstract:
In this paper, the problem of nonlinear frictions identification in a class of nonlinear systems embedding different automotive case studies is addressed. The power-oriented modeling of the system dynamics is first addressed. Next, the identification of the nonlinear friction coefficients representing the system losses, which can have different symmetric or asymmetric characteristics, is addressed using a parabolic interpolation. To show the versatility of the procedure, two automotive physical systems composing the vehicle powertrain are considered as case studies for the identification, namely a Full Toroidal Variator and a Gearbox. The novelty of this work consists of the proposal of a general approach to model nonlinear frictions in a wide class of automotive systems, and in their identification using the proposed least-square-based algorithm. With reference to the latter, we also provide a necessary condition to avoid the rank deficiency problem and considerations about how to increase the identification accuracy.

A Recursive Method to Encryption-Decryption-Based Distributed Set-Membership Filtering for Time-Varying Saturated Systems Over Sensor Networks

Jun Hu, Jiaxing Li, Chaoqing Jia, Xiaojian Yi, Hongjian Liu

, Available online

[Abstract](22) [FullText HTML] (0) [PDF 486KB](4)

Abstract:

Cooperation Under Stochastic Punishment in Social Dilemma Situations

Shiping Gao, Jinghui Suo, Nan Li

, Available online

[Abstract](17) [FullText HTML] (0) [PDF 459KB](0)

Abstract:

Full Perception Head: Bridging the Gap Between Local and Global Features

Jie Hua, Zhongyuan Wang, Xin Tian, Qin Zou, Jinsheng Xiao, Jiayi Ma

, Available online , doi: 10.1109/JAS.2025.125333

[Abstract](37) [FullText HTML] (0) [PDF 40820KB](8)

Abstract:
Object detection is a fundamental task in computer vision that involves identifying and localizing objects within an image. In this context, local features capture fine-grained details such as edges and textures, while global features represent the overall structure and long-range relationships within the image. These features are crucial for accurate object detection, yet most existing methods focus on aggregating local and global features, often overlooking the importance of medium-range dependencies. To address this gap, we propose a novel Full Perception Module (FP-Module), a simple yet effective feature extraction module designed to simultaneously capture local details, medium-range dependencies, and long-range dependencies. Building on this, we construct a full perception head (FP-Head) by cascading multiple FP-Modules, enabling the prediction layer to leverage the most informative features. Experimental results in the MS COCO dataset demonstrate that our approach significantly enhances object recognition and localization, achieving 2.7−5.7 AP_val gains when integrated into standard object detectors. Notably, the FP-Module is a universal solution that can be seamlessly incorporated into existing detectors to boost performance. The code will be released soon.

Correlation-Guided Particle Swarm Optimization Approach for Feature Selection in Fault Diagnosis

Ke Chen, Wenjie Wang, Fangfang Zhang, Jing Liang, Kunjie Yu

, Available online , doi: 10.1109/JAS.2025.125306

[Abstract](140) [FullText HTML] (0) [PDF 1821KB](38)

Abstract:
A large number of features are involved in fault diagnosis, and it is challenging to identify important and relative features for fault classification. Feature selection selects suitable features from the fault dataset to determine the root cause of the fault. Particle swarm optimization (PSO) has shown promising results in performing feature selection due to its promising search effectiveness and ease of implementation. However, most PSO-based feature selection approaches for fault diagnosis do not adequately take domain-specific a priori knowledge into account. In this study, we propose a correlation-guided PSO feature selection approach for fault diagnosis that focuses on improving the initialisation effectiveness, individual exploration ability, and population diversity. To be more specific, an initialisation strategy based on feature correlation is designed to enhance the quality of the initial population, while a probability individual updating mechanism is proposed to improve the exploitation ability. In addition, a sample shrinkage strategy is developed to enhance the ability to jump out of local optimal. Results on four public fault diagnosis datasets show that the proposed approach can select smaller feature subsets to achieve higher classification accuracy than other state-of-the-art feature selection methods in most cases. Furthermore, the effectiveness of the proposed approach is also verified by examining real-world fault diagnosis problems.

Unified Output Feedback Based Prescribed Performance Consensus Tracking Control of Heterogeneous Multi-Agent Systems

Dahui Luo, Yujuan Wang, Frank L. Lewis, Yongduan Song

, Available online , doi: 10.1109/JAS.2024.125094

[Abstract](50) [FullText HTML] (0) [PDF 1788KB](30)

Abstract:
This paper proposes an output-feedback based prescribed performance consensus tracking control methodology for a class of heterogeneous multi-agent systems (HMASs) with inconsistent system structure, where the performance behavior is allowed to be different from that of each other. Both the heterogeneous system structures and the nonidentical performance requirements make the control problem much more challenging than that of MASs with identical structure and performance requirement. This is mainly due to the coupling effect of the system dynamics and performance restriction of each agent in the cooperative control action. The key to solve this problem is to introduce a dual-phase performance-guaranteed method, in which the consensus tracking error is decomposed into auxiliary tracking error and filter tracking error and then the whole performance control is decomposed into two phases. By confining the two errors respectively, the practical tracking error can be proved to be explicitly confined within an arbitrarily given performance envelope by merely adjusting the design parameters rather than modifying control structure. Moreover, the prescribed performance control (PPC) result is not only uniform with any initial conditions and design parameters, allowing it to be global, but also unifying both the global and semi-global result into one frame, distinguishing itself from most existing PPC works where either only global or only semi-global result is guaranteed. Finally, the effectiveness of the proposed control scheme is confirmed by the simulation conducted on a group of tunnel-diode circuits (TDC).

An Interpretable Temporal Convolutional Framework for Granger Causality Analysis

Aoxiang Dong, Andrew Starr, Yifan Zhao

, Available online , doi: 10.1109/JAS.2025.125396

[Abstract](93) [FullText HTML] (0) [PDF 4978KB](19)

Abstract:
Most existing parametric approaches for detecting linear or nonlinear Granger causality (GC) face challenges in estimating appropriate time delays, a critical factor for accurate GC detection. This issue becomes particularly pronounced in nonlinear complex systems, which are often opaque and consist of numerous components or variables. In this paper, we propose a novel temporal convolutional network (TCN)-based end-to-end GC detection approach called the Interpretable Temporal Convolutional Framework (ITCF). Unlike conventional deep learning models, which act like a “black box” and are difficult to analyse the interactions between variables, the proposed ITCF is able to detect both linear and nonlinear GC and automatically estimate time delay during the multivariant time series prediction. Specifically, GC is obtained by employing the Least Absolute Shrinkage and Selection Operator (Lasso) regression during the prediction of multivariate time series using TCN. Then, time delays can be estimated by interpreting the TCN kernels. We propose a convolutional Hierarchical Group Lasso (cHGL), a hierarchical regularisation approach to effectively utilise temporal information within each TCN channel for enhanced GC detection. Additionally, as far as we are concerned, this paper is the first to integrate the Iterative Soft-Thresholding Algorithm into the backpropagation of TCN to optimise the proposed cHGL, which enabling causal channel selection and inducing sparsity within each TCN channel to remove redundant temporal information, ultimately creating an end-to-end GC detection framework. The testing results of four experiments, involving two simulations and two real data, demonstrate that the proposed ITCF, in comparison with state-of-the-art, offers a more reliable estimation of GC relationships in complex systems featuring intricate dynamics, limited data lengths, or numerous variables.

Precision Synchronous Control of Multiple Motion Systems: A Tube-Based MPC Approach

Shuaiqi Chen, Fazhi Song, Yue Dong, Ning Cui, Yang Liu, Xinkai Chen

, Available online

[Abstract](48) [FullText HTML] (0) [PDF 3380KB](14)

Abstract:
Lithography machines operate in scanning mode for the fabrication of large-scale integrated circuits (ICs), requiring high-precision synchronous motion between the reticle and wafer stages. Disturbances generated by each stage during high-acceleration movements are transmitted through the base frame, resulting in degradation of synchronization performance. To address this challenge, this paper proposes a tube-based model predictive control (tube-MPC) approach for synchronization in lithography machines. First, the proposed modeling method accurately characterizes the coupling disturbances and synchronization dynamics. Subsequently, a tube-MPC approach is developed to ensure that the states of the nominal system are constrained within the terminal constraint set. To reduce the complexity of online computations, an approach is employed to transform online optimization problems into offline problems by creating an online lookup table. This enables the determination of optimal control inputs via a simplified online optimization algorithm. The robustness and trajectory tracking performance of the proposed approach are verified through simulation experiments, demonstrating its effectiveness in enhancing the synchronization performance of multiple motion systems.

CSDD: A Benchmark Dataset for Casting Surface Defect Detection and Segmentation

Kai Mao, Ping Wei, Yangyang Wang, Meiqin Liu, Shuaijie Wang, Nanning Zheng

, Available online

[Abstract](85) [FullText HTML] (0) [PDF 33247KB](18)

Abstract:
Automatic surface defect detection is a critical technique for ensuring product quality in industrial casting production. While general object detection techniques have made remarkable progress over the past decade, casting surface defect detection still has considerable room for improvement. Lack of sufficient and high-quality data has become one of the most challenging problems for casting surface defect detection. In this paper, we construct a new casting surface defect dataset (CSDD) containing 2100 high-resolution images of casting surface defects and 56356 defects in total. The class and defect region for each defect are manually labeled. We conduct a series of experiments on this dataset using multiple state-of-the-art object detection methods, establishing a comprehensive set of baselines. We also propose a defect detection method based on YOLOv5 with the global attention mechanism and partial convolution. Our proposed method achieves superior performance compared to other object detection methods. Additionally, we also conduct a series of experiments with multiple state-of-the-art semantic segmentation methods, providing extensive baselines for defect segmentation. To the best of our knowledge, the CSDD has the largest number of defects for casting surface defect detection and segmentation. It would benefit both the industrial vision research and manufacturing applications.

Finite-Time Sliding-Mode Control for Semi-Markov Systems With Delayed Impulses

Fangmin Ren, Xiaoping Wang, Yangmin Li, Zhigang Zeng

, Available online , doi: 10.1109/JAS.2024.125004

[Abstract](62) [FullText HTML] (0) [PDF 530KB](30)

Abstract:

Release Power of Mechanism and Data Fusion: A Hierarchical Strategy for Enhanced MIQ-Related Modeling and Fault Detection in BFIP

Siwei Lou, Chunjie Yang, Zhe Liu, Shaoqi Wang, Hanwen Zhang, Ping Wu

, Available online , doi: 10.1109/JAS.2024.124821

[Abstract](156) [FullText HTML] (0) [PDF 18699KB](44)

Abstract:
Data-driven techniques are reshaping blast furnace iron-making process (BFIP) modeling, but their “black-box” nature often obscures interpretability and accuracy. To overcome these limitations, our mechanism and data co-driven strategy (MDCDS) enhances model transparency and molten iron quality (MIQ) prediction. By zoning the furnace and applying mechanism-based features for material and thermal trends, coupled with a novel stationary broad feature learning system (StaBFLS), interference caused by nonstationary process characteristics are mitigated and the intrinsic information embedded in BFIP is mined. Subsequently, by integrating stationary feature representation with mechanism features, our temporal matching broad learning system (TMBLS) aligns process and quality variables using MIQ as the target. This integration allows us to establish process monitoring statistics using both mechanism and data-driven features, as well as detect modeling deviations. Validated against real-world BFIP data, our MDCDS model demonstrates consistent process alignment, robust feature extraction, and improved MIQ modeling—Yielding better fault detection. Additionally, we offer detailed insights into the validation process, including parameter baselining and optimization. Details of the code are available online.¹

Prescribed Performance Bipartite Consensus Control for MASs Under Data-Driven Strategy

Qi Zhou, Caiyun Yin, Hui Ma, Hongru Ren, Hongyi Li

, Available online

[Abstract](47) [FullText HTML] (0) [PDF 1355KB](28)

Abstract:
This paper investigates the bipartite consensus control problem for discrete time nonlinear multiagent systems (MASs) based on data-driven adaptive method. To begin with, a dynamic linearization strategy is utilized to establish the relationship between bipartite tracking error and control input for MASs. Secondly, the unknown parameter linearly associated with control input is acquired by the adaptive control approach, and a discrete time extended state observer is designed to estimate nonlinear uncertainties. Thirdly, in order to achieve the prescribed performance, the constrained bipartite consensus error is transformed through a strictly increasing function. Based on the converted equivalent unconstrained error function, a sliding mode controller using only the input and output data of the MASs is designed. Finally, the efficacy of the controller is confirmed by simulations.

Multi-Agent Swarm Optimization With Contribution-Based Cooperation for Distributed Multi-Target Localization and Data Association

Tai-You Chen, Xiao-Min Hu, Qiuzhen Lin, Wei-Neng Chen

, Available online , doi: 10.1109/JAS.2025.125150

[Abstract](102) [FullText HTML] (0) [PDF 1876KB](23)

Abstract:
With the development of communication and computation capabilities on terminal hardware, it is promising to apply distributed optimization methods to wireless sensor networks to improve the autonomous collaboration ability of sensors. In this work, we study distributed optimization for multi-target localization with measurement-to-measurement association (DM2M), where each sensor only accesses its own measurement data without the association of measurements from other sensors. We first reformulate DM2M into a distributed bilevel optimization problem to reduce the search space of negotiated variables caused by the data association among sensors. Then, we propose a multi-agent swarm optimization method with contribution-based cooperation (MASTER). In MASTER, each sensor maintains a particle swarm to represent candidate solutions of target positions. Sensors evolve their particle swarms through two phases of local optimization and neighbor cooperation to locate the target cooperatively. To address the bilevel local objective function, we combine the Kuhn-Munkres algorithm and the competitive swarm optimization for local optimization. To promote sensors to optimize the global objective, we design a contribution-based cooperation method to guide sensors to learn from their neighbors. Through localization experiments for different target numbers and localization dimensions, the proposed algorithm achieves smaller localization errors and more stable consensus than existing algorithms.

The Confluence of Evolutionary Computation and Multi-Agent Systems: A Survey

Tai-You Chen, Wei-Neng Chen, Feng-Feng Wei, Xiao-Qi Guo, Wen-Xiang Song, Rui Zhu, Qiuzhen Lin, Jun Zhang

, Available online , doi: 10.1109/JAS.2025.125246

[Abstract](234) [FullText HTML] (0) [PDF 1981KB](78)

Abstract:
Both evolutionary computation (EC) and multi-agent systems (MAS) study the emergence of intelligence through interaction and cooperation of a group of individuals. EC focuses on solving various complex optimization problems, while MAS provides a flexible model for distributed artificial intelligence. Since their group interaction mechanisms can be borrowed from each other, many studies have made attempts to combine EC and MAS. With the rapid development of Internet of Things, the confluence of EC and MAS has become more and more important, and related articles have shown a continuously growing trend during the last decades. In this survey, we first elaborate on the mutual assistance of EC and MAS from two aspects, agent-based EC and EC-assisted MAS. Agent-based EC aims to introduce characteristics of MAS into EC to improve the performance and parallelism of EC, while EC-assisted MAS aims to use EC to better solve optimization problems in MAS. Furthermore, we review studies that combine the cooperation mechanisms of EC and MAS, which greatly leverage the strengths of both sides. A description framework is built to elaborate existing studies. Promising future research directions are also discussed in conjunction with emerging technologies and real-world applications.

A Transactional-Behavior-Based Hierarchical Gated Network for Credit Card Fraud Detection

Yu Xie, MengChu Zhou, Guanjun Liu, Honghao Zhu, Lifei Wei, Pasquale De Meo

, Available online , doi: 10.1109/JAS.2025.125243

[Abstract](86) [FullText HTML] (0) [PDF 10000KB](17)

Abstract:
The task of detecting fraud in credit card transactions is crucial to ensure the security and stability of a financial system, as well as to enforce customer confidence in digital payment systems. Historically, credit card companies have used rule-based approaches to detect fraudulent transactions, but these have proven inadequate due to the complexity of fraud strategies and have been replaced by much more powerful solutions based on machine learning or deep learning algorithms. Despite significant progress, the current approaches to fraud detection suffer from a number of limitations: for example, it is unclear whether some transaction features are more effective than others in discriminating fraudulent transactions, and they often neglect possible correlations among transactions, even though they could reveal illicit behaviour. In this paper, we propose a novel credit card fraud detection (CCFD) method based on a transaction behaviour-based hierarchical gated network. First, we introduce a feature-oriented extraction module capable of identifying key features from original transactions, and such analysis is effective in revealing the behavioural characteristics of fraudsters. Second, we design a transaction-oriented extraction module capable of capturing the correlation between users’ historical and current transactional behaviour. Such information is crucial for revealing users’ sequential behaviour patterns. Our approach, called transactional-behaviour-based hierarchical gated network model (TbHGN), extracts two types of new transactional features, which are then combined in a feature interaction module to learn the final transactional representations used for CCFD. We have conducted extensive experiments on a real-world credit card transaction dataset with an increase in average F1 between 1.42% and 6.53% and an improvement in average AUC between 0.63% and 2.78% over the state of the art.

A Survey of Distributed Algorithms for Aggregative Games

Huaqing Li, Jun Li, Liang Ran, Lifeng Zheng, Tingwen Huang

, Available online , doi: 10.1109/JAS.2024.124998

[Abstract](143) [FullText HTML] (0) [PDF 983KB](10)

Abstract:
Game theory-based models and design tools have gained substantial prominence for controlling and optimizing behavior within distributed engineering systems due to the inherent distribution of decisions among individuals. In non-cooperative settings, aggregative games serve as a mathematical framework model for the interdependent optimal decision-making problem among a group of non-cooperative players. In such scenarios, each player’s decision is influenced by an aggregation of all players’ decisions. Nash equilibrium (NE) seeking in aggregative games has emerged as a vibrant topic driven by applications that harness the aggregation property. This paper presents a comprehensive overview of the current research on aggregative games with a focus on communication topology. A systematic classification is conducted on distributed algorithm research based on communication topologies such as undirected networks, directed networks, and time-varying networks. Furthermore, it sorts out the challenges and compares the algorithms’ convergence performance. It also delves into real-world applications of distributed optimization techniques grounded in aggregative games. Finally, it proposes several challenges that can guide future research directions.

Text2UA: Automatic OPC UA Information Modeling from Textual Data with Large Language Model

Rongkai Wang, Chaojie Gu, Shibo He, Jiming Chen

, Available online , doi: 10.1109/JAS.2025.125114

[Abstract](67) [FullText HTML] (0) [PDF 8118KB](8)

Abstract:

Applications of Domain Generalization to Machine Fault Diagnosis: A Survey

Yongyi Chen, Dan Zhang, Ruqiang Yan, Min Xie

, Available online , doi: 10.1109/JAS.2025.125120

[Abstract](89) [FullText HTML] (0) [PDF 2647KB](20)

Abstract:
In actual industrial scenarios, the variation of operating conditions, the existence of data noise, and failure of measurement equipment will inevitably affect the distribution of perceptive data. Deep learning-based fault diagnosis algorithms strongly rely on the assumption that source and target data are independent and identically distributed, and the learned diagnosis knowledge is difficult to generalize to out-of-distribution data. Domain generalization (DG) aims to achieve the generalization of arbitrary target domain data by using only limited source domain data for diagnosis model training. The research of DG for fault diagnosis has made remarkable progress in recent years and lots of achievements have been obtained. In this article, for the first time a comprehensive literature review on DG for fault diagnosis from a learning mechanism-oriented perspective is provided to summarize the development in recent years. Specifically, we first conduct a comprehensive review on existing methods based on the similarity of basic principles and design motivations. Then, the recent trend of DG for fault diagnosis is also analyzed. Finally, the existing problems and future prospect is performed.

Adaptive Fault-Tolerant Consensus Tracking Control for Nonlinear Multi-Agent Systems With Double Semi-Markovian Switching Topologies and Unknown Control Directions

Chao Zhou, Zehui Mao, Bin Jiang, Xing-Gang Yan

, Available online , doi: 10.1109/JAS.2025.125285

[Abstract](55) [FullText HTML] (0) [PDF 1845KB](17)

Abstract:
This paper is concerned with adaptive consensus tracking control of nonlinear multi-agent systems with actuator faults and unknown nonidentical control directions under double semi-Markovian switching topologies. Considering the complex working environment and the stability differences in communication links between leaders and followers, a double semi-Markov process is first introduced to describe the random switching of communication topologies in the leader-follower structure. In order to address challenges from the unknown nonidentical control directions and partial loss of effectiveness actuator faults, a completely independent parameter is introduced into the Nussbaum function to overcome the inherent obstacle of mutual cancellation and avoid the rapid growth rate. Considering only the state information of agents is transmitted among the agents, an adaptive distributed fault-tolerant consensus tracking control is proposed based on the double semi-Markovian switching topologies using the designed Nussbaum function. Furthermore, the stability of the closed-loop nonlinear multi-agent systems is analyzed using contradiction argument and Lyapunov theorem, from which the asymptotic consensus tracking in mean square sense can be obtained. A numerical simulation example is provided to verify the effectiveness of the proposed algorithm.

Distributed Event-Triggered Nash Equilibrium Seeking for Aggregative Game With Second-Order Dynamics

Yi Huang, Jian Sun, Qing Fei

, Available online , doi: 10.1109/JAS.2024.124830

[Abstract](84) [FullText HTML] (0) [PDF 447KB](19)

Abstract:

Neural Adaptive Sliding-Mode Control of Vehicular Cyber-Physical Systems With Uniformly Quantized Communication Data and Disturbances

Yuan Zhao, Mengchao Li, Zhongchang Liu, Lichuan Liu, Shixi Wen, Lei Ding

, Available online , doi: 10.1109/JAS.2025.125186

[Abstract](48) [FullText HTML] (0) [PDF 3255KB](27)

Abstract:
This paper investigates the platoon control of heterogeneous vehicular cyber-physical systems (VCPSs) subject to external disturbances by using neural network and uniformly quantized communication data. To reduce the adverse effects of quantization errors on system performance, a coupling sliding mode surface is established for each following vehicle. The radial basis function (RBF) neural networks are employed to approximate the unknown external disturbances. Then, a novel platoon control law is proposed for cooperative tracking in which each following vehicle only uses the uniformly quantized data of the neighboring vehicles. And the designed controllers in this paper are fully distributed due to the fact that the selection of each vehicle’s controller parameters is independent of the entire communication topology. The string stability of VCPSs in the entire control process is ensured rather than only ensuring the string stability after the sliding mode surface converges to zero. Compared with the existing controller design methods and quantization mechanisms, the neural adaptive sliding-mode platoon controller proposed in this paper is superior in performances including tracking errors, driving comfort and fuel economy. Numerical simulations illustrate the effectiveness and superiority of the designed control strategy.

Multi-UAV Cooperative Pursuit Strategy With Limited Visual Field in Urban Airspace: A Multi-Agent Reinforcement Learning Approach

Zhe Peng, Guohua Wu, Biao Luo, Ling Wang

, Available online , doi: 10.1109/JAS.2024.124965

[Abstract](57) [FullText HTML] (0) [PDF 8179KB](21)

Abstract:
The application of multiple unmanned aerial vehicles (UAVs) for the pursuit and capture of unauthorized UAVs has emerged as a novel approach to ensuring the safety of urban airspace. However, pursuit UAVs necessitate the utilization of their own sensors to proactively gather information from the unauthorized UAV. Considering the restricted sensing range of sensors, this paper proposes a multi-UAV with limited visual field pursuit-evasion (MUV-PE) problem. Each pursuer has a visual field characterized by limited perception distance and viewing angle, potentially obstructed by buildings. Only when the unauthorized UAV, i.e., the evader, enters the visual field of any pursuer can its position be acquired. The objective of the pursuers is to capture the evader as soon as possible without collision. To address this problem, we propose the normalizing flow actor with graph attention critic (NAGC) algorithm, a multi-agent reinforcement learning (MARL) approach. NAGC executes normalizing flows to augment the flexibility of policy network, enabling the agent to sample actions from more intricate distributions rather than common distributions. To enhance the capability of simultaneously comprehending spatial relationships among multiple UAVs and environmental obstacles, NAGC integrates the “obstacle-target” graph attention networks, significantly aiding pursuers in supporting search or pursuit activities. Extensive experiments conducted in a high-precision simulator validate the promising performance of the NAGC algorithm.

Path Following Control of Uncertain and Underactuated Autonomous Surface Vessels

Yang Wu, Yueying Wang, Zhiguang Feng, Xiangpeng Xie

, Available online , doi: 10.1109/JAS.2024.124713

[Abstract](141) [FullText HTML] (0) [PDF 585KB](53)

Abstract:

Innovations and Refinements in LiDAR Odometry and Mapping: A Comprehensive Review

Guangjie Liu, Kai Huang, Xiaolan Lv, Yuanhao Sun, Hailong Li, Xiaohui Lei, Quanchun Yuan, Lei Shu

, Available online , doi: 10.1109/JAS.2025.125198

[Abstract](216) [FullText HTML] (0) [PDF 14486KB](42)

Abstract:
Since its introduction in 2014, the LiDAR odometry and mapping (LOAM) algorithm has become a cornerstone in the fields of autonomous driving and intelligent robotics. LOAM provides robust support for autonomous navigation in complex dynamic environments through precise localization and environmental mapping. This paper offers a comprehensive review of the innovations and optimizations made to the LOAM algorithm, covering advancements in multi-sensor fusion technology, frontend processing optimization, backend optimization, and loop closure detection. These improvements have significantly enhanced LOAM’s performance in various scenarios, including urban, agricultural, and underground environments. However, challenges remain in areas such as data synchronization, real-time processing, computational complexity, and environmental adaptability. Looking ahead, future developments are expected to focus on creating more efficient multi-sensor fusion algorithms, expanding application domains, and building more robust systems, thereby driving continued progress in autonomous driving, intelligent robotics, and autonomous unmanned systems.

Online Estimation of DC-link Capacitor Para-meters of Three-Level NPC Converters Using Inherent Signals Analysis

Ricardo Lucio de Araujo Ribeiro, Reuben Palmer Rezende de Sousa, Alexandre Cunha Oliveira, Antonio Marcus Nogueira Lima, Qing-Long Han

, Available online , doi: 10.1109/JAS.2025.125159

[Abstract](77) [FullText HTML] (2) [PDF 2036KB](13)

Abstract:
This paper presents a method for estimating the parameters of DC-link capacitors in three-level NPC voltage source inverters (3L-NPC-VSI) used in grid-tied systems. The technique uses the signals generated by the intermodulation caused by the PWM strategy and converter topology interaction to estimate the capacitor parameters of the converter DC-link. It utilizes an observer-based structure consisting of a recursive noninteger sliding discrete Fourier transform (rnSDFT) and an RLS filter improved with a forgetting factor (oSDFT-RLS) to accurately estimate the capacitance and equivalent series resistance (ESR). Importantly, this method does not require additional sensors beyond those already installed in off-the-shelf 3L-NPC-VSI systems, ensuring its noninvasiveness. Furthermore, the oSDFT-RLS estimates capacitor parameters in the time-frequency domain, enabling the tracking of capacitor degradation and predicting potential faults. Experimental results from the laboratory setup demonstrate the effectiveness of the proposed condition monitoring method.

A Survey on Rough Feature Selection: Recent Advances and Challenges

Keyu Liu, Xibei Yang, Weiping Ding, Hengrong Ju, Tianrui Li, Jie Wang, Tengyu Yin

, Available online , doi: 10.1109/JAS.2025.125231

[Abstract](173) [FullText HTML] (0) [PDF 2521KB](61)

Abstract:
Advances in data acquisition and accumulation on a massive scale are fueling “the curse of dimensionality” which may deteriorate the generalization performance of machine learning models. Such a dilemma gives birth to the technique of feature selection excelling in the presence of high-dimensional data. As a specific method based on rough set theory, Rough Feature Selection (RFS) has been widely concerned and fruitfully applied. In this survey, we provide a comprehensive review of RFS algorithms that have proliferated in recent years. Firstly, we briefly introduce some typical rough set models especially neighborhood rough set and fuzzy rough set, as well as representative rough feature evaluation criteria. We then systematically discuss several emerging topics of RFS including accelerated, ensemble, incremental, label ambiguous, weakly-supervised, and multi-granularity RFS. Additionally, we illuminate the regular performance validation scheme of RFS and conduct a number of experiments to present benchmarking results of state-of-the-art RFS algorithms. Finally, we summarize the pros and cons of existing research efforts and outline the open challenges and opportunities of class imbalance, multi-modal scenario, causality inference, and high-level representation for RFS. By providing in-depth knowledge of RFS, we anticipate this survey will: 1) serve as a guidebook for newcomers intending to delve into RFS and a stepping-stone for researchers and practitioners to solve domain-specific problems; 2) gain insights into the state-of-the-art published findings, triggering a series of breakthroughs in RFS; 3) underscore some challenges ahead of RFS, directing future efforts toward punctuating advances beyond questions currently pursued.

Efficient Knowledge-guided Self-evolving Intelligent Behavioral Control for Autonomous Vehicles

Qiao Peng, Kailong Liu, Jingda Wu, Amir Khajepour

, Available online , doi: 10.1109/JAS.2024.124746

[Abstract](52) [FullText HTML] (0) [PDF 715KB](9)

Abstract:

KT-RC: Kernel Time-Delayed Reservoir Computing for Time Series Prediction

Heshan Wang, Mengmeng Chen, Kunjie Yu, Jing Liang, Zhaomin Lv, Zhong Zhang

, Available online , doi: 10.1109/JAS.2024.124986

[Abstract](92) [FullText HTML] (0) [PDF 9327KB](26)

Abstract:
Reservoir computing (RC) is an efficient recurrent neural network (RNN) method. However, the performance and prediction results of traditional RCs are susceptible to several factors, such as their network structure, parameter setting, and selection of input features. In this study, we employ a kernel time-delayed RC (KT-RC) method for time series prediction. The KT-RC transforms input vectors linearly to obtain a high-dimensional set of time-delayed linear eigenvectors, which are then transformed by various kernel functions to represent the nonlinear characteristics of the input signal. Finally, the Bayesian optimization algorithm adjusts the few remaining weights and kernel parameters to minimize the manual adjustment process. The advantages of KT-RC can be summarized as follows: 1) KT-RC solves the problems of uncertainty in weight matrices and difficulty in large-scale parameter selection in the input and hidden layers of RCs. 2) The KT module can avoid massive reservoir hyperparameters and effectively reduce the hidden layer size of the traditional RC. 3) The proposed KT-RC shows good performance, strong stability, and robustness in several synthetic and real-world datasets for one-step-ahead and multistep-ahead time series prediction. The simulation results confirm that KT-RC not only outperforms some gate-structured RNNs, kernel vector regression models, and recently proposed prediction models but also requires fewer parameters to be initialized and can reduce the hidden layer size of the traditional RCs. The source code is available at https://github.com/whs7713578/RC.

LTDNet: A Lightweight Text Detector for Real-Time Arbitrary-Shape Traffic Text Detection

Runmin Wang, Yanbin Zhu, Ziyu Zhu, Lingxin Cui, Zukun Wan, Anna Zhu, Yajun Ding, Shengyou Qian, Changxin Gao, Nong Sang

, Available online , doi: 10.1109/JAS.2024.125022

[Abstract](140) [FullText HTML] (0) [PDF 14194KB](34)

Abstract:
Traffic text detection plays a vital role in understanding traffic scenes. Traffic text, a distinct subset of natural scene text, faces specific challenges not found in natural scene text detection, including false alarms from non-traffic text sources, such as roadside advertisements and building signs. Existing state-of-the-art methods employ increasingly complex detection frameworks to pursue higher accuracy, leading to challenges with real-time performance. In response to this issue, we propose a real-time and efficient traffic text detector named LTDNet, which strikes a balance between accuracy and real-time capabilities. LTDNet integrates three essential techniques to address these challenges effectively. First, a cascaded multilevel feature fusion network is employed to mitigate the limitations of lightweight backbone networks, thereby enhancing detection accuracy. Second, a lightweight feature attention module is introduced to enhance inference speed without compromising accuracy. Finally, a novel point-to-edge distance vector loss function is proposed to precisely localize text instance boundaries within traffic contexts. The superiority of our method is validated through extensive experiments on five publicly available datasets, demonstrating its state-of-the-art performance. The code will be released at https://github.com/runminwang/LTDNet.

An Emulation Approach to Semi-Global Robust Output Regulation for a Class of Nonlinear Uncertain Systems

Jieshuai Wu, Maobin Lu, Fang Deng, Jie Chen

, Available online , doi: 10.1109/JAS.2024.125085

[Abstract](82) [FullText HTML] (0) [PDF 1184KB](20)

Abstract:
In this paper, we investigate the semi-global robust output regulation problem of a class of nonlinear networked control systems. By the emulation approach, we propose a class of sampled-data output feedback control laws to solve this problem. In particular, we first develop a general sampled-data dynamic output feedback control law and characterize the closed-loop system by a hybrid system. Then, we design the internal model based on the sampled error output of the system. Based on the internal model principle, we convert the semi-global robust output regulation problem into a semi-global robust stabilization problem of an augmented hybrid system composed of the internal model and the original system. By proposing the sampled error output feedback control law and by means of Lyapunov analysis, we obtain the maximum allowable transmission interval for sampling and show that semi-global robust stabilization of the augmented hybrid system can be achieved by the proposed sampled-data control law and thus leading to the solution of the semi-global robust output regulation problem. Finally, we apply the proposed control approach to two practical applications to verify the effectiveness of the proposed control approach.

Bearings-Only Target Motion Analysis Via Deep Reinforcement Learning

Chengyi Zhou, Meiqin Liu, Senlin Zhang, Ronghao Zheng, Shanling Dong

, Available online

[Abstract](52) [FullText HTML] (0) [PDF 334KB](10)

Abstract:

A Homotopy Method for Continuous-Time Model-Free LQR Control Based on Policy Iteration

Wenwu Fan, Junlin Xiong

, Available online , doi: 10.1109/JAS.2025.125132

[Abstract](78) [FullText HTML] (0) [PDF 1038KB](22)

Abstract:
In recent years, reinforcement learning control theory has been well developed. However, model-free value iteration needs many iterations to achieve the desired precision, and model-free policy iteration requires an initial stabilizing control policy. It is significant to propose a fast model-free algorithm to solve the continuous-time linear quadratic control problem without an initial stabilizing control policy. In this paper, we construct a homotopy path on which each point corresponds to an linear quadratic regulator problem. Based on policy iteration, model-based and model-free homotopy algorithms are proposed to solve the optimal control problem of continuous-time linear systems along the homotopy path. Our algorithms are speeded up using first-order differential information and do not require an initial stabilizing control policy. Finally, several practical examples are used to illustrate our results.

An Intelligent Optimization Strategy for Blast Furnace Charging Operation Considering Three-Dimensional Burden Surface Shape

Jicheng Zhu, Zhaohui Jiang, Dong Pan, Haoyang Yu, Chuan Xu, Ke Zhou, Weihua Gui

, Available online , doi: 10.1109/JAS.2025.125192

[Abstract](126) [FullText HTML] (0) [PDF 4132KB](26)

Abstract:
Today, a well-devised charging operation scheme is urgently needed by on-site workmen and is critical for building an intelligent blast furnace (BF). Previous research on charging operations always focused on the two-dimensional shape of the burden surface (i.e., a single radial profile) while neglecting the unique feature of global dissymmetry, severely restricting the development of precise charging. For this reason, this study proposes an innovative optimization strategy for the charging operation under the three-dimensional burden surface, which is the first attempt in this field. First, a practicable region partitioning scheme is introduced, and the partitioning results are then integrated with the charging mechanism to construct a three-dimensional burden surface prediction model. Next, the intrinsic relationship between the operational parameters and charging volume is revealed based on the law of mass conservation, which forms the basis for defining a novel operational parameter with variable-speed utility, referred to as the neotype charging matrix (NCM). To find the best NCM, a customized NCM optimization strategy, involving a dual constraint handling technique in conjunction with a two-stage hybrid variable differential evolution algorithm, is further developed. The industrial experiment results manifest that the partitioning scheme significantly enhances the accuracy of burden surface description. Moreover, the NCM optimization strategy offers greater flexibility and higher accuracy than current mainstream optimization strategies for the charging matrix (CM).

Camera Planning for Physical Safety of Outdoor Electronic Devices: Perspective and Analysis

Qin Su, Lei Shu, Gerhard Petrus Hancke, Kai Huang, Edmond Nurellari, Qingsong Zhao, Nikumani Choudhury, Anakhi Hazarika

, Available online , doi: 10.1109/JAS.2025.125129

[Abstract](154) [FullText HTML] (0) [PDF 2265KB](28)

Abstract:
Camera technology advancement and deployment continue to play a vital role in modern life and production, amongst other capabilities, generating relevant visual information. The challenge of optimizing the use and deployment of camera networks in various applications (e.g., surveillance, traffic monitoring, and public safety to name but just a few) has attracted considerable attention from both academia and industries. Camera planning is the first step in addressing this challenge. The surveillance objectives and scenes of a camera network dictate the modelling and optimization algorithms for camera planning. However, existing reviews have primarily focused on models or optimization algorithms, with insufficient attention given to surveillance scenes. This review aims to bridge this gap by 1) Classifying surveillance scenes into the urban environment and rural outdoor environment and comparing the surveillance requirements and challenges; 2) Summarizing the details of camera coverage optimization in the relevant literature from the perspective of deployment scenes; and 3) Proposing a new surveillance scene—Solar Insecticidal Lamps with the Internet of Things—as a case study to analyze the surveillance requirement and challenges in agricultural outdoor environment. Finally, we state the technical outlook on the physical safety of outdoor electronic devices in agriculture settings and provide insights to draw more attention and effort into this area.

Comprehensive Dynamic Model of Vertical Pneumatic Bellows Actuator System Considering Bidirectional Asymmetric Hysteresis

Huai Xiao, Xuzhi Lai, Qingxin Meng, Jinhua She, Edwardo F. Fukushima, Min Wu

, Available online , doi: 10.1109/JAS.2025.125162

[Abstract](62) [FullText HTML] (0) [PDF 4366KB](8)

Abstract:
The complex nonlinear characteristics of pneumatic soft actuators, such as asymmetric hysteresis, rate-dependence, and mechanical load-dependence, pose a challenge in accurately modeling their dynamics. To address this challenge, this paper proposes a comprehensive dynamic model aimed at describing bidirectional asymmetric hysteresis, rate-dependent, and mechanical load-dependent characteristics of a vertical pneumatic bellows actuator (PBA) system. The dynamic model contains a hysteresis submodel and a load-dependent dynamic submodel. The hysteresis submodel consists of several sets of weighted double-side play (DSP) and weighted dead-zone (DZ) operators connected in series, and it is used to model the bidirectional asymmetric hysteresis of the system. The load-dependent dynamic submodel is built based on the gated recurrent unit (GRU) neural network, and it is used to fit the nonlinear relationship between the displacement of the system and the frequency of the input air pressure as well as the mechanical load. The model parameters of the hysteresis submodel and the load-dependent dynamic submodel are determined by intelligent optimization method and neural network training method, reseparately. The fitness value (FV) between the output of the dynamic model and the experimental data is calculated to be 96.1736%, demonstrating that the parameters of the dynamic model are valid. We conduct six set of experiments to compare the model output with the experimental data, and calculate the root-mean-square errors and the maximum error, respectively. The experimental results show that, the root-mean-square error remains consistently below 2.7700%, while the maximum error remains below 8.4000% across all experiments, thereby substantiating the validity and generality of the proposed model.

CRDet: An Artificial Intelligence-Based Framework for Automated Cheese Ripeness Assessment From Digital Images

Alessandra Perniciano, Luca Zedda, Cecilia Di Ruberto, Barbara Pes, Andrea Loddo

, Available online , doi: 10.1109/JAS.2024.125061

[Abstract](112) [FullText HTML] (0) [PDF 5395KB](27)

Abstract:
Assessing cheese quality and ripeness is a crucial challenge in the dairy industry, with significant implications for product quality, consumer satisfaction, and economic impact. Traditional evaluation methods relying on visual inspection and human expertise are susceptible to errors and time constraints. This study proposes an innovative approach leveraging machine learning and computer vision techniques for automated cheese ripeness detection to address these limitations.The key contributions of this work include the release of the first comprehensive public dataset of cheese wheel images depicting various products at different ripening stages comprising more than 775 images, CR-IDB, an extensive comparative analysis of the performance of machine learning classifiers trained with features extracted from convolutional neural networks and handcrafted descriptors, along with the evaluation of different feature selection techniques, and finally, a proposal of a novel AI-based framework built upon a Random Forest classifier for cheese ripeness detection, called CRDet.The novelty of CRDet lies in its enforceability across multiple types and dairy industries, which has not been previously addressed in the literature. Unlike earlier methodologies that focused on specific cheese types or relied on subjective visual inspections, this study introduces a comprehensive, noninvasive, and automated approach that demonstrates superior classification performance in differentiating ripeness phases. Thus, it overcomes the limitations of traditional methods and enhances the reliability of cheese ripening assessments.With performance in terms of F1 above 90%, the proposed approach reduces reliance on human expertise, ensuring efficient and reliable evaluation methods for the diverse cheese production landscape. The findings provide valuable insights into the potential of feature selection methods for advancing cheese quality analysis, with implications for the broader dairy industry.

Event-Triggered Adaptive Horizon DMPC for Discrete-Time Coupled Nonlinear Systems

Rui Guo, Jianwen Feng, Jingyi Wang, Yi Zhao

, Available online , doi: 10.1109/JAS.2024.124704

[Abstract](63) [FullText HTML] (0) [PDF 643KB](14)

Abstract:

Deep Reinforcement Learning for Zero-Shot Coverage Path Planning With Mobile Robots

José Pedro Carvalho, A. Pedro Aguiar

, Available online , doi: 10.1109/JAS.2024.125064

[Abstract](304) [FullText HTML] (0) [PDF 1606KB](91)

Abstract:
The ability of mobile robots to plan and execute a path is foundational to various path-planning challenges, particularly Coverage Path Planning. While this task has been typically tackled with classical algorithms, these often struggle with flexibility and adaptability in unknown environments. On the other hand, recent advances in Reinforcement Learning offer promising approaches, yet a significant gap in the literature remains when it comes to generalization over a large number of parameters. This paper presents a unified, generalized framework for coverage path planning that leverages value-based deep reinforcement learning techniques. The novelty of the framework comes from the design of an observation space that accommodates different map sizes, an action masking scheme that guarantees safety and robustness while also serving as a learning-from-demonstration technique during training, and a unique reward function that yields value functions that are size-invariant. These are coupled with a curriculum learning-based training strategy and parametric environment randomization, enabling the agent to tackle complete or partial coverage path planning with perfect or incomplete knowledge while generalizing to different map sizes, configurations, sensor payloads, and sub-tasks. Our empirical results show that the algorithm can perform zero-shot learning scenarios at a near-optimal level in environments that follow a similar distribution as during training, outperforming a greedy heuristic by sixfold. Furthermore, in out-of-distribution environments, our method surpasses existing state-of-the-art algorithms in most zero-shot and all few-shot scenarios, paving the way for generalizable and adaptable path-planning algorithms.

FDTs: A Feature Disentangled Transformer for Interpretable Squamous Cell Carcinoma Grading

Pan Huang, Xin Luo

, Available online

[Abstract](162) [FullText HTML] (0) [PDF 6689KB](22)

Abstract:

Global Sampled-Data Output Feedback Stabilization for Nonlinear Systems via Intermittent Hold

Le Chang, Cheng Fu, Huanjun Zhang

, Available online

[Abstract](100) [FullText HTML] (0) [PDF 1318KB](37)

Abstract:
This paper introduces a sampled-data and intermittent-hold controller for nonlinear feedforward systems. The intermittent hold allows the control signal to be held in a portion of each sampled period, which does not require the control to be persistently implemented, and thus has less control time. But, less control time degrades the performance of a continuous-time control system or even destabilizes it, especially when the holding portion is sufficiently small. To tackle this obstacle, we first introduce the notion of activating rate to describe the intermittent hold, and give the sampled-data and intermittent-hold controller based on some tuning parameters. Then it is proved that for any activating rate, these parameters can be designed to achieve the stability of the considered systems under appropriately choosing the sampling size. Finally, simulation examples are given to illustrate the effectiveness of the proposed method.

Fixed-Time Stability of Random Nonlinear Systems

Fuyong Wang, Jiayi Gong, Zhongxin Liu, Fei Chen

, Available online , doi: 10.1109/JAS.2024.124353

[Abstract](89) [FullText HTML] (0) [PDF 471KB](17)

Abstract:

DoS Attack Schedules for Remote State Estimation in CPSs with two-hop relay networks Under Round-Robin Protocol

Shuo Zhang, Lei Miao, Xudong Zhao

, Available online , doi: 10.1109/JAS.2024.124755

[Abstract](88) [FullText HTML] (0) [PDF 369KB](20)

Abstract:

Convex Optimization-Based Model Predictive Control for Mars Ascent Vehicle Guidance System

Kun Li, Yanning Guo, Guangtao Ran, Yueyong Lyu, Guangfu Ma

, Available online , doi: 10.1109/JAS.2024.124587

[Abstract](80) [FullText HTML] (0) [PDF 486KB](23)

Abstract:

Improving Control Performance by Cascading Observers: Case of ADRC With Cascade ESO

Ahmed T.-E. Benyahia, Momir Stanković, Rafal Madonski, Oluleke Babayomi, Stojadin M. Manojlović

, Available online , doi: 10.1109/JAS.2024.124995

[Abstract](122) [FullText HTML] (0) [PDF 3229KB](32)

Abstract:
In this paper, we show the performance benefits of connecting multiple observers within a control system. We focus here on a particular observer-based control approach, namely the active disturbance rejection control (ADRC) with cascade extended state observer (ESO). For this framework, we analyze the control performance in terms of quality of observer estimation, reference tracking, disturbance rejection, sensitivity to measurement noise/unmodeled dynamics, and overall stability. A comprehensive frequency response analysis is performed to study the influence of cascading the observers on the selected quality criteria. To make the inquiry beneficial also to practitioners, FPGA-in-the-loop tests are conducted using a guided missiles gimbaled seeker. They validate the theoretical findings in discrete-time settings, where the sampling time and hardware resource requirements become a factor. The results of the investigation are distilled into guidelines for prospective users on when and how a cascade observer structure can be useful for controls.

A Learning-Based Passive Resilient Controller for Cyber-Physical Systems: Countering Stealthy Deception Attacks and Complete Loss of Actuators Control Authority

Liang Xin, Zhi-Qiang Long

, Available online , doi: 10.1109/JAS.2024.124683

[Abstract](157) [FullText HTML] (0) [PDF 2804KB](30)

Abstract:
Cyber-physical systems (CPSs) are increasingly vulnerable to cyber-attacks due to their integral connection between cyberspace and the physical world, which is augmented by Internet connectivity. This vulnerability necessitates a heightened focus on developing resilient control mechanisms for CPSs. However, current observer-based active compensation resilient controllers exhibit poor performance against stealthy deception attacks (SDAs) due to the difficulty in accurately reconstructing system states because of the stealthy nature of these attacks. Moreover, some non-active compensation approaches are insufficient when there is a complete loss of actuator control authority. To address these issues, we introduce a novel learning-based passive resilient controller (LPRC). Our approach, unlike observer-based state reconstruction, shows enhanced effectiveness in countering SDAs. We developed a safety state set, represented by an ellipsoid, to ensure CPS stability under SDA conditions, maintaining system trajectories within this set. Additionally, by employing deep reinforcement learning (DRL), the LPRC acquires the capacity to adapt and diverse evolving attack strategies. To empirically substantiate our methodology, various attack methods were compared with current passive and active compensation resilient control methods to evaluate their performance.

SILIC: Intelligent On/Off Control for Networked Solar Insecticidal Lamps

Heyang Yao, Lei Shu, Yuli Yang, Miguel Martínez-García, Wei Lin

, Available online

[Abstract](154) [FullText HTML] (0) [PDF 1873KB](23)

Abstract:
The solar insecticidal lamp (SIL) is an innovative green control device. Nevertheless, a major challenge is often encountered when carrying out insecticidal work is low energy utilization efficiency. The substantial energy consumption required to turn on the SIL, coupled with the extension of insecticidal working time during the low pest activity periods, can result in low energy efficiency. Especially when the energy storage level is below 50%, the inefficient use of energy significantly reduces the effectiveness of pest control. Consequently, an ineffective on/off scheme for these lamps may lead to suboptimal energy utilization. In this paper, we present the solar insecticidal lamp intelligent energy management scheme (SIL-IEMS) to address the challenge of inefficient energy utilization in the solar insecticidal lamp internet of things (SIL-IoT). SIL-IEMS primarily utilizes genetic algorithm (GA) and greedy algorithms to optimize insecticidal working time by considering constraints such as residual energy and the number of trap pests. Comparing SIL-IEMS to the traditional remote switching method (TRSM) and the solar insecticidal lamp genetic algorithm (SILGA), our simulation results showcase its superior energy efficiency and pest control effectiveness. Particularly noteworthy is the SILIEMS’s 17.6% increase in insecticidal efficiency compared to TRSM and 6% improvement over SILGA when the SIL begins with a remaining energy level of 15%.

From Singleton to Collaboration: Robust 3D Cooperative Positioning for Intelligent Connected Vehicles Based on Hybrid Range-Azimuth-Elevation Under Zero-Trust Driving Environments

Zhenyuan Zhang, Heng Qin, Darong Huang, Xin Fang, Mu Zhou, Shenghui Guo

, Available online

[Abstract](296) [FullText HTML] (0) [PDF 9820KB](67)

Abstract:
Reliable and accurate cooperative positioning is vital to intelligent connected vehicles (ICVs), in which vehicle-vehicle relative measurements are integrated to provide stable location-aware services. However, in zero-trust autonomous driving environments, the possibility of measurement failures and malicious communication attacks tends to reduce positioning performance. With this in mind, this paper presents an ultra-wide bandwidth (UWB) based cooperative positioning system with the specific objective of ICV localization in zero-trust driving environments. Firstly, to overcome measurement degradation under non-line-of-sight (NLOS) propagation conditions, this study proposes a decentralized 3D cooperative positioning method based on a distributed Kalman filter (DKF) by integrating relative range-azimuth-elevation measurements, unlike the state-of-the-art methods that rely on only one single relative range information to update motion states. More specifically, in contrast to pioneering studies that mainly focus on the positioning problem arising from only one single type of communication attack (either false data injection (FDI) or denial of service (DoS)), we consider a more challenging case of secure cooperative state estimation under mixed FDI and DoS attacks. To this end, a singular-value decomposition (SVD)-assisted decoupled DKF algorithm is proposed in this work, in which a novel update-triggered inter-vehicular communication mechanism is introduced to ensure robust positioning performance against communication attacks while maintaining low transmission load between individuals. To verify the effectiveness in practical 3D NLOS scenarios, we design an intelligent connected multi-robot platform based on a robot operating system (ROS) and UWB technology. Consequently, extensive experimental results demonstrate its superiority and feasibility by achieving a high positioning accuracy of 0.68 m under adverse attacks, especially in the case of hybrid FDI and DoS attacks. In addition, several critical discussions, including the impact of attack parameters, resilience assessment, and a comparison with event-triggered methods, are provided in this work. Moreover, a demo video has been uploaded in the supplementary materials for a detailed presentation.

Nonlinear Integral-Ameliorated Model for Dynamic Convex Optimization With Perturbance Considered

Kangze Zheng, Yunong Zhang

, Available online

[Abstract](66) [FullText HTML] (0) [PDF 8944KB](8)

Abstract:
This work presents a nonlinear integral-ameliorated model for handling dynamic optimization problems with affine constraints. They pose a challenge as their optimal solutions evolve with time. Traditional iteration-based methods that exactly solve the problem at each time instant, fail to precisely and real-time track the solution due to computational and communication bottlenecks. Our model, through rigorous theoretical analyses, is able to reduce the optimality gap (i.e., the difference between the model state and optimal solution) to zero in a finite time, and thus, track the solution online. Besides, perturbance is taken into account. We prove that under certain conditions, our model can totally tolerate an important kind of noise that we call “error-related noise”. In numerical experiments, compared with six existing methods, our model exhibits superior robustness when contaminated by the error-related noise. The key techniques in the model design involve employing the zeroing neural network to leverage time-derivative information, and introducing an integral term as well as the class $ {{{\mathrm{C}}}^0_\text{L}} $ functions to enhance convergence and noise resistance. Finally, we establish a model-free control framework for a surgical manipulator with the remote-center-of-motion constraint and compare the performances of the framework based on different models in simulations. The results indicate that our model achieves the best performance among various models employed within the framework.

GT-A²T: Graph Tensor Alliance Attention Network

Ling Wang, Kechen Liu, Ye Yuan

, Available online , doi: 10.1109/JAS.2024.124863

[Abstract](138) [FullText HTML] (0) [PDF 592KB](31)

Abstract:

Fuzzy Prescribed-Time Control for Uncertain Nonlinear Pure Feedback Systems

Qidong Li, Changchun Hua, Kuo Li

, Available online , doi: 10.1109/JAS.2024.124848

[Abstract](111) [FullText HTML] (0) [PDF 1116KB](24)

Abstract:

Feature-Driven Variational Mesh Denoising

Jianbin Yang, Cong Wang, Hui Hou, Mingyuan Wang, Xuelong Li

, Available online , doi: 10.1109/JAS.2024.124923

[Abstract](58) [FullText HTML] (0) [PDF 1811KB](10)

Abstract:
This work elaborates an innovative mesh denoising approach that combines feature recovery and denoising in an alternating manner. It proposes a feature-driven variational model and introduces an iterative scheme that alternates between feature recovery and the denoising process. The main idea is to estimate feature candidates, filter noisy face normals in the smooth (non-feature) domain, and utilize erosion and dilation operators on the feature candidates. By imposing connectivity constraints on normal vectors with large amplitude variations, the proposed scheme effectively removes noise and progressively recovers both sharp and small-scale features during the iterative process. To validate its effectiveness, this work conducts extensive numerical experiments on both simulated and real-scanned data. The results demonstrate significant improvements in noise reduction and feature preservation compared to existing methods.

Robust Pose Graph Optimization Against Outliers Using Consistency Credibility Factor

Jie Cai, Guoliang Wei, Wangyan Li, Yaolei Wang

, Available online , doi: 10.1109/JAS.2023.123897

[Abstract](79) [FullText HTML] (0) [PDF 513KB](7)

Abstract:

Federated Experiments: Generative Causal Inference Powered by LLM-based Agents Simulation and RAG-based Domain Docking

De-Yu Zhou, Xiao Xue, Qun Ma, Chao Guo, Li-Zhen Cui, Yong-Lin Tian, Jing Yang, Fei-Yue Wang

, Available online , doi: 10.1109/JAS.2024.124671

[Abstract](208) [FullText HTML] (0) [PDF 682KB](64)

Abstract:

Data-Driven Iterative Learning Consensus Tracking Based on Robust Neural Models for Unknown Heterogeneous Nonlinear Multiagent Systems With Input Constraints

Chong Zhang, Yunfeng Hu, TingTing Wang, Xun Gong, Hong Chen

, Available online

[Abstract](103) [FullText HTML] (0) [PDF 409KB](22)

Abstract:

Distributed Optimal Formation Control of Unmanned Aerial Vehicles: Theory and Experiments

Gang Wang, Zhenhong Wei, Peng Li

, Available online , doi: 10.1109/JAS.2024.124518

[Abstract](176) [FullText HTML] (0) [PDF 4081KB](50)

Abstract:

Non-Singular Practical Fixed-time Prescribed Performance Adaptive Fuzzy Consensus Control for Multi-Agent Systems Based on an Observer

Chi Ma, Dianbiao Dong

, Available online , doi: 10.1109/JAS.2024.124428

[Abstract](157) [FullText HTML] (0) [PDF 2534KB](57)

Abstract:
In this paper, the problem of non-singular fixed-time control with prescribed performance is studied for multi-agent systems characterized by uncertain states, nonlinearities, and non-strict feedback. To mitigate the nonlinearity, a fuzzy logic algorithm is applied to approximate the intrinsic dynamics of the system. Furthermore, a fuzzy logic system state observer based on leader state information is designed to address the partial unobservability of followers. Subsequently, the power integral method is incorporated into the backstepping approach to avoid singularities in the fixed-time controller. A command filter method is introduced into the standard backstepping approach to reduce the computational complexity of controller design. Then, a non-singular fixed-time adaptive control strategy with prescribed performance is proposed by constraining the tracking error within a prescribed range. Rigorous theoretical analysis ensures the convergence of consensus error in the multi-agent system to the prescribed performance region within a fixed time. Finally, the practicality of the algorithm is validated through numerical simulations.

Set-Valued State Estimation of Nonlinear Discrete-Time Systems and Its Application to Attack Detection

Hao Liu, Qing-Long Han, Yuzhe Li

, Available online

[Abstract](164) [FullText HTML] (0) [PDF 1560KB](35)

Abstract:
This paper investigates set-valued state estimation of nonlinear systems with unknown-but-bounded (UBB) noises based on constrained polynomial zonotopes which is utilized to characterize non-convex sets. First, properties of constrained polynomial zonotopes are provided and the order reduction method is given to reduce the computational complexity. Then, the corresponding improved prediction-update algorithm is proposed so that it can be adapted to non-convex sets. Based on generalized intersection, the utilization of set-based estimation for attack detection is analyzed. Finally, an example is given to show the efficiency of our results.