主题

分布式机器学习、卡尔曼滤波、传感成像、容错控制、多目标优化、深度 Q 学习、进化算法、智能故障诊断、事件触发控制、自主水面飞行器、弱监督学习、卷积神经网络、图像处理、移动机器人、多智能体系统、神经网络...

全球科研机构

美国Indiana University-Purdue University Indianapolis；英国Loughborough University、Brunel University London；德国Bielefeld University；加拿大University of Alberta；澳大利亚Murdoch University、Central Queensland University、Swinburne University of Technology；西班牙University of Granada、University of the Basque Country、TECNALIA；清华大学、浙江大学、同济大学、北京航空航天大学、东北大学、华东理工大学、西安交通大学、北京理工大学、电子科技大学、中南大学、西北工业大学、山东大学、长春工业大学、海南大学、合肥工业大学；阿里巴巴、上海航空测控技术研究所...

F.-Y. Wang, Q. Miao, L. Li, Q. Ni, X. Li, J. Li, L. Fan, Y. Tian, and Q.-L. Han, “When Does Sora Show: The Beginning of TAO to Imaginative Intelligence and Scenarios Engineering,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 809-815, Apr. 2024. 

W.-H. Chen, “Goal-oriented control systems (GOCS): From HOW to WHAT,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 816–819, Apr. 2024.

J. Li, R. Qin, S. Guan, X. Xue, P. Zhu, and F.-Y. Wang, “Digital CEOs in digital enterprises: Automating, augmenting, and parallel in metaverse/CPSS/TAOs”, IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 820–823, Apr. 2024.

M. V. Luzón, N. Rodríguez-Barroso, A. Argente-Garrido, D. Jiménez-López, J. M. Moyano, J. Del Ser, W. Ding, and  F. Herrera,  “A tutorial on federated learning from theory to practice: Foundations, software frameworks, exemplary use cases, and selected trends,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 824–850, Apr. 2024.

> The aim is to provide a practical tutorial on FL for practitioners and researchers.

> Includes a short methodology and a systematic analysis of software frameworks.

> Provides cases of study including foundations of FL and implementation guidelines.

J. Zhou, J. Shang, and  T. Chen,  “Cybersecurity landscape on remote state estimation: A comprehensive review,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 851–865, Apr. 2024.

> An overview of recent advances in cyber-attacks and defensive countermeasures is presented, with a specific focus on integrity attacks against RSE.

> A detailed review of typical attack detection and resilient estimation algorithms is included, illustrating the latest defensive measures safeguarding RSE from adversaries.

> Some prevalent attacks impairing the confidentiality and data availability of RSE are examined from both attackers’ and defenders’ perspectives.

E. Javanfar and  M. Rahmani,  “Data-based filters for non-Gaussian dynamic systems with unknown output noise covariance,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 866–877, Apr. 2024. 

> Novel data-based linear and non-linear filters are proposed for linear dynamic systems subjected to non-Gaussian noise.

> These filters address the particular challenges posed by unknown output noise covariance and inaccurate process noise covariance.

> A weighted SON clustering approach is presented to enhance the regularization and improve the performance of the conventional SON clustering.

H. Wang and  Q.-L. Han,  “Designing proportional-integral consensus protocols for second-order multi-agent systems using delayed and memorized state information,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 878–892, Apr. 2024. 

> New results on Hurwitz stability for a class of quasi-polynomials.

> Consensus design for LTI multi-agent systems via eigenvalue assignment.

> Improving the dynamic performance in addition to achieving the consensus.

Z. Chen, X. Wang, W. Gui, J. Zhu, C. Yang, and  Z. Jiang,  “A novel sensing imaging equipment under extremely dim light for blast furnace burden surface: Starlight high-temperature industrial endoscope,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 893–906, Apr. 2024. 

> A starlight optical imaging system with large depth of field and wide field of view is designed.

> Intelligent self-maintenance protection device with water-air dual cooling system is developed.

> Optimum configuration of the installation position of the system is found.

X. Wang, Q. Wang, Y. Su, Y.  Ouyang, and  C. Sun,  “Adaptive sensor-fault tolerant control of unmanned underwater vehicles with input saturation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 907–918, Apr. 2024. 

> Proposed FTC can deal with both additive and multiplicative types of sensor faults, which is different from existing results that only consider one or two types of sensor faults. Then, an online estimator is given to estimate the sensor faults without traditional fault detection and isolation module.

> Nonlinear dynamic knowledge of the UUV or the sensor fault information is not required. The increased uncertainty makes it more challenging to deal with sensor faults, but enhances the availability of the developed FTC scheme in practical implementation.

> Asymptotic tracking performance is guaranteed with the proposed RISE-based active FTC scheme, which is different from the existing UUV control method。To the best of our knowledge, this is the first asymptotic tracking result for UUVs that are capable of tolerating various sensor faults.

F. Ming, W. Gong, L. Wang, and  Y. Jin,  “Constrained multi-objective optimization with deep reinforcement learning assisted operator selection,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 919–931, Apr. 2024. 

> A generic deep reinforcement learning-assisted multi-objective optimization operator selection model.

> The model can contain an arbitrary number of operators.

> An adaptive operator-assisted constrained multi-objective optimization framework.

B. Yang, Y. Lei, X. Li, N. Li, and  A. Nandi,  “Label recovery and trajectory designable network for transfer fault diagnosis of machines with incorrect annotation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 932–945, Apr. 2024. 

> A semi-supervised transfer learning framework is presented for intelligent diagnosis.

> Domain adaptation is achieved in the presence of a false-labeled source domain.

> A new indicator is proposed to evaluate and further modify label anomaly.

Y. Shi and  E. Nekouei,  “Quantization and event-triggered policy design for encrypted networked control,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 946–955, Apr. 2024. 

> An event-driven encrypted control framework is proposed using the Paillier cryptosystem, modified static and dynamic quantization policies, and the quantization-related event-triggered strategy.

> A novel dynamic quantization policy with a state-dependent sensitivity is presented, which ensures the asymptotic convergence of the system state.

> By defining a quantization-related measurement error, the adverse effect of quantization errors is implicitly considered in the event-triggered strategy, which contributes to a rigorous analysis of the inter-event time interval.

L.-Y. Hao, G. Dong, T. Li, and  Z. Peng,  “Path-following control with obstacle avoidance of autonomous surface vehicles subject to actuator faults,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 956–964, Apr. 2024. 

> Considering actuator faults and obstacle avoidance simultaneously, the path-following control scheme with obstacle avoidance and fault tolerance is developed which can ensure the uniform ultimate boundedness of tracking errors.

> Actuator fault effect on existing obstacle avoidance strategy is revealed. As the lower bound of actuator efficiency factors decreases, the safe distance becomes smaller.

> To compensate for actuator faults, an improved artificial potential function is constructed by introducing the lower bound of actuator efficiency factors. The proposed obstacle avoidance strategy can be reduced to an existing one in the absence of actuator faults.

Y.-C. Li, R.-S. Jia, Y.-X. Hu, and  H.-M. Sun,  “A weakly-supervised crowd density estimation method based on two-stage linear feature calibration,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 965–981, Apr. 2024. 

> A weakly-supervised crowd density estimation method is proposed.

> A novel and effective training approach for incremental learning is used.

> A characteristic linear calibration is designed to improve the weakly-supervised.

T. Wang, Q. Chen, X. Lang, L. Xie, P. Li, and  H. Su,  “Detection of oscillations in process control loops from visual image space using deep convolutional networks,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 982–995, Apr. 2024. 

> A visual framework for oscillation detection in control loops using typical CNNs is explored.

> The framework demonstrates strong robustness to noise and mean non-stationarity.

> The detection speed of the framework is not limited by the length of the oscillation data.

S. Wang, W. Ji, Y. Jiang, Y. Zhu, and  J. Sun,  “Relaxed stability criteria for time-delay systems: A novel quadratic function convex approximation approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 996–1006, Apr. 2024. 

> A novel quadratic convex function is constructed to approximate the quadratic function induced by LKF derivative, regardless of the sign of the coefficient in the quadratic term. 

> To estimate the derivative of the constructed LKF, ERCC technique in our previous work combining the B-L inequality is utilized to obtain the tighter lower bound. 

> The relaxed stability conditions for linear systems with time-varying delays can be obtained by combining our developed quadratic function convex approximation lemma, ERCC technique and the B-L inequality. 

Y. Zheng, J. Zheng, K. Shao, H. Zhao, H. Xie, and  H. Wang,  “Adaptive trajectory tracking control for nonholonomic wheeled mobile robots: A barrier function sliding mode approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1007–1021, Apr. 2024. 

> The finite-time control with predefined precision for nonholonomic wheeled mobile robot with uncertainties is achieved.

> Proposed method eliminates the requirements for uncertainty bounds and guarantees the non-overestimation for control gain.

> Actuator saturation issue is prevented by introducing a modified barrier function-like control gain with specified performance.

X. Xue, D. Zhou, X. Yu, G. Wang, J. Li, X. Xie, L. Cui, and  F.-Y. Wang,  “Computational experiments for complex social systems: Experiment design and generative explanation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1022–1038, Apr. 2024. 

> It is difficult for traditional design of experiment methods to achieve the generative explanation of system emergence.

> Propose an integrated approach to the design of computational experiments, incorporating three key modules: descriptive module, interpretative module, and predictive module.

C. Ma and D. Dong, “Finite-time prescribed performance time-varying formation control for second-order multi-agent systems with non-strict feedback based on a neural network observer,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1039–1050, Apr. 2024. 

> A finite-time prescribed performance time-varying formation control algorithm is proposed for the time-varying formation control of non-strict feedback MASs.

> Considering the information-unmeasured state and partial feedback of the system, the NN state observer of MASs is designed, which not only ensures the transient and steady-state characteristics of the time-varying formation control of MASs but also solves the unknowability and unmeasurability of the system.

> Although finite-time prescribed performance control with output feedback has been studied in the literature, these studies have been focused on the single nonlinear system. In contrast, this paper extends the study from the single nonlinear system to MASs by establishing communication topologies.

Y. Li, W. Yu, and X. Guan, “3D localization for multiple AUVs in anchor-free environments by exploring the use of depth information,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1051–1053, Apr. 2024. 

H. Guo, Z.-H. Pang, and C. Li, “Side information-based stealthy false data injection attacks against multi-sensor remote estimation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1054–1056, Apr. 2024. 

T. Zhang, J. Cao, and X. Li, “Lyapunov conditions for finite-time input-to-state stability of impulsive switched systems,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1057–1059, Apr. 2024.

H. Zhang, Y. Li, Z. Wang, Y. Ding, and H. Yan, “Policy gradient adaptive dynamic programming for model-free multi-objective optimal control,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1060–1062, Apr. 2024. 

Y. Tan and  Z. Huang,  “Synchronization of drive-response networks with delays on time scales,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1063–1065, Apr. 2024. 

S. Xiao, X. Ge, and Q. Wu, “Attack-resilient distributed cooperative control of virtually coupled high-speed trains via topology reconfiguration,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1066–1068, Apr. 2024. 

R. Yu, H. Zhao, S. Zhen, K. Huang, X. Chen, H. Sun, and K. Shao, “A novel trajectory tracking control of AGV based on Udwadia-Kalaba approach,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1069–1071, Apr. 2024. 

X. Wu, Z. Ren, and F. Yu, “Parameter-free shifted Laplacian reconstruction for multiple kernel clustering,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 4, pp. 1072–1074, Apr. 2024.