本期导读

主题

强化学习、自适应控制、数字孪生、自我优化、逆最优控制、图像增强、自我监督学习、动态事件触发机制、3D检测、无监督学习、模型预测控制、微电网、分散控制、无模型控制、神经网络...

全球科研机构

新加坡Nanyang Technological University、Singapore University of Technology and Design；日本University of Toyama、Kobe University、University of Fukui；波兰University of Social Sciences；浙江大学、东北大学、上海交通大学、香港中文大学、北京航空航天大学、中南大学、电子科技大学、华东理工大学、武汉大学、西安交通大学、北京科技大学、华南理工大学、中国矿业大学、南京航空航天大学、中国地质大学（武汉）、香港大学、华为、鹏城实验室...

Z. Shao, Y. Wang, Z. Li, and  Y. Song,  “Dynamic constraint-driven event-triggered control of strict-feedback systems without max/min values on irregular constraints,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 569–580, Mar. 2024. doi: 10.1109/JAS.2023.123804 

> Proposed constraints switching mechanism is capable of converting irregular constraints into regular constraints while essentially not imposing additional constraining effects on the system output.

> Unlike most existing works considering positive-negative alternating constraints, the maximum and minimum values of constraints are not in need.

> In contrast to the particular barrier function, a general barrier function is constructed, which allows the designed control scheme to be more complete.

Z. Jiang, C. Xu, J. Liu, W.  Luo, Z. Chen, and  W. Gui,  “A dual closed-loop digital twin construction method for optimizing the copper disc casting process,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 581–594, Mar. 2024. doi: 10.1109/JAS.2023.123777 

> A liquid copper droplet model is presented to describe the liquid copper flow pattern of the casting package during the casting process. 

> A CPMC objective function is constructed for the first time.

> A novel digital twin dual closed-loop self-optimization application framework for copper disc casting processes is proposed.

J. Zhao, C. Yang, W. Gao, L. Zhou, and  X. Liu,  “Adaptive optimal output regulation of interconnected singularly perturbed systems with application to power systems,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 595–607, Mar. 2024. doi: 10.1109/JAS.2023.123651 

> Proposes a composite control framework to solve the optimal output regulation problem of singularly perturbed systems.

> Considers the existence of interconnections between fast subsystems and gives the decentralized stabilizable condition of fast time-scale dynamics

> A novel off-policy reinforcement algorithm is exploited to learn the optimal control strategy of unknown slow time-scale dynamics.

S. Cao, Z. Luo, and  C. Quan,  “Sequential inverse optimal control of discrete-time systems,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 608–621, Mar. 2024. doi: 10.1109/JAS.2023.123762

> SIOC method proposed, capable of real-time cost function recovery.

> SIOC method is applicable even without the invertible Jacobian assumption.

> Convergence condition for each step of the SIOC is established.

H. Xu, J. Ma, Y. Yuan, H. Zhang, and X. Guo, “More than lightening: A self-supervised low-light image enhancement method capable for multiple degradations”, IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 622–637, Mar. 2024. doi: 10.1109/JAS.2024.124263 

> Addresses multiple degradations, including illumination, noise, and color shift.

> A network is designed to adjust low illumination in a self-supervised manner.

> A color correction block is designed, breaking free from reliance on white balanced images.

X. Du, L. Zou, and  M. Zhong,  “Set-membership filtering approach to dynamic event-triggered fault estimation for a class of nonlinear time-varying complex networks,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 638–648, Mar. 2024. doi: 10.1109/JAS.2023.124119

> A new fault estimation problem is investigated under the dynamic event-triggered mechanism.

> A non-fragile event-triggering condition is introduced to describe the rounding errors.

> A new UIO-based fault estimator is designed to ensure optimal performance.

M. Li, Y. Long, T. Li, H. Liang, and  C. Chen,  “Dynamic event-triggered consensus control for input constrained multi-agent systems with a designable minimum inter-event time,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 649–660, Mar. 2024. doi: 10.1109/JAS.2023.123582 

> Dynamic ETMs proposed can ensure a larger IET, which can further reduce the energy use and cost of the control protocol updating

> Bounded event-triggered control protocols based on two novel dynamic ETMs under the directed graph are proposed.

> With the designed centralized dynamic ETM and the distributed dynamic ETM, the expressions of the minimum IET are established which avoids the complex relationship with the system matrix.

D. Zhang, J. Hu, J. Cheng, Z.-G. Wu, and  H. Yan,  “A novel disturbance observer based fixed-time sliding mode control for robotic manipulators with global fast convergence,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 661–672, Mar. 2024. doi: 10.1109/JAS.2023.123948 

> A new fixed-time non-singular fast terminal sliding mode control strategy for robotic manipulators is proposed.

>A new non-singular fast terminal sliding mode surface based on the arctan function is designed to overcome the singularity problem more simply and effectively.

> A new adaptive fixed-time disturbance observer is designed to guarantee faster estimation speed and higher estimation accuracy.

C. Pan, J. Peng, and  Z. Zhang,  “Depth-guided vision transformer with normalizing flows for monocular 3D object detection,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 673–689, Mar. 2024. doi: 10.1109/JAS.2023.123660 

> Depth-guided vision transformer for monocular 3D object detection is proposed.

> Employing normalizing flows to establish priors in depth maps.

> Developing novel relative position embeddings with pixel-wise relative depth values.

Y. Zhang, L. Zhang, and  Y. Cai,  “Value iteration-based cooperative adaptive optimal control for multi-player differential games with incomplete information,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 690–697, Mar. 2024. doi: 10.1109/JAS.2023.124125 

> Presents a novel cooperative VI-based adaptive dynamic programming method for multi-player differential game models with incomplete information structure

> Different from most existing results, our algorithm enables the players to adapt their control policies with incomplete information structure, which is characterized by the limit information from neighbors.

N. Wang, X. Liang, H. Li, and X. Lu, “Decentralized optimal control and stabilization of interconnected systems with asymmetric information,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 698–707, Mar. 2024. doi: 10.1109/JAS.2023.124044 

> Employing the stochastic maximum principle, an equivalent solvability condition for the problem of optimization has been presented in terms of FBSDEs.

>Based on the equivalence, a complete solution, the necessary and sufficient conditions and an closed-loop explicit form of controllers, has been obtained for the finite-horizon case.

> Under standard assumptions, it has been shown that the system is mean-square bounded for the infinite-horizon case if and only if the algebraic Riccati equation admits a unique positive definite solution.

H. Liu, Q. Zhang, Y. Hu, H. Zeng, and  B. Fan,  “Unsupervised multi-expert learning model for underwater image enhancement,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 708–722, Mar. 2024. doi: 10.1109/JAS.2023.123771 

> An unsupervised framework is used to obviate the need for paired underwater images.

> Design a multi-expert model by considering channel differences of underwater images.

> Content perceptual loss and edge loss are introduced to preserve image details.

X. Wan, C. Zhang, F. Wei, C.-K. Zhang, and  M. Wu,  “Hybrid dynamic variables-dependent event-triggered fuzzy model predictive control,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 723–733, Mar. 2024. doi: 10.1109/JAS.2023.123957 

> A new DETM with hybrid variables is proposed.

> This DETM enables us to save more resources and gain the anticipated performance.

> A DETM-based fuzzy MPC algorithm is devised with analysis on recursive feasibility.

Y. Zheng, Y. Wang, X. Meng, S. Li, and  H. Chen,  “Distributed economic MPC for synergetic regulation of the voltage of an island DC micro-grid,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 734–745, Mar. 2024. doi: 10.1109/JAS.2023.123750 

> A stabilized Distributed Model Predictive Control for island DC micro-grids is proposed.

> Proposed DMPC takes over the secondary control layer and the primary control layer together.

> Current is directly dispatched at the low layer which simplifies the control structure.

P. Huang, G. Wang, S. Wang, and  H. Xiao,  “A mean-field game for a forward-backward stochastic system with partial observation and common noise,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 746–759, Mar. 2024. doi: 10.1109/JAS.2023.124047

> Large-population system is governed by an FBSDE with partial observation, which plays a vital role in both theoretical research and practical application.

> By virtue of optimal Filter technique, decomposition technique and dimensional-expansion technique, we get a decentralized control strategy, which is an approximate Nash equi- librium of the mean-field game.

> Significantly improves the description and resolution of mean-field game with partial observation.

D. He, H. P. Wang, Y. Tian, and  Y. Guo,  “A fractional-order ultra-local model-based adaptive neural network sliding mode control of n-DOF upper-limb exoskeleton with input deadzone,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 760–781, Mar. 2024. doi: 10.1109/JAS.2023.123882 

> A fractional-order ultra-local model is proposed to re-formulate the complex exoskeleton system.

> Time-delay estimation is combined with neural network to eliminate the lumped disturbance.

> Nussbaum technique is introduced into model-free controller to make control gain adaptive.

W. Zhang, W. Zheng, Q. Li, and F.-Y. Wang, “Parallel vision ⊇ image synthesis/augmentation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 782–784, Mar. 2024. doi: 10.1109/JAS.2023.124038 

Y. Cui, P. Cheng, and X. Ge, “Exponential synchronization of delayed stochastic complex dynamical networks via hybrid impulsive control,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 785–787, Mar. 2024. doi: 10.1109/JAS.2023.123867 

X. Chen, X. Li, S. Yu, Y. Lei, N. Li, and B. Yang, “Dynamic vision enabled contactless cross-domain machine fault diagnosis with neuromorphic computing,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 788–790, Mar. 2024. doi: 10.1109/JAS.2023.124107 

B. Huang, Y. Liu, K. Kou, and W. Gui, “Multi-timescale distributed approach to generalized-Nash-equilibrium seeking in noncooperative nonconvex games,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 791–793, Mar. 2024. doi: 10.1109/JAS.2023.123909 

J. Wang, B. Liu, E. Wu, J. Ma, and P. Li, “Simulation analysis of deformation control for magnetic soft medical robots,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 794–796, Mar. 2024. doi: 10.1109/JAS.2023.124143 

W. Cao, J. Yan, X. Yang, C. Chen, and X. Guan, “Communication-aware mobile relaying via an AUV for minimal wait time: A broad learning-based solution,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 797–799, Mar. 2024. doi: 10.1109/JAS.2023.124095 

C. Ren, C. Zou, Z. Xiong, H. Yu, Z.-Y. Dong, and N. Dusit, “Achieving 500X acceleration for adversarial robustness verification of tree-based smart grid dynamic security assessment,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 800–802, Mar. 2024. doi: 10.1109/JAS.2023.124053 

Z. Liu, Z. Zhang, Z. Lei, M. Omura, R.-L. Wang, and S. Gao, “Dendritic deep learning for medical segmentation,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 803–805, Mar. 2024. doi: 10.1109/JAS.2023.123813 

L. Lin, J. Cao, J. Lu, and L. Rutkowski, “Set stabilization of large-scale stochastic Boolean networks: A distributed control strategy,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 806–808, Mar. 2024. doi: 10.1109/JAS.2023.123903