本 期 导 读
主题
DeepSeek、大型AI模型、强化学习、网络化控制、故障检测、特征驱动、网格去噪、多模态大型语言模型、数据驱动、非线性多智能体系统、神经网络、多目标优化、精密运动控制、鲁棒控制、遥感图像、分布式算法、博弈论...
全球科研机构
美国New Jersey Institute of Technology；英国Birmingham City University；澳大利亚Swinburne University of Technology、University of Adelaide；墨西哥Autonomous University of Nuevo Leon；日本Shibaura Institute of Technology；中国科学院自动化研究所、浙江大学、复旦大学、同济大学、哈尔滨工业大学、北京航空航天大学、西安交通大学、西安电子科技大学、中南大学、华东理工大学、北京科技大学、武汉大学、华中科技大学、中国地质大学（武汉）、深圳理工大学、西北工业大学、西南大学、广东工业大学、上海大学、深圳大学；数据堂（北京）科技股份有限公司...
F.-Y. Wang, “In Memory of Wolter J. Fabrycky: A pioneer of systems engineering and US-Sino academic exchange,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 839–840, May 2025. doi: 10.1109/JAS.2025.125468
L. Xiong, H. Wang, X. Chen, L. Sheng, Y. Xiong, J. Liu, Y. Xiao, H. Chen, Q.-L. Han, and Y. Tang, “DeepSeek: Paradigm shifts and technical evolution in large AI models,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 841–858, May 2025. doi: 10.1109/JAS.2025.125495
> Reviews paradigm shifts in large AI models with a focus on the DeepSeek approach and highlights the transition from mainstream LLMs to DeepSeek's efficient design strategies.
> Summarizes DeepSeek's core innovations like MLA, MoE, MTP, and GRPO. These novel algorithms improve model performance while reducing computational cost.
H. Li, J. Li, L. Ran, L. Zheng, and T. Huang, “A survey of distributed algorithms for aggregative games,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 859–871, May 2025. doi: 10.1109/JAS.2024.124998
> Investigates distributed Nash equilibrium seeking algorithms for aggregative games under various network architectures, with a particular focus on the design of fully distributed algorithms that eliminate the need for central coordinators and accommodate network structural constraints.
Z. Deng, W. Ma, Q.-L. Han, W. Zhou, X. Zhu, S. Wen, and Y. Xiang, “Exploring DeepSeek: A survey on advances, applications, challenges and future directions,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 872–893, May 2025. doi: 10.1109/JAS.2025.125498
> Provides a comprehensive review of the entire DeepSeek family models, summarizing the core innovations in their development processes, including data processing, training, and infrastructure, and comparing them with traditional counterparts.
S. Lou, C. Yang, Z. Liu, S. Wang, H. Zhang, and P. Wu, “Release power of mechanism and data fusion: A hierarchical strategy for enhanced MIQ-related modeling and fault detection in BFIP,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 894–912, May 2025. doi: 10.1109/JAS.2024.124821
> Develop a zone-based BFIP mechanism model and SIA for parameter refinement.
> Propose stationary feature extraction using KL-divergence-based loss in autoencoder framework.
> Solve sampling-rate mismatch by time-matching lagged samples with mechanism/data features.
J. Yang, C. Wang, H. Hou, M. Wang, and X. Li, “Feature-driven variational mesh denoising,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 913–924, May 2025. doi: 10.1109/JAS.2024.124923
> Develops a feature-based variational model for mesh denoising.
> Proposes an alternating iteration scheme, recovering mesh features and smoothing flat regions.
> Conducts comprehensive experiments in comparison with state-of-the-art approaches.
X. Jia, J. Li, S. Wang, H. Qi, F.-Y. Wang, R. Qin, M. Zhang, and X. Liang, “Federated services: A smart service ecology with federated security for aligned data supply and scenario-oriented demands,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 925–936, May 2025. doi: 10.1109/JAS.2024.124860
> Propose blockchain-based federated services for the alignment of data supply and scenario-oriented demands.
> Establish a five-layer technical framework under the decentralized intelligent architecture for federated services.
> Discuss the operational mechanism consisting of data federation and service confederation.
Q. Zhou, C. Yin, H. Ma, H. Ren, and H. Li, “Prescribed performance bipartite consensus control for MASs under data-driven strategy,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 937–946, May 2025. doi: 10.1109/JAS.2024.124956
> The controller combines PPC and DSMC, using only I/O data.
> A fully distributed relationship between bipartite tracking error and control input is established.
> Designs adaptive estimator and observer to handle parameter and nonlinear uncertainties.
K. Mao, P. Wei, Y. Wang, M. Liu, S. Wang, and N. Zheng, “CSDD: A benchmark dataset for casting surface defect detection and segmentation,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 947–960, May 2025. doi: 10.1109/JAS.2025.125228
> Constructs a CSDD as a novel benchmark for surface defect detection and segmentation, which would promote advancements in related research.
> Extensively evaluates existing methods of defect detection and segmentation on CSDD, providing comprehensive baselines for future research.
Q. Deng, Q. Kang, M. C. Zhou, X. Wang, S. Zhao, S. Wu, and M. Ghahramani, “Evolutionary algorithm based on surrogate and inverse surrogate models for expensive multiobjective optimization,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 961–973, May 2025. doi: 10.1109/JAS.2025.125111
> When dealing with expensive multiobjective optimization problems, majority of existing SAEAs generate solutions in decision space and screen candidate solutions mostly by using designed surrogate models.
S. Chen, F. Song, Y. Dong, N. Cui, Y. Liu, and X. Chen, “Precision synchronous control of multiple motion systems: A tube-based MPC approach,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 974–988, May 2025. doi: 10.1109/JAS.2025.125222
> Innovative Modeling Methods for Multiple Ultra-precision Motion Systems A high-fidelity modeling approach is proposed to precisely characterize inter-system output disturbances in ultra-precision motion systems. The synchronization mechanism among multiple systems is formalized via directed graph theory, with explicit mathematical definitions of inter-system synchronization errors.
Y. Tang, Y. Wang, C. Liu, Q. Sui, Y. Liu, K. Huang, and W. Gui, “Data-driven two-stage robust optimization allocation and loading for salt lake chemical enterprise products under demand uncertainty,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 989–1003, May 2025. doi: 10.1109/JAS.2025.125204
> An attention-based gated stacked temporal autoencoder clustering method is designed.
> A multistage hybrid heuristic algorithm is designed.
> The efficacy of the proposed method is verified on a real industrial case.
Y. Li, Y. Wu, G. Cheng, C. Tao, B. Dang, Y. Wang, J. Zhang, C. Zhang, Y. Liu, X. Tang, J. Ma, and Y. Zhang, “MEET: A million-scale dataset for fine-grained geospatial scene classification with zoom-free remote sensing imagery,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1004–1023, May 2025. doi: 10.1109/JAS.2025.125324
> Million-scale fine-grained geospatial scene classification dataset.
> Context-Aware Transformer.
> Scene-in-Scene Layout.
X. Chen, C. Tang, Z. Zhang, and G. Chen, “A game-theoretic approach to solving the Roman domination problem,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1024–1040, May 2025. doi: 10.1109/JAS.2023.123840
> Designed a Roman domination game in multi-agent systems.
> Proved that the game is an exact potential game and Nash equilibrium (NE) exists.
> Showed that every NE is a strong minimal Roman dominating function and a Pareto-optimal solution.
B.-L. Xu, C. Peng, and W.-B. Xie, “Synchronous membership function dependent event-triggered H∞ control of T-S fuzzy systems under network communications,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1041–1043, May 2025. doi: 10.1109/JAS.2023.123729
J. Cai, G. Wei, W. Li, and Y. Wang, “Robust pose graph optimization against outliers using consistency credibility factor,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1044–1046, May 2025. doi: 10.1109/JAS.2023.123897
J. Hu, J. Li, C. Jia, X. Yi, and H. Liu, “A recursive method to encryption-decryption-based distributed set-membership filtering for time-varying saturated systems over sensor networks,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1047–1049, May 2025. doi: 10.1109/JAS.2023.123915
S. Gao, J. Suo, and N. Li, “Cooperation under stochastic punishment in social dilemma situations,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1050–1052, May 2025. doi: 10.1109/JAS.2023.123912
J.-Z. Xu, Z.-W. Liu, M.-F. Ge, Y.-W. Wang, and D. He, “Distributed robust predefined-time algorithm for seeking Nash equilibrium in MASs,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1053–1055, May 2025. doi: 10.1109/JAS.2023.123879
Y. Cui, L. Cheng, M. Basin, and Z. Wu, “Distributed byzantine-resilient learning of multi-UAV systems via filter-based centerpoint aggregation rules,” IEEE/CAA J. Autom. Sinica, vol. 12, no. 5, pp. 1056–1058, May 2025. doi: 10.1109/JAS.2024.124905
转载本文请联系原作者获取授权，同时请注明本文来自Ouariel科学网博客。
链接地址：https://wap.sciencenet.cn/blog-3291369-1487801.html?mobile=1
收藏
