主题
自动驾驶、人工神经网络、最优控制、轨迹跟踪、强化学习、目标优化、Petri 网、传感器、编队控制、深度学习...
全球科研机构
美国New Jersey Institute of Technology、Indiana University-Purdue University Indianapolis;意大利Polytechnic University of Bari;瑞典Chalmers University of Technology;清华大学、中国科学院自动化研究所、中国科学院人工智能学院、复旦大学、香港中文大学、北京理工大学、北京航空航天大学、重庆大学...
H. Y. Lin, Y. Liu, S. Li, and X. B. Qu, “How generative adversarial networks promote the development of intelligent transportation systems: A survey,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1781–1796, Sept. 2023. doi: 10.1109/JAS.2023.123744
> Development of GANs and their existing applications are categorized.
> Applications of GANs in autonomous driving, traffic flow research, and traffic anomaly inspection are classified and demonstrated.
> Challenges and future research directions associated with the integration of GANs into transportation operations are identified.
D. Wang, J. Y. Wang, M. M. Zhao, P. Xin, and J. F. Qiao, “Adaptive multi-step evaluation design with stability guarantee for discrete-time optimal learning control,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1797–1809, Sept. 2023. doi: 10.1109/JAS.2023.123684 > Properties of convergence and monotonicity are investigated under MsHDP framework, in order to solve the discrete-time optimal learning control problem. > Traditional stability criterion is extended. > Develop a novel integrated MsHDP algorithm, which can accelerate the whole phase of the learning process without using an initial admissible policy. D. F. Li, Y. L. Zhang, P. Li, R. Law, Z. R. Xiang, X. Xu, L. M. Zhu, and E. Q. Wu, “Position errors and interference prediction-based trajectory tracking for snake robots,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1810–1821, Sept. 2023. doi: 10.1109/JAS.2023.123612 > Optimizes the LOS guidance law through predicted position errors and interference variables. > Uses model parameter and friction coefficient predictions of a snake robot to compensate for system input by eliminating the joint’s jitter. > Reduces the fluctuation peak and convergence time of errors and enhances the adaptability of a snake robot to environmental shifts. W. Xu, C. Zhao, J. Cheng, Y. Wang, Y. Q. Tang, T. Zhang, Z. M. Yuan, Y. S. Lv, and F.-Y. Wang, “Transformer-based macroscopic regulation for high-speed railway timetable rescheduling,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1822–1833, Sept. 2023. doi: 10.1109/JAS.2023.123501 > Analyzes the existing TTR methods of high-speed railway in complex network operating environment under emergencies. > Presents a Transformer-based macroscopic regulation approach which consists of two stages including Transformer-based modeling and policy-based decision making. > Experimental results show that the proposed approach outperforms other compared methods in terms of robustness and effectiveness in reducing train delays. Y. L. Gong, J. H. Zhou, Q. W. Wu, M. C. Zhou, and J. H. Wen, “A length-adaptive non-dominated sorting genetic algorithm for bi-objective high-dimensional feature selection,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1834–1844, Sept. 2023. doi: 10.1109/JAS.2023.123648 > A bi-objective high-dimensional feature selection method called LA-NSGA is proposed. > Length-variable individual encoding and length-adaptive evolution mechanism are used. > Experimental results based on 12 gene datasets verify the superiority of LA-NSGA. A. M. Mangini and M. Roccotelli, “Innovative services for electric mobility based on virtual sensors and Petri Nets,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1845–1859, Sept. 2023. doi: 10.1109/JAS.2023.123699 > Studies the use of VSs in the field of electromobility and proposes services, mainly related to the charge planning of an EV. > Presents VSs in the electromobility ecosystem by a sensor-cloud platform in which both physical and virtual data sources coexist. > Virtual Sensor algorithms are described by means of a UML diagram and modeled (and simulated) by different TPNs. B. Y. Zheng, C. Song, and L. Liu, “Cyclic-pursuit-based circular formation control of mobile agents with limited communication ranges and communication delays,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1860–1870, Sept. 2023. doi: 10.1109/JAS.2023.123576 > A novel cyclic-pursuit-based circular formation control scheme is proposed for MASs with heterogeneous communication ranges and time-varying communication delays. > A novel distributed controller based on a cyclic pursuit strategy is developed in which each agent needs only its leading neighbour’s information. > Proposed a set of new potential functions to deal with heterogeneous communication ranges and communication delays simultaneously. Y. Q. Qin, W. Hua, J. C. Jin, J. Ge, X. Y. Dai, L. X. Li, X. Wang, and F.-Y. Wang, “AUTOSIM: Automated urban traffic operation simulation via meta-learning,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1871–1881, Sept. 2023. doi: 10.1109/JAS.2023.123264 > AUTOSIM creates traffic simulation models considering heterogeneous layouts of urban intersections. > AUTOSIM maps traffic spatiotemporal characteristics with a wide range of simulation scenarios (modeling tasks). > AUTOSIM transfers learned knowledge from source models across different simulation scenarios to improve model estimation performance in a target simulation model with limited data samples. Y. Y. Li, C. Q. Fei, C. Q. Wang, H. M. Shan, and R. Q. Lu, “Geometry flow-based deep riemannian metric learning,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1882–1892, Sept. 2023. doi: 10.1109/JAS.2023.123399 > A new DRML is proposed via the geometry flow with adding the geometric structure as a regularization term to the hidden layer. > DRML firstly uses the curvature information of feature distributions for the regularization of the deep metric learning. > Effectiveness of DRML has been evaluated on the convergence of the embedding learning as well as the performance of the image clustering. W. C. Huang, Z. J. Pan, and Z. Z. Xu, “Underwater cable localization method based on beetle swarm optimization algorithm,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1893–1895, Sept. 2023. doi: 10.1109/JAS.2022.106073 Y. Yang and C. Peng, “MPC-based change management of supply chain under disruption risks: The case of battery industry,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1896–1898, Sept. 2023. doi: 10.1109/JAS.2023.123294 D. X. Ji, Z. B. Wei, C. Y. Tian, H. R. Cai, and J. H. Zhao, “Deep transfer ensemble learning-based diagnostic of lithium-ion battery,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1899–1901, Sept. 2023. doi: 10.1109/JAS.2022.106001 B. X. Weng, J. Sun, G. Huang, F. Deng, G. Wang, and J. Chen, “Competitive meta-learning,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 9, pp. 1902–1904, Sept. 2023. doi: 10.1109/JAS.2023.123354
转载本文请联系原作者获取授权,同时请注明本文来自欧彦科学网博客。
链接地址:https://wap.sciencenet.cn/blog-3291369-1405793.html?mobile=1
收藏