IEEEJAS的个人博客分享 http://blog.sciencenet.cn/u/IEEEJAS

博文

【当期目录】IEEE/CAA JAS第9卷第1期

已有 231 次阅读 2022-1-14 14:19 |系统分类:博客资讯

导读

※ 热点主题

水下机器人、强化学习、生成对抗网络、非线性系统、PID控制、多智能体系统、智能电网、卷积神经网络、分布式计算、机器学习、自动驾驶...


※ 全球科研机构

美国North Carolina State University、Missouri University of Science and Technology、University of Virginia、Michigan Technological University;澳大利亚Swinburne University of Technology、RMIT University、University of Sydney;加拿大University of Alberta;瑞典ABB研究部;日本University of Toyama;韩国Yonsei University;中国科学院自动化研究所、清华大学、北京大学、中国科学技术大学...


Ziye Zhou, Jincun Liu and Junzhi Yu, "A Survey of Underwater Multi-Robot Systems," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 1-18, Jan. 2022. 

doi: 10.1109/JAS.2021.1004269


 Present a novel taxonomy and comprehensive survey to Underwater Multi-Robot Systems (UMRS) from the perspective of the emergence of new functions.

 Categorize the cooperation of UMRS in terms of task-space, motion-space, measurement-space, as well as their combination.

 Provide valuable insights into the reasonable utilization of UMRS to attain diverse underwater tasks in complex ocean application scenarios.


Ruofan Wu, Zhikai Yao, Jennie Si and He (Helen) Huang, "Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 19-30, Jan. 2022. 

doi: 10.1109/JAS.2021.1004272


 The first real-time tracking control of a wearable robotic prosthesis with human in the loop.

 Performance guarantees on learning convergence, solution optimality, practical stability.

 Systematic performance evaluation of human-robot system during different walking tasks.



Xiaohua Ge, Shunyuan Xiao, Qing-Long Han, Xian-Ming Zhang and Derui Ding, "Dynamic Event-Triggered Scheduling and Platooning Control Co-Design for Automated Vehicles Over Vehicular Ad-Hoc Networks," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 31-46, Jan. 2022. 

doi: 10.1109/JAS.2021.1004060


 A new bandwidth-aware dynamic event-triggered scheduling mechanism (DESM) is developed to efficiently alleviate communication resource expenditure.

 The theoretical relationship between the proposed DESMs and some existing ESMs is explicitly disclosed. It is demonstrated that the proposed DESMs are more flexible for achieving a trade-off between communication efficiency and platoon control performance.

 A scalable co-design criterion on the existence of desired event-triggered platoon control law and DESMs is presented. Both controller gain matrix and trigger weighting matrix can be obtained from the derived criterion that is independent of platoon scale.



Yongliang Yang, Zihao Ding, Rui Wang, Hamidreza Modares and Donald C. Wunsch, "Data-Driven Human-Robot Interaction Without Velocity Measurement Using Off-Policy Reinforcement Learning," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 47-63, Jan. 2022. 

doi: 10.1109/JAS.2021.1004258


 Presented a novel two-level HRI controller design framework consisting of a task-oriented performance optimization design and a plant-oriented impedance controller design.

 In the outer-loop, the data-driven reinforcement learning technique is used for performance optimization to assign the optimal impedance parameters.

 In the inner-loop, a velocity-free filter is designed to avoid the requirement of end-effector velocity measurement.



Tianyi Zhang, Jiankun Wang and Max Q.-H. Meng, "Generative Adversarial Network Based Heuristics for Sampling-Based Path Planning," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 64-74, Jan. 2022. 

doi: 10.1109/JAS.2021.1004275


 Propose a heuristic method for sampling-based path planning algorithm using GAN.

 Design a GAN model to predict the promising region for non-uniform sampling.

 Apply the GAN-based heuristic method to case studies to demonstrate the effectiveness of the proposed method.



Aijuan Song, Guohua Wu, Witold Pedrycz and Ling Wang, "Integrating Variable Reduction Strategy With Evolutionary Algorithms for Solving Nonlinear Equations Systems," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 75-89, Jan. 2022. 

doi: 10.1109/JAS.2021.1004278


 Variable reduction strategy was proposed to reduce nonlinear equations systems.

 A framework of variable reduction strategy and evolutionary algorithms was presented.

 Variable reduction strategy enables a better performance of an original algorithm.

 A better algorithm and a reduction scheme with more reduced variables perform better.



Xujun Lyu and Zongli Lin, "PID Control of Planar Nonlinear Uncertain Systems in the Presence of Actuator Saturation," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 90-98, Jan. 2022. 

doi: 10.1109/JAS.2021.1004281


 PID control design for planar nonlinear uncertain systems with input saturation.

 Robustness with respect to uncertain nonlinearities.

 Maximization of the domain of attraction and output tracking capacity.

 LMI based design algorithm.

 Application to a test rig for magnetic suspension systems.



Yang Yu, Zhenyu Lei, Yirui Wang, Tengfei Zhang, Chen Peng and Shangce Gao, "Improving Dendritic Neuron Model With Dynamic Scale-Free Network-Based Differential Evolution," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 99-110, Jan. 2022. 

doi: 10.1109/JAS.2021.1004284


 The optimization performance of DE is enhanced by a dynamic scale-free network.

 DSNDE is developing as a learning algorithm to improve the performance of DNM.

 The DSNDE-trained DNM has high accuracy in prediction, classification and other issues.



Guohuai Lin, Hongyi Li, Hui Ma, Deyin Yao and Renquan Lu, "Human-in-the-Loop Consensus Control for Nonlinear Multi-Agent Systems With Actuator Faults," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 111-122, Jan. 2022. 

doi: 10.1109/JAS.2020.1003596


 The leader of the nonlinear MASs is considered as non-autonomous and the leader's control input is time-varying, which is provided by the human operator. In addition, we remove the restriction assumption that a subset of followers can access the leader's control input.

 Different from most existing results, the controller designed in this paper achieves the leader-following consensus via adaptive coupling strengths for online adjustment. Furthermore, the considered nonlinear MASs are more general than the high-order Brunovsky form nonlinear systems.

 By using the relative information of neighboring nodes, the neighborhood observer is designed to estimate the unmeasurable states of nonlinear MASs, and the neighborhood observer-based neural fault-tolerant controller with dynamic coupling gains is constructed to achieve the leader-following consensus of MASs.



Yanni Wan, Jiahu Qin, Xinghuo Yu, Tao Yang and Yu Kang, "Price-Based Residential Demand Response Management in Smart Grids: A Reinforcement Learning-Based Approach," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 123-134, Jan. 2022. 

doi: 10.1109/JAS.2021.1004287 


 Study the price-based residential demand response management in smart grid considering PEV loads.

 Model the PB-RDRM from a social perspective, i.e., maximize the weighted sum of UC's profit and loads' cost.

 Propose a model-free reinforcement learning-based DR algorithm to address the uncertainties.



Yuxiang Yang, Zhihao Ni, Mingyu Gao, Jing Zhang and Dacheng Tao, "Collaborative Pushing and Grasping of Tightly Stacked Objects via Deep Reinforcement Learning," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 135-145, Jan. 2022. 

doi: 10.1109/JAS.2021.1004255


 A novel collaborative pushing and grasping method is proposed for handling tightly stacked objects.

 An efficient non-maximum suppression policy is devised to suppress unreasonable actions.

 A novel PR-Net is devised to assess the degree of aggregation or separation between objects.

 A common household item dataset is established to train and evaluate the model.



Yinlong Zhang, Wei Liang, Mingze Yuan, Hongsheng He, Jindong Tan and Zhibo Pang, "Monocular Visual-Inertial and Robotic-Arm Calibration in a Unifying Framework," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 146-159, Jan. 2022. 

doi: 10.1109/JAS.2021.1004290


 Visual-inertial and robotic-arm calibration in a unifying framework.

 Spiral moving trajectory for consistent and repeatable calibration.

 The spatial relationship is geometrically correlated between the sensing units and robotic arm.



Lun Hu, Shicheng Yang, Xin Luo, Huaqiang Yuan, Khaled Sedraoui and MengChu Zhou, "A Distributed Framework for Large-scale Protein-protein Interaction Data Analysis and Prediction Using MapReduce," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 160-172, Jan. 2022. 

doi: 10.1109/JAS.2021.1004198


 A distributed framework is presented to reimplement one of state-of-the-art algorithms with MapReuce such that it can be applied for large-scale protein-protein interaction prediction.

 Experimental results well demonstrate that the proposed framework can considerably improve its computational efficiency by more than two orders of magnitude while retaining the same high accuracy.

 The upper limit of the proposed framework efficiency exists, as it is impossible to reduce its running time by simply increasing the number of computing nodes. We note that when the number of computing nodes exceeds some threshold, the process of data transfer takes more time than the computation, and thus constrains the further improvement of efficiency.



Ben Niu, Jidong Liu, Ding Wang, Xudong Zhao and Huanqing Wang, "Adaptive Decentralized Asymptotic Tracking Control for Large-Scale Nonlinear Systems With Unknown Strong Interconnections," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 173-186, Jan. 2022. 

doi: 10.1109/JAS.2021.1004246


 The decentralized control scheme proposed in this paper removes all the two widely adopted traditional conditions of the interconnected terms by using the inherent properties of Gaussian function and thereby deals with completely unknown strong interconnections successfully.

 The asymptotic tracking control is realized in this paper even though the uncertain parameters, large-scale system structure and unknown strong interconnections are considered.

 By applying the DSC technology, the inherent “explosion of complexity” problem in backstepping is eliminated.



Wonje Jang, Junhyuk Hyun, Jhonghyun An, Minho Cho and Euntai Kim, "A Lane-Level Road Marking Map Using a Monocular Camera," IEEE/CAA J. Autom. Sinica, vol. 9, no. 1, pp. 187-204, Jan. 2022. 

doi: 10.1109/JAS.2021.1004293


 A lane-level RM map is built using only a monocular camera and wheel encoder.

 RMNet was developed to train on SeRM dataset for road marking segmentation.

 Class-weighted loss and class-weighted focal loss are proposed to handle class imbalance problem.

 The semantic road mark mapping (SeRM) dataset is developed for effective RM segmentation and mapping.




https://blog.sciencenet.cn/blog-3291369-1321048.html

上一篇:自动化学报多篇论文入选中国百篇最具影响国内论文和中国精品期刊顶尖论文
下一篇:《自动化学报》致谢审稿人

0

该博文允许注册用户评论 请点击登录 评论 (0 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2022-5-20 16:32

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部