博文
【当期目录】IEEE/CAA JAS 第8卷 第7期
|
本期导读
☑主题：
本期含<协作机器人认知计算专题>，以及神经网络、模型预测控制等论文
☑作者：
IEEE Transactions on Artifical Intelligence主编Hussein A. Abbass教授、IEEE Transactions on Intelligent Transportation Systems主编Azim Eskandarian教授、IEEE SMCS意大利分会主席Giancarlo Fortino教授...
☑机构：
美国University of Florida、Virginia Tech Autonomous System and Intelligent Machine Lab、意大利University of Naples Federico II、University of Calabria、澳大利亚University of New South Wales、北京科技大学、上海交通大学等
Special Issue on Cognitive Computing for Collaborative Robotics
Huimin Lu, Dongpu Cao, Dacheng Tao, Schahram Dustdar and Pinhan Ho, "Guest Editorial for Special Issue on Cognitive Computing for Collaborative Robotics," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1221-1221, July 2021.
Ce Zhang and Azim Eskandarian, "A Survey and Tutorial of EEG-Based Brain Monitoring for Driver State Analysis," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1222-1242, July 2021.
■Over 100 driver state estimation papers, mostly focused on Brain EEG waves, have been reviewed critically.
■A comprehensive survey and short tutorial of the most popular signal processing, conventional machine learning classification, and deep learning algorithms for driver state estimation are presented.
■The future algorithmic requirements of EEG artifact reduction, real-time processing, and between-subject classification accuracy of driver state estimation are discussed.
Pei Liu, Yingjie Zhou, Dezhong Peng and Dapeng Wu, "Global-Attention-Based Neural Networks for Vision Language Intelligence," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1243-1252, July 2021.
■Proposed a model in which the global information is incorporated into the attention weight calculation process. The number of local regions is larger than the actual object appeared in a sentence; the we want to activate local regions as less as possible to avoid noises.
■Experiment analysis;
■A multi-task learning approach, in which the global information extraction and training strategy.
Imran Ahmed, Sadia Din, Gwanggil Jeon, Francesco Piccialli and Giancarlo Fortino, "Towards Collaborative Robotics in Top View Surveillance: A Framework for Multiple Object Tracking by Detection Using Deep Learning," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1253-1270, July 2021.
■Collaborative surveillance framework is presented for multiple object tracking and detection.
■Framework consists of a smart camera, visual processing unit, & deep learning models.
■Generalization performance of detection models has been investigated for top view.
Long Sun, Zhenbing Liu, Xiyan Sun, Licheng Liu, Rushi Lan and Xiaonan Luo, "Lightweight Image Super-Resolution via Weighted Multi-Scale Residual Network," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1271-1280, July 2021.
■A novel weighted multi-scale residual block (WMRB) is proposed, which can not only effectively exploit multi-scale features but also dramatically reduce the computational burden.
■A global residual shortcut is deployed, which adds high frequency features to generate more clear details and promote gradient information propagation.
■Extensive experiments show that the WMRN model utilizes only a modest number of parameters and operations to achieve competitive SR performance on different benchmarks with different upscaling factors.
Adam J. Hepworth, Daniel P. Baxter, Aya Hussein, Kate J. Yaxley, Essam Debie and Hussein A. Abbass, "Human-Swarm-Teaming Transparency and Trust Architecture," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1281-1295, July 2021.
■Propose a Human-Swarm-Teaming Transparency and Trust Architecture, HST3.
■HST3-Architecture reinforces transparency as a key contributor towards situation awareness.
■Assert that transparency is the overarching concept, comprising of three subordinate tenants.
■Define the key sub-tenants of interpretability, explainability, and predictability.
Tian Wang, Xing Xu, Fumin Shen and Yang Yang, "A Cognitive Memory-Augmented Network for Visual Anomaly Detection," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1296-1307, July 2021.
■A Cognitive Memory-Augmented Network is proposed for visual anomaly detection.
■A memory module is designed to simulate the memory capacity of humans.
■A density estimation module is developed to learn the data distribution.
■A two-step scheme is proposed to enable the cooperation of the two modules.
Review
Xiwang Guo, MengChu Zhou, Abdullah Abusorrah, Fahad Alsokhiry and Khaled Sedraoui, "Disassembly Sequence Planning: A Survey," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1308-1324, July 2021.
■Presents an analysis of disassembly sequences to help decision makers engage in product recovery and reuse activities. Over 100 scientific papers published between 2007 and 2020 are reviewed in this work.
■Modeling methods include graphical ones such as graph-based modeling, AND/OR graph, Petri nets and matrix-based models. All the possible disassembly sequences can be generated by using these modeling methods.
■AI methods are also discussed to solve a DSP problem, for example, genetic algorithm (GA), ant colony optimizer, scatter search (SS) and particle swarm optimizer. Their advantages and disadvantages are summarized in this work.
Papers
Chentao Xu and Xing He, "A Fully Distributed Approach to Optimal Energy Scheduling of Users and Generators Considering a Novel Combined Neurodynamic Algorithm in Smart Grid," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1325-1335, July 2021.
■Presents a fully distributed scheme in smart grid for optimal energy scheduling considering both user side and generator side.
■Uses a zero-one variable to distinguish the charging and discharging states of electric vehicles.
■Designs a novel neurodynamic algorithm which combines the neural network algorithm with the differential evolution algorithm to deal with the nonconvex optimization problem of the user side.
Ting Bai, Shaoyuan Li and Yuanyuan Zou, "Distributed MPC for Reconfigurable Architecture Systems via Alternating Direction Method of Multipliers," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1336-1344, July 2021.
■A reconfiguration control strategy is presented in presence of three typical modes;
■A non-cooperative distributed MPC scheme combined with ADMM algorithm is proposed;
■A benchmark four-tank plant with reconfigurable architecture is employed.
Ruihua Jiao, Kaixiang Peng and Jie Dong, "Remaining Useful Life Prediction for a Roller in a Hot Strip Mill Based on Deep Recurrent Neural Networks," IEEE/CAA J. Autom. Sinica, vol. 8, no. 7, pp. 1345-1354, July 2021.
■A novel framework based on deep RNN is developed to estimate the RUL of rollers.
■The proposed deep RNN extracts coarse-grained and fine-grained features to develop a HI.
■The HI can automatically obtain the FT in the fault state without manual specification.
■The RUL of the roller is determined by a comprehensive HI.
https://blog.sciencenet.cn/blog-3291369-1301667.html
上一篇：精选 ‖ 国家自然科学基金资助论文
下一篇：《自动化学报》2021年47卷8期目录分享
