【当期目录】IEEE/CAA JAS 第8卷 第8期

本期导读>>

☑主题：

机器学习、鲁棒控制、优化、图像分割、物理信息系统、故障检测...

☑作者：

美国工程院院士Stephen Boyd教授、加拿大皇家科学院院士Witold Pedrycz教授、波兰科学院院士Jacek M. Zurada教授...

☑机构：

美国Stanford University，University of Louisville，Kent State University，Virginia Commonwealth University; 加拿大University of Alberta，University of Waterloo; 澳大利亚Queensland University of Technology; 荷兰Delft University of Technology; 浙江大学，吉林大学，华中科技大学...

Akshay Agrawal, Shane Barratt and Stephen Boyd, "Learning Convex Optimization Models," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1355-1364, Aug. 2021.

doi: 10.1109/JAS.2021.1004075

*Convex optimization models predict outputs by solving an optimization problem.

*We show how many models are in fact convex optimization models.

*We give a general technique for learning convex optimization models.

Zhe Du, Rudy R. Negenborn and Vasso Reppa, "Cooperative Multi-Agent Control for Autonomous Ship Towing Under Environmental Disturbances," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1365-1379, Aug. 2021.

doi: 10.1109/JAS.2021.1004078 

*Formulation of the towing process in a multi-agent, multi-layer control framework.

*Derivation of the kinematic model of the physically interconnected ship-towing system for coordinating multiple vessels.

*Design of adaptive weights for regulating the ship velocity to make the manipulation of the ship smooth even under harsh environmental conditions.

*Extensive simulations performed to show the robustness of the proposed method in scenarios with various environmental disturbances in a realistic framework.

Hossein Mirinejad, Tamer Inanc and Jacek M. Zurada, "Radial Basis Function Interpolation and Galerkin Projection for Direct Trajectory Optimization and Costate Estimation," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1380-1388, Aug. 2021.

doi: 10.1109/JAS.2021.1004081

*An accurate, direct method proposed for solving optimal control problems (especially nonsmooth).

*RBF-Galerkin, the proposed method, offers a highly flexible framework for direct transcription.

*Any type of global RBFs (as interpolants) and any arbitrary discretization points can be used.

*RBF-Galerkin uses global RBF interpolation and Galerkin projection for trajectory optimization.

*Costate estimation provided via RBF-Galerkin Costate Mapping Theorem.

He Zhang, Lingqiu Jin and Cang Ye, "An RGB-D Camera Based Visual Positioning System for Assistive Navigation by a Robotic Navigation Aid," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1389-1400, Aug. 2021.

doi: 10.1109/JAS.2021.1004084

*An RGB-D camera based VPS for real-time localization of a RNA for assistive navigation.

*A new depth-enhanced visual-inertial odometry method that tightly couples the visual features, geometric feature, and inertial data in a graph optimization framework to estimate the RNA’s 6-DOF pose.

*A particle filter localization method that uses the geometric information of an indoor space’s architectural CAD drawing to reduce the accumulative error of the DVIO-estimated pose.

*An RNA prototype consists of VPS and other essential software modules, including path planning, obstacle avoidance, and ART control, for assistive navigation.

S. Mohsen Azizi, "Robust Controller Synthesis and Analysis in Inverter-Dominant Droop-Controlled Islanded Microgrids," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1401-1415, Aug. 2021.

doi: 10.1109/JAS.2021.1004006

*Controller design for inverters that is robust against uncertainties and time delays.

*Linear technique for stability analysis and design criterion for droop gains.

*Robustness analysis of droop controllers against voltage amplitude and phase variations.

Dan Wang, Xiubin Zhu, Witold Pedycz, Zhenhua Yu and Zhiwu Li, "Development of Granular Fuzzy Relation Equations Based on a Subset of Data," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1416-1427, Aug. 2021.

doi: 10.1109/JAS.2021.1004054

*A novel framework of granular fuzzy relation equations based on the optimized subset of data.

*An encoding mechanism of PSO are applied for selecting a subset of data.

*Numeric fuzzy relation is transformed to granular version with a level of information granularity.

*The interpretability and accuracy are balanced by designing the granular mode.

Kunhua Liu, Zihao Ye, Hongyan Guo, Dongpu Cao, Long Chen and Fei-Yue Wang, "FISS GAN: A Generative Adversarial Network for Foggy Image Semantic Segmentation," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1428-1439, Aug. 2021.

doi: 10.1109/JAS.2021.1004057

*No method has previously been developed to directly explore the relationship between foggy images and semantic segmentation images. We investigated this relationship and propose a GAN for foggy image semantic segmentation.

*Propose a novel efficient network architecture based on a combination of concepts from U_Net, called a dilated convolution U_Net. 

*A direct FISS GAN that generates semantic segmentation images under edge information guidance is proposed. 

Yue Zhao, Ze Chen, Chunjie Zhou, Yu-Chu Tian and Yuanqing Qin, "Passivity-Based Robust Control Against Quantified False Data Injection Attacks in Cyber-Physical Systems," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1440-1450, Aug. 2021.

doi: 10.1109/JAS.2021.1004012

*It is a kind of robust control method, and its design core is to make the closed-loop system passive. Its core is to start from the perspective of energy. Its physical concept is very intuitive and easy to be accepted by engineers. It has a wide range of applications in many actual physical systems.

*Cyber-physical systems are multi-dimensional and complex systems that integrates computing, network and physical environment. Through the organic integration of technology and in-depth collaboration, it can realize real-time perception, dynamic control and information services of large-scale engineering systems. It has important and broad application prospects.

*By adding false attack signals to the control input and sensor output, the purpose of destroying the control command and sensor output command is achieved. Its implementation is simple and can destroy system performance arbitrarily.

Xiaoxing Ren, Dewei Li, Yugeng Xi and Haibin Shao, "Distributed Subgradient Algorithm for Multi-Agent Optimization With Dynamic Stepsize," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1451-1464, Aug. 2021.

doi: 10.1109/JAS.2021.1003904

*Proposes a novel dynamic stepsize selection approach for the distributed gradient algorithm and develops the associated distributed gradient algorithms for synchronous and asynchronous gossip-like communication protocol.

*Differently from the existing distributed algorithms whose diminishing or fixed stepsizes are determined before the algorithm is run, the proposed algorithms use dynamic stepsizes that rely on the time-varying estimates of the optimal function values generated at each iteration during the algorithms.

*The dynamic stepsize needs no knowledge of the global information on the network or the objective functions, which makes the proposed algorithms more applicable compared to distributed algorithms with fixed stepsizes. 

Donglei Zheng, Le Zhou and Zhihuan Song, "Kernel Generalization of Multi-Rate Probabilistic Principal Component Analysis for Fault Detection in Nonlinear Process," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1465-1476, Aug. 2021. 

doi: 10.1109/JAS.2021.1004090

*The constraint nonlinear relationships with different sampling rates are considered in the proposed model.

*A nonlinear EM algorithm is proposed for model parameter estimation.

*A fault detection scheme for a nonlinear multi-rate process is developed.