【当期目录】IEEE/CAA JAS 第9卷 第2期

导读

☀热点主题

自适应控制、神经网络、非线性系统、计算机视觉、机器学习、多智能体系统、无人机...

☀全球科研机构

英国University of Cambridge、Loughborough University；意大利Polytechnic University of Bari；瑞士Università della Svizzera italiana；瑞典Lund University；荷兰Eindhoven University of Technology；塞浦路斯University of Cyprus; 中国科学院计算技术研究所、清华大学、北京大学、同济大学、上海交通大学、西安交通大学...

敬请阅览！

Xin Liu, Mingyu Yan, Lei Deng, Guoqi Li, Xiaochun Ye and Dongrui Fan, "Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 205-234, Feb. 2022. 

doi: 10.1109/JAS.2021.1004311

*Provide the first comprehensive taxonomy of sampling methods for efficient GCN training.

*Compare sampling methods from multiple aspects and highlight their characteristics.

*Analyze multiple categories of sampling methods in theoretical and experimental manner.

Dong Zhao and Marios M. Polycarpou, "Fault Accommodation for a Class of Nonlinear Uncertain Systems With Event-Triggered Input," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 235-245, Feb. 2022. 

doi: 10.1109/JAS.2021.1004314

*Event-induced signal discrepancy for fault accommodation design is explicitly quantified.

*Adaptive approximation based fault accommodation design under event-triggered control effort implementation is proposed.

*Explicit upper bounds on the tracking error are derived for the event-triggered fault accommodation system before and after the detection of system fault.

Luca Butera, Alberto Ferrante, Mauro Jermini, Mauro Prevostini and Cesare Alippi, "Precise Agriculture: Effective Deep Learning Strategies to Detect Pest Insects," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 246-258, Feb. 2022. 

doi: 10.1109/JAS.2021.1004317 

*Comparing State-of-the-art Neural Network Object Detectors in outdoors pest insects monitoring.

*FasterRCNN with a MobileNetV3 backbone is the best tradeoff between precision and latency on GPU.

*Proving known models are well suited for insect detection, reducing the need of ad-hoc ones.

Gianvito Difilippo, Maria Pia Fanti and Agostino Marcello Mangini, "Maximizing Convergence Speed for Second Order Consensus in Leaderless Multi-Agent Systems," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 259-269, Feb. 2022. 

doi: 10.1109/JAS.2021.1004320

*The presented consensus protocol allows to the agents to form a uniformly spaced string.

*The agents decide a non-predetermined common reference velocity and reach the common velocity.

*The conditions ensuring that the proposed second order consensus is achieved are proved.

Xiaodong He, Zhiyong Sun, Zhiyong Geng and Anders Robertsson, "Exponential Set-Point Stabilization of Underactuated Vehicles Moving in Three-Dimensional Space," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 270-282, Feb. 2022. 

doi: 10.1109/JAS.2021.1004323

*The vehicle investigated is an underactuated system, which has six degrees of freedom but only four independent control inputs.

*The model of the underactuated vehicle is established on the matrix Lie group SE(3), which describes the rigid body’s configuration globally and uniquely.

*Two additional rotation matrices are constructed to generate a motion of rotation coupled with translation, so that the underactuated states can be driven by the control inputs.

Binghui Li and Badong Chen, "An Adaptive Rapidly-Exploring Random Tree," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 283-294, Feb. 2022. 

doi: 10.1109/JAS.2021.1004252

*Fast RRT algorithm for narrow passage:

Proposes an improved RRT algorithm which can better deal with the planning task with narrow passage environment. The algorithm improves the planning speed and success rate of RRT algorithm for narrow passage task.

*Rapid planning of common environment:

Although the new algorithm increases the amount of computation because of dealing with narrow channel environment, it can still deal with common planning tasks quickly without great performance loss.

*Simple algorithm flow:

The new algorithm improves the sampling process of the original RRT algorithm, simplifies the local environment judgment process of RRV algorithm, and uses dual tree search to enhance the stability of the algorithm. The whole process of the algorithm is simple and unified, easy to understand and implement.

Sarah P. Madruga, Augusto H. B. M. Tavares, Saulo O. D. Luiz, Tiago P. do Nascimento and Antonio Marcus N. Lima, "Aerodynamic Effects Compensation on Multi-Rotor UAVs Based on a Neural Network Control Allocation Approach," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 295-312, Feb. 2022. 

doi: 10.1109/JAS.2021.1004266

*Novel control allocation approach to take into account aerodynamic effects.

*Compensation of the allocation error caused by the classic matrix.

*Improved performance of the quadrotor controller and flight pergormance.

*Better overall signal quality.

Hanjiang Hu, Hesheng Wang, Zhe Liu and Weidong Chen, "Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 313-328, Feb. 2022. 

doi: 10.1109/JAS.2021.1003907

*A domain-invariant feature learning framework is proposed based with feature consistency loss.

*A new gradient-weighted similarity activation map is proposed for high-accuracy retrieval.

*A novel self--supervised contrastive learning is proposed with adaptive triplet.

*Our results keep on par with state-of-the-art baselines with efficient two-stage pipeline.

Dan You, Oussama Karoui and Shouguang Wang, "Computation of Minimal Siphons in Petri Nets Using Problem Partitioning Approaches," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 329-338, Feb. 2022. 

doi: 10.1109/JAS.2021.1004326

*An algorithm based on problem partitioning is proposed for the enumeration of minimal siphons in a Petri net.

*The proposed algorithm behaves better than GPMSE in both computational time and memory consumption.

Peiliang Huang, Junwei Han, Nian Liu, Jun Ren and Dingwen Zhang, "Scribble-Supervised Video Object Segmentation," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 339-353, Feb. 2022. 

doi: 10.1109/JAS.2021.1004210

*An early attempt to achieve video object segmentation with scribble-level supervision, which can alleviate large amounts of human labors for collecting the manual annotation.

*The proposed scribble attention module can capture more accurate context information and learns an effective attention map to enhance the contrast between foreground and background.

*The proposed scribble-supervised loss can optimize the unlabeled pixels and dynamically corrects inaccurate segmented areas during the training stage.

Hao Zhang, Jianwen Sun and Zhuping Wang, "Distributed Control of Nonholonomic Robots Without Global Position Measurements Subject to Unknown Slippage Constraints," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 354-364, Feb. 2022. 

doi: 10.1109/JAS.2021.1004329

*The fully distributed formation control of multi-robot system without global position information while overcoming the effect of the unknown slippage constraint is proposed.

*Novel adaptive formation controllers and adaptive laws are proposed to achieve distributed control under the unknown slippage constrain.

*It is meaningful to overcome the dependence on global position information, therefore, a novel distributed finite time state observer without using any global position information is proposed in this paper to obtain the related states of the leader.

Lu Zhang, Jun Yang and Shihua Li, "A Model-Based Unmatched Disturbance Rejection Control Approach for Speed Regulation of a Converter-Driven DC Motor Using Output-Feedback," IEEE/CAA J. Autom. Sinica, vol. 9, no. 2, pp. 365-376, Feb. 2022. 

doi: 10.1109/JAS.2021.1004213

*The explicit relationship between the observer gains and the assigned poles has been developed for both the proposed method and the ADRC method. 

*This paper is concerned with unmatched disturbance rejections via output-feedback control.  

*It is further shown via numerical calculations and experimental results that the poles of the observer within the proposed control approach can be largely increased without significantly increasing magnitude of the observer gains.

网站：

http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570654

https://www.ieee-jas.net/

微信：JAS自动化学报英文版

Blog: http://blog.sciencenet.cn/?3291369

Twitter: IEEE/CAA JAS

Facebook: Ieee/Caa Jas

投稿：https://mc03.manuscriptcentral.com/ieee-jas

Email: jas@ia.ac.cn

Tel: 010-82544459