2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)最新文献

Weld Seam Extraction of Intersecting Pipelines Based on Point Cloud Entropy 基于点云熵的相交管道焊缝提取

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858446

Shuaibing Lu, Xiaorui Shi, Xincheng Tian, Yan Liu

引用次数: 1

Rehabilitation Path Planning Based on Human Motion Output and Ergonomic Index Optimization 基于人体运动输出和工效指标优化的康复路径规划

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858384

Tianyu He, Yangben Yan, Gang-Yi Wang, Yongbai Liu, Keping Liu, Zhongbo Sun

{"title":"Rehabilitation Path Planning Based on Human Motion Output and Ergonomic Index Optimization","authors":"Tianyu He, Yangben Yan, Gang-Yi Wang, Yongbai Liu, Keping Liu, Zhongbo Sun","doi":"10.1109/DDCLS55054.2022.9858384","DOIUrl":"https://doi.org/10.1109/DDCLS55054.2022.9858384","url":null,"abstract":"Rehabilitation robots help patients perform rehabilitation training according to the planned path, and reasonable planning of the rehabilitation path can enable patients to obtain better rehabilitation effects. In view of the problems of low degree of personification and poor comfort in the path planning of rehabilitation robots. In this paper, the normalized output function for human-like path planning is obtained, which is based on the inherent virtual constraints or output of the human lower limb, and the constraints are optimized through ergonomic index. First, the human body output data of the subject is collected through the optical motion capture system, after that the original normalized output function is obtained by Fourier fitting, and then the constraints are based on ergonomic indicators. Second, the constrained human body output data is calculated by the golden section algorithm, and finally the final human body standardized output function is obtained by Fourier fitting. Last, the standardized output function based on human output is applied in the path planning of rehabilitation robots, which can make the training of rehabilitation robots have a higher degree of human simulation and comfort, so as to achieve better rehabilitation effect.","PeriodicalId":412672,"journal":{"name":"2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115600580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance Analysis of Optimal Relay Selection for Urban Vehicles Based on Max-min Strategy 基于最大最小策略的城市车辆继电器优选性能分析

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858545

Junjie Yi, Lei Liu

引用次数: 0

Adaptive Repetitive Control for a Class of Uncertain Nonlinear Systems Based on Additive-state-decomposition and Dynamic Surface Technique 基于加性状态分解和动态曲面技术的一类不确定非线性系统自适应重复控制

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858450

Yongbo Sun, Lan Zhou, F. Jia, Dongxu Gao

{"title":"Adaptive Repetitive Control for a Class of Uncertain Nonlinear Systems Based on Additive-state-decomposition and Dynamic Surface Technique","authors":"Yongbo Sun, Lan Zhou, F. Jia, Dongxu Gao","doi":"10.1109/DDCLS55054.2022.9858450","DOIUrl":"https://doi.org/10.1109/DDCLS55054.2022.9858450","url":null,"abstract":"This paper proposes an adaptive repetitive control (RC) scheme for a class of uncertain nonlinear systems with mismatched disturbances based on additional-state-decomposition and dynamic surface technique. First, the original tracking problem for uncertain nonlinear system is decomposed into two subproblems, which are RC problem for linear time-invariant (LTI) primary system and robust stabilization problem for uncertain nonlinear secondary system with mismatched disturbances. For LTI primary system, modified RC is used to deal with periodic signals. In addition, the time-delay constant of the repetitive controller is corrected in the frequency domain, which further improves the tracking performance. For uncertain nonlinear secondary system, backstepping control is used to deal with mismatched disturbances, and dynamic surface technique is used to avoid “explosion of terms” in backstepping design. Under the designed composite controller, all signals of the closed-loop system are semi-globally bounded and the system output quickly tracks the reference input. Finally, numerical results illustrate the validity and superiorities of the proposed method.","PeriodicalId":412672,"journal":{"name":"2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125032370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Model Free Adaptive Tracking Control of Multi-cascade Connection Systems with Switching Topology 具有切换拓扑的多级联系统无模型自适应跟踪控制

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858501

Zhipeng Zhang, Shuangshuang Xiong, Zhongsheng Hou

引用次数: 0

Adaptive Estimation for Quantized Nonlinear Cascade System 量化非线性级联系统的自适应估计

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858456

Ying Wang, Fengxian Wang, J. Zhang, Linwei Li, X. Ren

{"title":"Adaptive Estimation for Quantized Nonlinear Cascade System","authors":"Ying Wang, Fengxian Wang, J. Zhang, Linwei Li, X. Ren","doi":"10.1109/DDCLS55054.2022.9858456","DOIUrl":"https://doi.org/10.1109/DDCLS55054.2022.9858456","url":null,"abstract":"In this paper, we introduce an adaptive estimation method for quantized nonlinear cascade system using moving window theory. Firstly, by force of the sub-decomposition technique, the considered system is transformed to a regression model without product term, in which the computational complexity is reduced. Secondly, by developing a moving window, the moving window output and moving window observation data are constructed, in which the estimation accuracy is lifted. Then, based on moving data, a filter is introduced to filter noise data, and to improve the bias estimation issue. Thirdly, by designing the forcing variables with adaptive attenuation coefficient, the estimation error data can be got which is used to develop estimator, in which it gives an optional scheme to design the adaptive estimator compared with the prediction error and observation error criterion. Finally, the example results demonstrate that the developed method is effective to achieve the parameter estimation for quantized nonlinear cascade system, and the has better performance compared with some estimators in term of estimation precision and convergence rate.","PeriodicalId":412672,"journal":{"name":"2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122412149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-innovation Parameter Identification Based on Coupling Auxiliary Model for Three-axis Turntable 基于耦合辅助模型的三轴转台多创新参数辨识

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858554

Minlin Wang, Xueming Dong, X. Ren

引用次数: 0

Vehicle Tracking Method Based on Attention-YOLOv5 and Optimized DeepSort Models 基于注意力- yolov5和优化深度排序模型的车辆跟踪方法

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858395

Zhuang Li, Xincheng Tian, Yan Liu, Xiaorui Shi

{"title":"Vehicle Tracking Method Based on Attention-YOLOv5 and Optimized DeepSort Models","authors":"Zhuang Li, Xincheng Tian, Yan Liu, Xiaorui Shi","doi":"10.1109/DDCLS55054.2022.9858395","DOIUrl":"https://doi.org/10.1109/DDCLS55054.2022.9858395","url":null,"abstract":"Vehicle tracking plays a vital role in traffic management and autonomous driving. In order to further improve the accuracy of vehicle tracking, reduce the number of ID-Switch and enhance the anti-interference ability to the outside world, we propose a vehicle detection and tracking model based on Attention-YOLOv5 and optimized DeepSort. Firstly, YOLOv5 with attention mechanism was used as the front-end target detector, that is, add CBAM and ECA attention mechanisms to the backbone network of the benchmark YOLOv5 separately to improve the feature extraction ability. Then use the transfer learning idea to train it on the BDD dataset, it is concluded that ECA-YOLOv5 has the highest detection accuracy. Further we optimize the DeepSort algorithm, in order to overcome the disadvantages of the pre-training model not targeting traffic vehicles, we improve the re-recognition network structure and optimize the VeRi re-identification dataset, next perform re-identification pre-training on the Improved-VeRi dataset based on transfer learning. In order to make the vehicle features evenly distributed around the center of the class and improve feature resolution, a loss function ${L_{vehicle_CL}}$ combining the Softmax loss function and Center loss function is proposed. In the experimental part, collecting some highway traffic videos of different scenes. At first, conduct visual analysis, then perform ablation experiments, and evaluate by using MOTA, MOTP and ID-Switch. Compared with the benchmark algorithm, the tracking performance is significantly improved.","PeriodicalId":412672,"journal":{"name":"2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122445931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Adaptive Gaussian Process Regression Based Remaining Useful Life Prediction of PEMFC Incorporating An Improved Health Indicator 基于改进健康指标的PEMFC剩余使用寿命预测自适应高斯过程回归

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858570

Lin Tang, Xu Yang, Jingjing Gao, Jian Huang, Jiarui Cui

引用次数: 0

Output Regulation for Switched Systems: An Event-Triggered Model Predictive Control Approach 切换系统的输出调节:一种事件触发模型预测控制方法

2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS) Pub Date : 2022-08-03 DOI: 10.1109/DDCLS55054.2022.9858368

Shitong Guo, Yiwen Qi, Simeng Zhang, Yiwen Tang, Wenke Yu

引用次数: 0