检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Diehl, Christopher Klosek, Tobias Krüger, Martin Murzyn, Nils Bertram, Torsten Institute of Control Theory and Systems Engineering TU Dortmund University Dortmund Germany ZF Friedrichshafen AG Artificial Intelligence Lab Saarbrücken Germany

Game theory offers an interpretable mathematical framework for modeling multi-agent interactions. However, its applicability in real-world robotics applications is hindered by several challenges, such as unknown agents’ preferences and goals. To address these challenges, we show a connection between differential games, optimal control, and energy-based models and demonstrate how existing approaches can be unified under our proposed Energy-based Potential Game formulation. Building upon this formulation, this work introduces a new end-to-end learning application that combines neural networks for game-parameter inference with a differentiable game-theoretic optimization layer, acting as an inductive bias. The experiments using simulated mobile robot pedestrian interactions and real-world automated driving data provide empirical evidence that the game-theoretic layer improves the predictive performance of various neural network backbones. Copyright © 2023, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

An Approach for Predicting and Compensating the End Deformation of a Heavy Load Robot for Friction Stir Welding 16th

An Approach for Predicting and Compensating the End Deformat...

引用

16th International Federation of theory of Machines and Mechanisms World Congress, IFToMM WC 2023

作者： Bai, Yujie Liu, Haitao Meng, Shaofei Ma, Yue Yue, Wei Li, Guangxi Xiao, Juliang Wang, Guofeng Ding, Yabin Key Laboratory of Mechanism Theory and Equipment Design of State Ministry of Education Tianjin University Tianjin300072 China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Dongguan University of Technology Dongguan523808 China

ISBN: (纸本)9783031457043

Aiming at solving the problem of insufficient plunge depth by the deformation of friction stir welding robots, this paper presents a method for predicting and compensating for the end deformation of friction stir welding robots. Firstly, the numerical model of FSW is established using DEFORM-3D software, then the axial force on the welding tool is obtained. Subsequently, the robot stiffness model is established based on the screw theory to realize the prediction of robot deformation in the workspace. Finally, a deformation compensation method based on the mirror principle is proposed to realize the compensation of the welding trajectory. Taking the 10 mm AA6061 aluminium alloy FSW as an example, the compensation method proposed in this paper is verified by using computer simulation. The results show that the stiffness model established in this paper can accurately predict the end deformation of the robot. The maximum plunge depth deviation of the compensation method proposed in this paper is reduced by 95.17% compared with the uncompensated case, which proves the effectiveness of the proposed compensation method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Friction stir welding

来源：评论

学校读者我要写书评

暂无评论

A High-Precision Edge Detection Algorithm Based on Improved Sobel Operator-Assisted HED 14

A High-Precision Edge Detection Algorithm Based on Improved ...

引用

14th IEEE International Conference on Cyber Technology in Automation, control, and Intelligent Systems, CYBER 2024

作者： Yuan, Yeborui Chen, Wenyuan Tang, Jie Yang, Jia School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang State Key Laboratory of Robotics 110016 China University of Chinese Academy of Sciences Beijing100049 China School of Electrical Engineering and Automation Tianjin University of Technology Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin300384 China

ISBN: (纸本)9798331506056

In response to the problem of poor detection performance of the traditional Sobel operator in edge detection, a high-precision edge detection algorithm based on Sobel operator-assisted Holistically-nested Edge Detection (HED) network was proposed, which is named ISAHED here. The algorithm is designed as follows. Firstly, an improved Sobel operator based on the traditional Sobel operator was proposed through adding gradient direction. Then, the image output by the improved Sobel operator is taken as the ground-truth image and as the end-to-end comparison object in a HED-like network. Finally, the ISAHED algorithm outputs edge images with better quality through iterative learning of the HED-like neural network. The experimental results prove that the proposed ISAHED algorithm has better edge detection performance by visually observing the final edge images and further evaluating the values of FOM. This work provides an important reference for the further development of the edge detection technology. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A time-delay approach to stabilization by extremum seeking controller via simplified ISS analysis

引用

IFAC-PapersOnLine 2023年第2期56卷 4289-4294页

作者： Jin Zhang Emilia Fridman Xuefei Yang School of Mechatronic Engineering and Automation Shanghai University Shanghai 200072 China School of Electrical Engineering Tel Aviv University Tel Aviv 69978 Israel Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China

We study stabilization of linear uncertain systems under unknown control directions using a bounded extremum seeking controller with a small parameter. We consider a small time-varying measurement delay. By using the recently proposed time-delay approach to Lie-Brackets-based averaging, we transform the closed-loop system to a time-delay (neutral type) one, which has a form of perturbed Lie brackets system. The input-to-state stability (ISS) of the time-delay system guarantees the same for the original one. Differently from the existing analysis via Lyapunov-Krasovskii (L-K) method, we transform the neutral system to an ordinary differential equation (ODE) with delayed perturbations and employ variation of constants formula that greatly simplifies the analysis and leads to simpler stability conditions. Two numerical examples illustrate that the proposed method allows essentially larger parameter uncertainties with bounds on the small parameter and time-delay that are not too small.

关键词： Time-delay Lie-brackets-based averaging extremum seeking

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement Method for Arc Welding Process Monitoring in the Present of Strong Arc Light Interference 7th

Image Enhancement Method for Arc Welding Process Monitoring ...

引用

7th International Conference on Nanomanufacturing, nanoMan2021

作者： He, Xinxin Liu, Bin Yang, Fan Wang, Zhongya Wen, Yaxin Zhang, Baofeng School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin China Co. Ltd. Tianjin China University of Technology Tianjin China

ISBN: (纸本)9789811919176

The application of vision technology plays a significant role in the development of intelligent automatic welding. However, the welding process would produce strong arc light. The arc light seriously reduces the imaging quality of the vision system. In this case, the function of vision auxiliary would fail. The operation of a suitable image enhancement algorithm is capable of solving the problems caused by the strong arc light, such as nonuniform brightness, the loss of edges and low signal-to-noise. In this paper, image enhancement algorithm was studied to solve the imaging interference caused by the strong arc light. According to the characteristic of captured image, the advantage of LIME algorithm was analyzed. Then suitable filtering method was introduced into LIME to improve the enhancement. Experimental results showed that the algorithm could balance the global brightness and suppress the intensity of the strong light area. Furthermore, the original object contour details could be restored to optimize the visual effect. By investigating the effect of various low-light image enhancement algorithms from both subjective and objective aspects, the combined algorithm was proved to be effective. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition in Chinese Medical Texts Based on RoBERTa-WWM-IDCNN-CRF

Named Entity Recognition in Chinese Medical Texts Based on R...

引用

System Simulation Technology and its Application (CCSSTA), IEEE China Conference on

作者： Lan Tang Jie Kong Liang Xu School of Computer Xi‘an Shiyou University Xi‘an China Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China

ISBN: (数字)9798350366600

ISBN: (纸本)9798350366617

Electronic medical records and doctor-patient conversations contain a wealth of useful information, such as disease symptoms, drug names, and cure cycles. Traditional deep learning approaches utilize bidirectional recurrent neural networks to encode text, which cannot effectively capture long-distance dependencies in text. In order to identify medical entity types in various texts more accurately, a named entity recognition approach based on RoBERTa-WWM-IDCNN-CRF is proposed. This approach introduces the RoBERTa-WWM pre-trained model, in order to improve the overall understanding of long Chinese texts for the first time. The model generates semantic representations containing prior knowledge. Then, the generated semantic representations are feed to the IDCNN to extract sentence level characteristics. Finally, the global optimal solution is obtained and the results of the named entity are produced through the CRF. The experiment indicates that the improvement of $F_{1}$ score, accuracy, and recall of RoBERTa-WWM-IDCNN-CRF model are 7.94%, 4.52% and 10.02% comparing with the classical BiLSTM-CRF model.

关键词： Drugs Recurrent neural networks Semantics Named entity recognition Oral communication Medical services Systems simulation Feeds Electronic medical records Diseases

来源：评论

学校读者我要写书评

暂无评论

FATUnetr:fully attention Transformer for 3D medical image segmentation

FATUnetr:fully attention Transformer for 3D medical image se...

引用

IEEE International Conference on Mechatronics and Automation

作者： QingFeng Li Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology Tianjin China Department of Electrical Engineering Tshwane University of Technology South Africa

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Recent studies have explored the applicability of the Transformer model in 3D medical segmentation tasks. The core attention mechanism of transformer, has the property of capturing remote dependencies, which is highly robust when segmenting medical images. Inspired by the emerging visual groupings in Vision Transformers (ViTs), self-attention can be made more robust by improving the intermediate representation. We propose a novel framework called FATUnetr that aims to take advantage of the full attention module to improve accuracy. We also reduce the number of parameters by applying deeply separable convolution at the bottleneck layer. We have verified the effectiveness in the extracranial vault multiple atlas labelling (BTCV) dataset for multi-organ segmentation.

关键词： Image segmentation Visualization Three-dimensional displays Attention mechanisms Accuracy Convolution Transformer cores

来源：评论

学校读者我要写书评

暂无评论

Simplified Nonlinear Programs for NMPC Based on Active Set Construction *

Simplified Nonlinear Programs for NMPC Based on Active Set C...

引用

IEEE Conference on Decision and control

作者： Raphael Dyrska Martin Mönnigmann Faculty of Mechanical Engineering Automatic Control and Systems Theory Ruhr-Universität Bochum Bochum Germany

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

The nonlinear program arising in nonlinear model predictive control can be simplified by constructing candidate active sets for the successor state. Instead of modifying the optimization algorithm directly, we use these active sets to anticipate the relevant constraints for the next time step and to solve a simplified nonlinear program. Since active sets are in general valid for a set of initial states, an inherent robustness with respect to additive disturbances results.

关键词： Performance evaluation Uncertainty Computational modeling Prediction algorithms Robustness Hardware Batteries

来源：评论

学校读者我要写书评

暂无评论

Response Estimation and Reference Model-free controller Design Approach for 2-DOF control Systems

Response Estimation and Reference Model-free Controller Desi...

引用

Fully Actuated System theory and Applications (CFASTA), Conference on

作者： Ruirui Yang Kazuhiro Yubai Satoshi Komada Daisuke Yashiro Weijie Ren Department of Electrical and Electronic Engineering Mie University Kurimamachiya Tsu Japan Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern Uni. of Sci. and Tech Shenzhen China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

In this paper, we adopt a linear time-invariant (LTI) two-degree-of-freedom (2-DOF) control system as our subject of control. An input-output response estimation method and a controller design method based on response estimation are proposed. First, using the initial input-output data of a closed-loop system to estimate the response when updating controller parameters. Second, the controller parameters are updated by optimizing the objective function based on the estimated response data. Finally, numerical examples verify the effectiveness of the proposed method. Unlike traditional data-driven design methods based on reference models, the proposed controller design method does not require a reference model, which solves the problem of the difficulty of selecting a suitable reference model. Additionally, the response after the controller update can be estimated in advance before being applied to the real machine system. Avoiding the wear and tear or damage of the machine caused by the direct real machine test when the designed controller is not ideal, meanwhile saving the experimental cost.

关键词： Linear systems Design methodology Noise Estimation 2-DOF Process control Numerical models

来源：评论

学校读者我要写书评

暂无评论

Optimization of b-spline parameterized trajectories for on-road vehicle guidance 12

Optimization of b-spline parameterized trajectories for on-r...

引用

12th GMM Symposium on Automotive meets Electronics, AmE 2021

作者： Dorpmüller, Philip Keller, Martin Bertram, Torsten TU Dortmund Institute of Control Theory and Systems Engineering Dortmund44227 Germany ZF Group Division Electronics and ADAS Gelsenkirchen45881 Germany

ISBN: (纸本)9783800754885

The guidance of an automated vehicle requires a software-module, which plans a comfortable and collision-free future motion. Furthermore, it must be able to lead the vehicle into a given planning goal. This requires the design of a trajectory planning method including a suitable objective function under consideration of vehicle dynamics and environmental constraints. In this contribution, a trajectory planning algorithm is proposed, which enables the execution of different maneuvers for on-road driving. Restrictions of the state-and input space are included as hard constraints. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：