检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhao, Fuyu Gao, Weinan Liu, Tengfei Jiang, Zhong-Ping Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Liaoning Shenyang110819 China New York University Tandon School of Engineering Department of Electrical and Computer Engineering BrooklynNY11201 United States

ISBN: (纸本)9798350316339

This paper presents a novel policy iteration (PI) based event-triggered cooperative adaptive cruise control (CACC) approach for vehicular platoons, which are composed of autonomous vehicles. An observer is established to observe the signal of leading vehicle. To reduce computation and communication resources, event-triggered based adaptive optimal controllers are designed by using the PI algorithm without relying on the knowledge of system dynamics. Sufficient conditions are introduced to achieve the leader-to-formation stability (LFS) of the vehicular platoons. Simulation results are presented to verify the effectiveness of the proposed design. © 2024 IEEE.

关键词： Adaptive cruise control

来源：评论

学校读者我要写书评

暂无评论

A study of advanced mathematical modeling and adaptive control strategies for trajectory tracking in the Mitsubishi RV-2AJ 5-DOF Robotic Arm

引用

Discover Robotics 2025年第1期1卷 1-38页

作者： Ben Hazem, Zied Guler, Nivine Altaif, Ali Husain Automation and Sustainability Research Centre (ASRC) Department of Mechatronics Engineering College of Engineering (COE) University of Technology Bahrain Salmabad Kingdom of Bahrain Department of Computer Science University of Central Asia Naryn Kyrgyzstan

This study is focused on the advanced mathematical modeling and control strategies for a Mitsubishi RV-2AJ 5-DOF Robotic Arm, with an emphasis on achieving precision in trajectory tracking. Robotic trajectory tracking has long been challenged by the constraints of conventional modeling techniques and control methods. Prior contributions have been limited by the use of traditional dynamic models and classical controllers, which often failed to adapt to complex trajectory requirements. To address these challenges, a comprehensive dynamic model has been developed using Euler–Lagrange equations and validated through a comparison with a 3D CAD Simscape model in MATLAB/Simulink. For the control approach, a PID controller and an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller have been implemented to regulate the robotic arm’s joints. The ANFIS controller has been demonstrated to outperform the PID controller, achieving improved stability and adaptability in trajectory tracking. The robustness of the proposed system has been confirmed through simulation results for various trajectory types, including N-shaped, circular, and complex paths. This study underscores the importance of advanced modeling and hybrid control strategies in overcoming the limitations of traditional methods. By establishing a solid foundation in precise trajectory tracking through advanced mathematical modeling, this work contributes to the development of more adaptive and efficient robotic systems, with potential applications in industrial and research domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Finite-time robust performance improvement for non-linear systems in the presence of input non-linearity and external disturbance

引用

IET Control Theory and Applications 2023年第6期17卷 672-682页

作者： Wang, Haoping Ghaffari, Valiollah Mobayen, Saleh Bartoszewicz, Andrzej Fekih, Afef Assawinchaichote, Wudhichai School of Automation Nanjing University of Science and Technology Nanjing China Department of Electrical Engineering Persian Gulf University Bushehr Iran Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin Douliou Taiwan Institute of Automatic Control Lodz University of Technology Lodz Poland Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA United States Department of Electronic and Telecommunication Engineering Faculty of Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand

The main focus of this research is on improving the performance of dynamic systems with actuator non-linearities and time-varying disturbances. To this end, using the concept of finite-time stability, a novel observer is presented to estimate the disturbances in systems with input non-linearities. Then, introducing an innovative sliding manifold, a robust observer-based technique is derived to guarantee the finite-time stability of the sliding surface. Hence, the closed-loop system would be stable in the presence of hard non-linearities and time-varying disturbances. The performance of the proposed approach was assessed in using a simulation study of two numerical examples. The obtained results and comparison with a conventional method confirmed the benefits of the suggested approach. © 2022 The Authors. IET Control Theory & Applications published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

GRU-Net: Gaussian Attention Aided Dense Skip Connection Based MultiResUNet for Breast Histopathology Image Segmentation 28th

GRU-Net: Gaussian Attention Aided Dense Skip Connection Base...

引用

28th Annual Conference on Medical Image Understanding and Analysis, MIUA 2024

作者： Roy, Ayush Pramanik, Payel Ghosal, Sohom Valenkova, Daria Kaplun, Dmitrii Sarkar, Ram Department of Electrical Engineering Jadavpur University Kolkata700032 India Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Department of Electronics and Communication Engineering International Institute of Information Technology Chhattisgarh India Department of Automation and Control Processes Saint Petersburg Electrotechnical University LETI Saint Petersburg Russia Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China

ISBN: (纸本)9783031669545

Breast cancer is a major global health concern. Pathologists face challenges in analyzing complex features from pathological images, which is a time-consuming and labor-intensive task. Therefore, efficient computer-based diagnostic tools are needed for early detection and treatment planning. This paper presents a modified version of MultiResU-Net for histopathology image segmentation, which is selected as the backbone for its ability to analyze and segment complex features at multiple scales and ensure effective feature flow via skip connections. The modified version also utilizes the Gaussian distribution-based Attention Module (GdAM) to incorporate histopathology-relevant text information in a Gaussian distribution. The sampled features from the Gaussian text feature-guided distribution highlight specific spatial regions based on prior knowledge. Finally, using the Controlled Dense Residual Block (CDRB) on skip connections of MultiResU-Net, the information is transferred from the encoder layers to the decoder layers in a controlled manner using a scaling parameter derived from the extracted spatial features. We validate our approach on two diverse breast cancer histopathology image datasets: TNBC and MonuSeg, demonstrating superior segmentation performance compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Resilient Design of Continuous-time Distributed Optimization Algorithm in the Presence of Cyber-attacks

引用

IFAC-PapersOnLine 2023年第2期56卷 5907-5912页

作者： Muhammad Iqbal Zhihua Qu Azwirman Gusrialdi Automation and Mechanical Engineering unit Tampere University Finland Department of Electrical and Computer Engineering University of Central Florida USA Florida

This paper presents a continuous-time resilient distributed optimization algorithm based on competitive interaction design method on connected graphs in the presence of adversaries. The competitive interaction method allows us to design a network that protects the multi-agent systems from adversaries without requiring high network connectivity. In addition, the proposed algorithm does not require the global information about the number of adversaries. First, we show that the proposed distributed algorithm solves the resilient distributed optimization problem with no attack on the communication links. Second, we show that the proposed continuous-time distributed optimization algorithm on connected graphs converges to the small neighborhood of the optimal solution in the presence of cyber-attacks onto the communication channel. Simulations are presented to illustrate our theoretical results.

关键词： Networked Systems Distributed optimization for large-scale systems Security in networked control systems

来源：评论

学校读者我要写书评

暂无评论

Application of Correction Methods for Measured Data from a Model Object's Microclimate Monitoring System

Application of Correction Methods for Measured Data from a M...

引用

Information, Control, and Communication Technologies (ICCT), International Conference on

作者： Nickita Potapov Alexandr Kaychenov Ilya Selyakov Automation and Computer Engineering Department Murmansk Arctic University Murmansk Russia

This paper describes the correction methods for humidity sensors included in the microclimate monitoring system based on the model object located in Murmansk, Russia. The first part of the paper provides the sensor placement scheme for wall and log parts of the model object. Zonal correction method (with splitting and sorting data by humidity groups) and regression correction (linear regression based) method are described. Advantages and potential caveats of aforementioned methods are provided. The second part of the paper describes the correction experiment carried on data being collected from the model object during 2022. Correlation coefficients describing the connection between indicative humidity sensors and reference sensors were calculated from the data. Further calculations through correction methods were made; each corrected sensor was evaluated via mean squared error (MSE) score. The final part of the paper provides the conclusive evaluation of performance of each correction method with considerations of various correlation coefficients and external influences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Quasi-Hyperbolic Discounting

arXiv

引用

arXiv 2024年

作者： Eshwar, S.R. Motwani, Mayank Roy, Nibedita Thoppe, Gugan Department of Computer Science and Automation Indian Institute of Science Bengaluru India Department of Computer Science and Engineering Indian Institute of Technology Bombay India

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which has a bias towards immediate gratification. Quasi-Hyperbolic (QH) discounting is a simple alternative for modeling this bias. Unlike in traditional discounting, though, the optimal QH-policy, starting from some time t1, can be different to the one starting from t2. Hence, the future self of an agent, if it is naive or impatient, can deviate from the policy that is optimal at the start, leading to sub-optimal overall returns. To prevent this behavior, an alternative is to work with a policy anchored in a Markov Perfect Equilibrium (MPE). In this work, we propose the first model-free algorithm for finding an MPE. Using a two-timescale analysis, we show that, if our algorithm converges, then the limit must be an MPE. We also validate this claim numerically for the standard inventory system with stochastic demands. Our work significantly advances the practical application of reinforcement learning. © 2024, CC BY-NC-ND.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Soil Property Estimations from Earth Observation Data with Differential Evolution-Based Multi-Objective TSK Model 13

Enhanced Soil Property Estimations from Earth Observation Da...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Tsakiridis, Nikolaos L. Samarinas, Nikiforos Kalopesa, Eleni Theocharis, John B. Zalidis, George C. Aristotle University of Thessaloniki Spectra Lab Group Laboratory of Remote Sensing Spectroscopy and Gis Department of Agriculture Thessaloniki54124 Greece Aristotle University of Thessaloniki Automation and Robotics Laboratory Electrical and Computer Engineering Thessaloniki54124 Greece

ISBN: (纸本)9798350308365

This paper introduces a novel approach integrating Differential Evolution (DE) with multi-objective optimization techniques for enhancing Type-1 Takagi-Sugeno-Kang (TSK) fuzzy rule-based systems to attain both fair predictive performance and enhanced interpretability within the context of explainable artificial intelligence. The developed approach encodes the whole knowledge base into one chromosome and endeavors to concurrently optimize the prediction accuracy, the number of rules, and the selection of relevant input features. The methodology was tested on Earth observation data for the estimation of soil health parameters via infrared spectroscopy, and more concretely i) on the 2015 LUCAS topsoil dataset to predict three key soil properties (namely, soil organic carbon, clay content, and pH) from laboratory spectra, and ii) on a set of PRISMA hyperspectral images to predict soil organic carbon in a region of northern Greece. Compared to the classical Random Forest (RF) algorithm, our proposed learning algorithm attains a fair balance between accuracy and interpretability, and is statistically equivalent to RF in terms of accuracy. The findings underscore the potential of the proposed methodology in refining TSK models and its applicability in Earth observation-driven predictions, paving the way for both enhanced modeling accuracy and sparse feature selection. © 2024 IEEE.

关键词： Fuzzy rules

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Quasi-Hyperbolic Discounting (Extended Abstract)

Reinforcement Learning with Quasi-Hyperbolic Discounting (Ex...

引用

Indian Control Conference (ICC)

作者： S.R. Eshwar Mayank Motwani Nibedita Roy Gugan Thoppe Department of Computer Science and Automation Indian Institute of Science Bengaluru India Department of Computer Science and Engineering Indian Institute of Technology Bombay India

ISBN: (数字)9798331517212

ISBN: (纸本)9798331517229

Human decision-making is better modeled via discounting schemes such as quasi-hyperbolic and hyperbolic than classical ones such as exponential or average reward. In [3], we initiated the study of reinforcement learning with Quasi-Hyperbolic (QH) discounting and proposed the first model-free algorithm for finding a type of policy called the Markov perfect equilibrium. This paper provides a summary of that algorithm and our other findings on its convergence.

关键词： Decision making Reinforcement learning Convergence

来源：评论

学校读者我要写书评

暂无评论

Adaptive dynamic programming control algorithm and simulation software design 3

Adaptive dynamic programming control algorithm and simulatio...

引用

2022 3rd International Conference on computer Information and Big Data Applications, CIBDA 2022

作者： Ma, Runmin Xia, Xiaonan School of Computer Sciences and Engineering Northeastern University Shenyang110169 China Department of Automation College of Information Engineering Yangzhou University Yangzhou225127 China

ISBN: (纸本)9783800758760

In this paper, an event-triggered adaptive dynamic programming tracking control scheme is investigated for a class of nonlinear systems with unmodeled dynamics based on dynamic surface control method. Due to considering the ummodeled dynamics, the feedback control consists of two controllers. One is used to compensate the unmodeled dynamics and system functions, and the other is used to optimize the system performance. Based on the control scheme, a parameter setting and real-time simulation system is developed by using Matlab GUI and M language. The system provides the functions of solving the optimal controller, tuning the controller parameters and real-time simulation of the control system. Through this software, the design parameters can be set repeatedly online and the control results can be observed in real time. The main results of algorithm design and simulation software are given in this paper. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Controllers

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：