检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Junyi Zhu, Yuanyang Wang, Zhi Zheng, Yan Hao, Jianye Chen, Chunlin Department of Control Science and Intelligent Engineering Nanjing University China College of Intelligence and Computing Tianjin University China

Evolutionary reinforcement learning (ERL) algorithms recently raise attention in tackling complex reinforcement learning (RL) problems due to high parallelism, while they are prone to insufficient exploration or model collapse without carefully tuning hyperparameters (aka meta-parameters). In the paper, we propose a general meta ERL framework via bilevel optimization (BiERL) to jointly update hyperparameters in parallel to training the ERL model within a single agent, which relieves the need for prior domain knowledge or costly optimization procedure before model deployment. We design an elegant meta-level architecture that embeds the inner-level’s evolving experience into an informative population representation and introduce a simple and feasible evaluation of the meta-level fitness function to facilitate learning efficiency. We perform extensive experiments in MuJoCo and Box2D tasks to verify that as a general framework, BiERL outperforms various baselines and consistently improves the learning performance for a diversity of ERL algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ECG Signal Anomaly Detection Algorithm Based on CNN-BiLSTM 11

ECG Signal Anomaly Detection Algorithm Based on CNN-BiLSTM

引用

11th International Conference of Information and Communication Technology, ICTech 2022

作者： Cui, Kai Xing Xia, Xiao Jun School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100049 China Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Shenyang110168 China

ISBN: (数字)9781665496940

ISBN: (纸本)9781665496940

Aiming at the problems of low feature extraction efficiency and low detection accuracy of traditional ECG signal detection algorithms, this paper proposes a convolutional neural network (CNN) and bi-directional long short-term memory (Bi-directional long short-term memory, LSTM) network hybrid ECG signal anomaly detection algorithm. This model effectively utilizes the ability of CNN to automatically extract features and BiLSTM's ability to efficiently process time series data. Through experimental verification on the arrhythmia data set in the MIT-BIH database, the overall accuracy of the model is 98.56%. Compared with support vector machine (SVM) and bidirectional long short-term memory neural network (BiLSTM), the accuracy and F1 value of this model are improved. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Adaptive Higher order finite-time sliding mode control for master-slave manipulator with fixed-time delays

Adaptive Higher order finite-time sliding mode control for m...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Neila Mezghani Ben Romdhane Mohamed Boukattaya Tarak Damak Laboratory of Sciences and Technique of Automatic Control and Computing (Lab-STA) Nationnal School of Engineering of Sfax Sfax Tunisia

In this paper, an adaptive second order nonsingular fast terminal sliding mode control is proposed for the tracking problem of a teleoperation system. A robust control law is developed to achieve high precision tracking and strong robustness against parametric uncertainties, external disturbances, and time-varying delay. Meanwhile, through involving the discontinuous function into the time derivative of the control input, the proposed control scheme eliminates the chattering phenomenon and reduces the amplitude of the control effort. Furthermore, an adaptive tuning law is derived to avoid the prior knowledge of the upper bound of the compound disturbances, which is more efficient for practical applications. The stability of the system is proved using the Lyapunov theory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Serial Chain Hinge Support for Soft, Robust and Effective Grasp

Serial Chain Hinge Support for Soft, Robust and Effective Gr...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Dario Stuhne Jelena Vuletić Marsela Car Matko Orsag LARICS Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

This paper presents a serial chain hinge support, a rigid yet flexible structure that improves the mechanical performance and robustness of soft-fingered grippers. Gravity can reduce the integrity of soft fingers in horizontal approach, resulting in lower maximum payload caused by a large deflection of fingers. To substantiate our claim we performed multiple experiments on the payload and deflection of the SofIA gripper under both horizontal and vertical approaches. In addition, we show that this reinforcement does not impede the original compliant behavior of the gripper, maintaining the original kinematic model functionality. Also, we showcase the proprioceptive and exteroceptive capabilities for two opposing manipulation problems: grasping small and large objects. Finally, we validated the improved SofIA gripper in agricultural and everyday activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Printed Capacitive Displacement/Force Sensor with Different Patterns of Dielectric Layer 30

3D Printed Capacitive Displacement/Force Sensor with Differe...

引用

30th Telecommunications Forum, TELFOR 2022

作者： Suvara, Dragana Vajda, Kristina Katanic, Miroslav Kisic, Milica Damnjanovic, Mirjana Babkovic, Kalman Faculty of Technical Sciences University of Novi Sad Department of Computing and Control Engineering Novi Sad Serbia Faculty of Technical Sciences University of Novi Sad Department of Power Electronic and Telecommunication Engineering Novi Sad Serbia

ISBN: (数字)9781665472739

ISBN: (纸本)9781665472739

In this paper a simple capacitive sensor for displacement/force measuring is presented. Additive 3D printing technology was used to make the sensor housing and electrodes, while silicone rubber was used for the dielectric layer to ensure good sensitivity to the applied force. Three different patterns of dielectric layers were investigated. During experimental measurements, a change in capacitance was observed depending on the performed displacement in the range of 0.5 mm with 0.1 mm increments. The measured capacitance values and characteristics for all three types of sensors were compared. © 2022 IEEE.

关键词： Capacitive sensors

来源：评论

学校读者我要写书评

暂无评论

Accelerating Heterogeneous Federated Learning with Closed-form Classifiers

arXiv

引用

arXiv 2024年

作者： Fanì, Eros Camoriano, Raffaello Caputo, Barbara Ciccone, Marco Department of Computing and Control Engineering Polytechnic University of Turin Italy Istituto Italiano di Tecnologia Genoa Italy CINI Consortium Rome Italy

Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, particularly pronounced in the final classification layer, negatively impacting convergence speed and accuracy. To address this issue, we introduce Federated Recursive Ridge Regression (FED3R). Our method fits a Ridge Regression classifier computed in closed form leveraging pre-trained features. FED3R is immune to statistical heterogeneity and is invariant to the sampling order of the clients. Therefore, it proves particularly effective in cross-device scenarios. Furthermore, it is fast and efficient in terms of communication and computation costs, requiring up to two orders of magnitude fewer resources than the competitors. Finally, we propose to leverage the FED3R parameters as an initialization for a softmax classifier and subsequently fine-tune the model using any FL algorithm (FED3R with Fine-Tuning, FED3R+FT). Our findings also indicate that maintaining a fixed classifier aids in stabilizing the training and learning more discriminative features in cross-device settings. Official website: https://***/. © 2024, CC BY.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired visual relative localization for large swarms of UAVs

Bio-inspired visual relative localization for large swarms o...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Martin Křížek Matouš Vrba Antonella Barišić Kulaš Stjepan Bogdan Martin Saska Faculty of Electrical Engineering Czech Technical University in Prague Prague Laboratory for Robotics and Intelligent Control Systems (LARICS) Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We propose a new approach to visual perception for relative localization of agents within large-scale swarms of Unmanned Aerial Vehicles (UAVs). Inspired by biological perception utilized by schools of sardines, swarms of bees, and other large groups of animals capable of moving in a decentralized yet coherent manner, our method does not rely on detecting individual neighbors by each agent and estimating their relative position, but rather we propose to regress a neighbor density over distance. This allows for a more accurate distance estimation as well as better scalability with respect to the number of neighbors. Additionally, a novel swarm control algorithm is proposed to make it compatible with the new relative localization method. We provide a thorough evaluation of the presented methods and demonstrate that the regressing approach to distance estimation is more robust to varying relative pose of the targets and that it is suitable to be used as the main source of relative localization for swarm stabilization.

关键词： Location awareness Visualization Scalability Estimation Object detection Autonomous aerial vehicles Robustness

来源：评论

学校读者我要写书评

暂无评论

Overview of the SWCs Communication Mechanisms in Autonomous Vehicles 11

Overview of the SWCs Communication Mechanisms in Autonomous ...

引用

11th IEEE International Conference on Consumer Electronics, ICCE-Berlin 2021

作者： Kenjic, Dusan Antic, Marija University of Novi Sad Faculty of Technical Sciences Department of Computing and Control Engineering Novi Sad Serbia

ISBN: (纸本)9781665428316

The wide range of functional applications and the diversity of the use-cases, as well as the safety requirements in the automotive domain can only be supported by creating complex systems, with multiple control units and software components. The solution for speeding-up the developing process and decoupling the application development from the hardware specifics is layered standardized architecture. It defines the interfaces providing the platform services to the applications, regardless of the hardware itself. This way, it is possible to implement the system functionality on the application layer without the knowledge of how the lower layers which provide platform services are built. For that reason, the exact implementation of specific services has remained obscure, which often leads to confusion. This paper presents the overview of the main aspects in term of communication between software components (SWCs) in the automotive system. Different approaches will be presented and compared, considering both inter-and intra-core communications by examining single-core and multi-cores ECU architectures. © 2021 IEEE.

关键词： Ethernet

来源：评论

学校读者我要写书评

暂无评论

UAV Path Planning from Human Demonstrations Using Inverse Reinforcement Learning

UAV Path Planning from Human Demonstrations Using Inverse R...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Xu, Zhiang Dong, Jin Hua, Yongzhao Dong, Xiwang Li, Qingdong Ren, Zhang School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Academy of Blockchain and Edge Computing Beijing100086 China

ISBN: (纸本)9789811966125

In UAV path planning tasks, classical algorithms can only solve the tasks where environment is knowable and can be changed into mathematical model. For the tasks with unknown environment information is difficult to solve. However, such tasks can be easily solved by human. In this paper, we first bulid a UAV path planning environment and train the agent with deep reinforcement learning as human demonstration. Then, we use inverse reinforcement learning algorithm and processed human demonstrations to learn human policy. Finally, we test the trained policy in path planning tasks to verify the feasibility. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Modeling of doubly fed induction generator based wind energy conversion system and speed controller

Journal of Energy Systems

引用

Journal of Energy Systems 2021年第1期5卷 46-59页

作者： Haile, Endalew Ayenew Worku, Getachew Biru Beyene, Asrat Mulatu Tuka, Milkias Berhanu Adama Science and Technology University School of Electrical Engineering and Computing Electrical Power and Control Engineering Adama Ethiopia Addis Ababa Science and Technology University Center of Excellence for Sustainable Energy Addis Ababa Ethiopia

In this paper, modeling of doubly fed induction generator (DFIG) based wind energy conversion system (WECS) and generator speed controller are presented. The System Identification Toolbox of MatLab is used to develop the linear model of the WECS by considering the wind speed as input and speed of the generator as output. Two models, namely Auto Regressive with eXogenous Input (ARX) and Auto-Regressive Moving Average with eXogenous Input (ARMAX), are estimated. We used the ARX221 model structure with the best fit of 84.31%, Final Prediction Error (FPE) of 0.0433 and Mean Square Error (MSE) of 0.0432. The Ziegler-Nichols (Z-N) method and the fuzzy logic technique are employed in the proportional integral derivative (PID) controller design to control the speed of the generator. The classical Z-N PID used for the responses of the system is observed to be insufficient for both uniform and variable inputs, hence, a better response has been obtained by applying the fuzzy logic-based PID controller. The present study proves that the fuzzy logic based control enhances the speed regulation of generator in the WECS by overcoming the effect of varying wind speed. © Journal of Energy Systems 2021.

关键词： Fuzzy logic

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：