检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Wang, Gang Giannakis, Georgios B. Chen, Jie Digital Technology Center Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States State Key Lab of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Tongji University Shanghai200092 China

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the underlying data distribution being e.g. Gaussian, or require the network size and/or training size to be sufficiently large. In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted. Leveraging the power of random noise perturbation, this paper presents a novel stochastic gradient descent (SGD) algorithm, which can provably train any single-hidden-layer ReLU network to attain global optimality, despite the presence of infinitely many bad local minima, maxima, and saddle points in general. This result is the first of its kind, requiring no assumptions on the data distribution, training/network size, or initialization. Convergence of the resultant iterative algorithm to a global minimum is analyzed by establishing both an upper bound and a lower bound on the number of non-zero updates to be performed. Moreover, generalization guarantees are developed for ReLU networks trained with the novel SGD leveraging classic compression bounds. These guarantees highlight a key difference (at least in the worst case) between reliably learning a ReLU network as well as a leaky ReLU network in terms of sample complexity. Numerical tests using both synthetic data and real images validate the effectiveness of the algorithm and the practical merits of the theory. Copyright © 2018, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Synthesis of H/sub 2/ guaranteed cost fuzzy controller for missile altitude system via linear matrix inequalities

Synthesis of H/sub 2/ guaranteed cost fuzzy controller for m...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Xiao-Hu Yuan Jian-Cun Ren You-Jin He Fu-Chun Sun Dept. of Control Engineering Naval Aeronautical Engineering Academy Yantai Shandong province China State Key Lab. of Intelligent Technology and Systems Tsinghua University Beijing China

ISBN: (纸本)0780385675

This paper deals with H/sub 2/ guaranteed cost (GC) fuzzy output feedback control problem for missile altitude control system. First, the Takagi-Sugeno fuzzy model is employed to represent the dynamics of the missile altitude control system. Next, we present necessary and sufficient conditions for the existence of a quadratically stabilizing fuzzy output feedback controller which also assure H/sub 2/ guaranteed cost performance on a fuzzy dynamic system where the uncertainty is of the norm bounded type. The conditions are presented as a collection of linear matrix inequalities. A simulation on the missile altitude system is given to illustrate the effectiveness of the proposed design method.

关键词： Fuzzy control Fuzzy systems control systems Missiles control system synthesis Costs Output feedback Takagi-Sugeno model Sufficient conditions Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Small World Effect and Random Fuzzy Graph

Research Square

引用

Research Square 2021年

作者： Zhang, Yijin Huang, Jie Lin, Zongbing Key Lab of Intelligent Analysis and Decision on Complex Systems Chongqing Municipal Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China School of Mathematics and Computer Science Panzhihua University Panzhihua617000 China

Small World Effect (or Six Degrees of Separation theory) has generated significant influence in the world. Many researchers and institutes have done lots of work on the study of it. We model Small World Effect by random process and Graph, calculate the probability that any two people i and j in the world can contact each other after n steps (forwarding messages by intermediaries) based on different R (average number of acquaintances everyone has in the world).When R=50 or 80, if, the probability is 0.848 and the search is very likely to happen. When R=150, n=4, this probability is 0.99994, that is, after 4 steps, any two people in the world will establish connection almost surely. In the sense of Dunbar's number (R=150), six degrees of separation becomes four degrees of separation. We propose the concepts of (directed) Random Fuzzy Graph for the very first time which can describe the fact of recognition among people best, because the relation among persons is random and fuzzy. © 2021, CC BY.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Automatic Cell Assembly by Two-fingered Microhand

Automatic Cell Assembly by Two-fingered Microhand

引用

2019 IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Junnan Chen Xiaoming Liu Shengnan Dong Pengyun Li Xiaoqing Tang Dan Liu Masaru Kojima Qiang Huang Tatsuo Arai Intelligent Robotics Institute School of Mechatronical Engineering Key Laboratory of Biomimetic Robots and Systems Ministry of Education Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing CHINA Department of Systems Innovation Graduate school of Engineering Science Osaka University Toyonaka Osaka Japan Global Alliance Lab The University of Electro-Communications Tokyo Japan

We have successfully achieved manipulation and assembly of microbeads having the size of 100μm diameter by hemispherical end-effectors with high stability and accuracy. The motivation of achieving assembly of actual cells lies in the great significance of it in tissue regeneration and cell analysis. Firstly, the most difficult problem we need to solve is the releasing problem caused by adhesion force. The viscosity on cell surface is much larger than the microbeads which makes cell releasing challenging. Secondly, the cell can generate its deformation, then contact area with end-effector will change during grasping process. This may influence the adhesion force and also bring problem to releasing. Thirdly, cell is much smaller, around 15μm in diameter, so we need to fabricate smaller end-effector to achieve successful manipulation and ensure the stability in the meantime. In this paper, we realize the manipulation by decreasing the adhesion forces and apply vibration to release a cell stably. We found the appropriate scale size for the end-effector is around 10μm diameter. It can not only grasp a 15μm cell but also bring little interference to the environment. As a demonstration of the proposed manipulation method, the repeated experiments were conducted to explore the dependence of adhesion force on the grasping distance, which can be helpful in the improvement of successful rate. Finally, we achieved automatic cell assembly using Hela cells.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Domain Adaptation Regression for Force Calibration of Optical Tactile Sensors

arXiv

引用

arXiv 2024年

作者： Chen, Zhuo Ou, Ni Jiang, Jiaqi Luo, Shan Robot Perception Lab Centre for Robotics Research Department of Engineering King’s College London LondonWC2R 2LS United Kingdom State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-lab.led tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4% in full force range) for normal force, and 0.095N (6.3%) and 0.062N (4.1%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

TransForce: Transferable Force Prediction for Vision-based Tactile Sensors with Sequential Image Translation

arXiv

引用

arXiv 2024年

作者： Chen, Zhuo Ou, Ni Zhang, Xuyang Luo, Shan The Robot Perception Lab Centre for Robotics Research Department of Engineering King's College London LondonWC2R 2LS United Kingdom The State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

Vision-based tactile sensors (VBTSs) provide high-resolution tactile images crucial for robot in-hand manipulation. However, force sensing in VBTSs is underutilized due to the costly and time-intensive process of acquiring paired tactile images and force lab.ls. In this study, we introduce a transferable force prediction model, TransForce, designed to leverage collected image-force paired data for new sensors under varying illumination colors and marker patterns while improving the accuracy of predicted forces, especially in the shear direction. Our model effectively achieves translation of tactile images from the source domain to the target domain, ensuring that the generated tactile images reflect the illumination colors and marker patterns of the new sensors while accurately aligning the elastomer deformation observed in existing sensors, which is beneficial to force prediction of new sensors. As such, a recurrent force prediction model trained with generated sequential tactile images and existing force lab.ls is employed to estimate higher-accuracy forces for new sensors with lowest average errors of 0.69N (5.8% in full work range) in x-axis, 0.70N (5.8%) in y-axis, and 1.11N (6.9%) in z-axis compared with models trained with single images. The experimental results also reveal that pure marker modality is more helpful than the RGB modality in improving the accuracy of force in the shear direction, while the RGB modality show better performance in the normal direction. Copyright © 2024, The Authors. All rights reserved.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

Distributed Cooperative Attitude Tracking for Multiple Flexible Spacecraft under a Directed Graph

Distributed Cooperative Attitude Tracking for Multiple Flexi...

引用

第三十八届中国控制会议

作者： Lei Wang Zhuoyue Song Housheng Su Yiqun Zou Xiafei Tang State Key Laboratory of Intelligent Control and Decision of Complex Systems and School of Automation Beijing Institute of Technology School of Automation Huazhong University of Science and Technology School of Automation Central South University School of Electrical and Information Engineering Changsha University of Science and Technology

This paper is concerned with the problem of cooperative attitude tracking and vibration reduction for multiple flexible spacecraft without modal variable measurement under a directed communication topology. Firstly, a distributed attitude synchronization control law for MRPs representation is proposed in the absence of external disturbances, where the modal information is obtained using a modal variable estimator. To deal with a more practical case that the spacecraft are affected by external disturbances, the control law is further modified by integrating a disturbance observer and a feedforward compensating scheme,in which the lumped disturbances including the external disturbances and errors of the estimated modal information are observed and compensated in finite time. Under this enhanced control scheme, the attitude tracking errors and vibration variables will converge to zero even in the presence of external disturbances, and the controller is continuous and chattering-free. Besides,compared with the existing results, the communication graph in this paper is assumed to be directed and contain a spanning tree with the virtual leader as the root node. A numerical example is illustrated to demonstrate the effectiveness of the proposed results.

关键词： Attitude tracking Multiple flexible spacecraft Directed graph External disturbance

来源：评论

学校读者我要写书评

暂无评论

Event-triggered Observability: A Set-membership Perspective

arXiv

引用

arXiv 2022年

作者： Zheng, Kaikai Shi, Dawei Chen, Tongwen State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 1H9 Canada

This work attempts to discuss the observability of linear time-invariant systems with event-triggered measurements. A new notion of observability, namely, ǫ-observability is defined with parameter ǫ, which relates to the worst-case performance of inferring the initial state based on not only the received measurement but also the implicit information in the event-triggering conditions at no-event instants. A criterion is developed to test the proposed ǫ-observability of discrete-time linear systems, based on which an iterative event-triggered set-membership observer is designed to evaluate a set containing all possible values of the state. The proposed set-membership observer is designed as the outer approximation of the ellipsoids predicted based on previous state estimates and the ellipsoids inferred by fusing the received measurement and communication conditions, which is optimal in the sense of trace at each step and is proved to be asymptotically bounded. The efficiency of the proposed event-triggered set-membership state observer is verified by numerical experiments. © 2022, CC BY.

关键词： state estimation

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Disturbance Rejection controller for Artificial Pancreas

引用

IFAC-PapersOnLine 2020年第2期53卷 16372-16379页

作者： Deheng Cai Wei Liu Eyal Dassau Francis J. Doyle Iii Xiaoling Cai Junzheng Wang Linong Ji Dawei Shi State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing 100081 China Department of Endocrine and Metabolism Peking University People’s Hospital Beijing China. Harvard John A. Paulson School of Engineering and Applied Sciences Harvard University Cambridge MA 02138 USA.

Artificial pancreas (AP) systems are designed to automate glucose management for patients with type 1 diabetes. In this work, we propose an adaptive disturbance rejection control approach for AP systems to achieve safe and effective glucose regulation. The controller is built within the framework of active disturbance rejection control, but incorporates safety operation constraints, and glucose- and velocity-dependent parameter adaptation modules for the key control parameters. In silico performance comparison between the proposed controller and an adaptive zone model predictive controller (MPC) (Shi, Dassau, and Doyle III, 2019a) is conducted on the 10-adult cohort of the FDA-accepted UVA/Padova T1DM simulator. For both announced and unannounced meals, the controller achieves comparable glucose regulation performance in terms of mean glucose (134.9 mg/dL vs. 135.4 mg/dL, p < 0.001; 149.7 mg/dL vs. 151.7 mg/dL, p < 0.001, respectively) and percentage time in [70, 180] mg/dL (93.8% vs. 92.4%, p < 0.001; 76.0% vs. 72.4%, p < 0.001, respectively) without increasing the risk of hypoglycemia. The results indicate the feasibility of achieving comparable glucose regulation performance through a non-optimization control law for AP systems.

关键词： Artificial pancreas Active disturbance rejection control Adaptive control Glucose regulation

来源：评论

学校读者我要写书评

暂无评论

Dual adaptive control of bimanual manipulation with online fuzzy parameter tuning

Dual adaptive control of bimanual manipulation with online f...

引用

IEEE International Symposium on intelligent control (ISIC)

作者： Alex Smith Chenguang Yang Hongbin Ma Phil Culverhouse Angelo Cangelosi Etienne Burdet Center for Robotics and Neural Systems Plymouth University Devon UK Key Laboratory of Autonomous System and Network Control South China University of Technology Guangzhou P. R. China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing P. R. China Department of Bioengineering Imperial College London UK

A biomimetic controller with online adaptation of impedance and force is applied to a full kinematic and dynamic model of the Baxter bimanual robot. A set of fuzzy logic engines are proposed to infer the values of tuning gains which affect the control performance and control effort of the controller, which would conventionally be set to a static value based on expert knowledge of the controller; the aim of this being to avoid the use of arbitary values to set these values. A simulated experiment is carried out, where the Baxter robot is required to move an object through a trajectory while subjected to two different disturbance forces in four phases. The controller with fuzzy inferred control gains is compared against the same controller with fixed gains to gauge the effectiveness of the new method. Results show that fuzzy inference of control gains impart an improvement in both tracking error and control effort.

关键词： Trajectory Fuzzy logic Force Dynamics Mathematical model Manipulators

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：