检索结果-内蒙古大学图书馆

15th International Conference on Computer Science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous Information Technologies and Applications, CUTE 2023

作者： Zhang, Zhengshen Liu, Chenchen Wang, Haozhe Liu, Zhiyang Zhou, Lei Ang, Marcelo H. Lu, Wen Feng Tay, Francis Eng Hock Advanced Robotics Centre National University of Singapore Singapore117608 Singapore Integrative Sciences and Engineering Programme National University of Singapore Graduate School Singapore119077 Singapore

ISBN: (纸本)9789819724468

This paper presents an effective neural network, Residual Generative Grasping Convolutional Neural Network (ReGG-CNN), to predict reliable robotic grasps for novel objects based on an n-channel scene image. Based on Generative Grasping Convolutional Neural Network (GG-CNN) architecture, ReGG-CNN incorporates residual blocks to enhance performance while preserving the network’s lightweight and single-pass generative nature. ReGG-CNN is evaluated on two standard open-source datasets, Cornell and Jacquard grasping datasets, achieving 87% and 89% accuracy, respectively. Moreover, multiple cluttered scenes are created using novel household and adversarial objects to assess the model’s capability to generalize to most kinds of objects and make multi-grasp predictions. Even though only training on individual objects, ReGG-CNN effectively predicts grasps for diverse objects in cluttered scenes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Neural Network Model of Continuum Soft Robots Based on WaveNets Equipped with Adaptive IIR 21

Neural Network Model of Continuum Soft Robots Based on WaveN...

引用

21st International Conference on Electrical engineering, Computing Science and Automatic Control, CCE 2024

作者： Garcia-Castro, Oscar Federico Ramos-Velasco, Luis Enrique Parra-Vega, Vicente Garcia-Rodriguez, Rodolfo Vazquez-Garcia, Carlos Ernesto CINVESTAV-IPN Robotics and Advanced Manufacturing Coahuila Ramos Arizpe Mexico Universidad Politecnica Metropolitana Posgraduate Program of Aeroespace Engineering de Hidalgo Mexico CINVESTAV-IPN Robotics and Advanced Manufacturing Coahuila Mexico Universidad Autónoma de Coahuila Facultad de Ciencias de la Administración de Coahuila Mexico

ISBN: (纸本)9798350377545

Soft robots have attracted attention from many areas, such as robotics, materials, automatic control, and artificial intelligence. The particular class of continuum soft robot (cSR) is the most challenging given its highly nonlinear dynamics from the hyperviscoelasticity and varying stiffness, which arise from the modeling of an infinite conglomerate of particles enclosed in a deformable finite-dimensional body based on the lumped parameters assumption and the D' Alambert principle. The cSR is a complex model that presents a significant challenge in the field. Its nonintuitive structure, variable natural frequency, and parametric uncertainties, including its input matrix and lack of reliable velocity measurements, make it difficult to approximate its dynamics using only input and partial output data. This paper proposes a wavelet-based neural network (WaveNet) with an adaptive infinite impulse response (IIR) output filter. The WaveNet sweeps over modal frequencies, while the IIR enforces feedback and forward loops to propagate current and past neural outputs. The input shapes a controllable canonical output form. Simulations for a 2-degree-of-freedom CSR show that a bounded approximate modeling error is guaranteed at a low computational cost. © 2024 IEEE.

关键词： Impulse response

来源：评论

学校读者我要写书评

暂无评论

An integrated decision-making process for sustainable supplier selection and order allocation in the automotive industry 31

An integrated decision-making process for sustainable suppli...

引用

31st CIRP Conference on Life Cycle engineering, LCE 2024

作者： Ghadimi, Pezhman Sar, Kubra Azadnia, Amir Hossein Laboratory for Advanced Manufacturing Simulation and Robotics School of Mechanical & Materials Engineering University College Dublin Belfield Dublin Ireland School of Business Maynooth University Maynooth Ireland

A sustainable supplier selection problem can be concisely defined as a classical supplier selection problem that incorporates environmental and social criteria to select and monitor suppliers' performances, creating the sustainable supplier selection and order allocation (SSS&OA) problem. Finding the optimal order allocation to suppliers in the automotive industry is crucial as it can significantly improve the social, environmental, and economic performance of the whole supply chain. Therefore, this research aims to find an optimal order allocation plan for suppliers using an augmented ϵ-constraint optimization method in the automotive industry while considering all three dimensions of sustainability. Using a previously established comprehensive framework, this paper has adapted the solution approach of an existing bi-objective order allocation model that was used to make sourcing decisions. The results showed a higher total value of sustainable purchasing is achieved by the augmented ϵ-constraint optimization method compared to the traditional max-min method. © 2024 The Author(s).

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Editorial:special issue on frontiers of control and automation,dedicated to *** *** 60th birthday

引用

Control Theory and Technology 2023年第3期21卷 263-264页

作者： Jie Chen Jie Huang Lihua Xie Department of Control Science and Engineering Tongji UniversityShanghaiChina Department of Mechanical and Automation Engineering The Chinese University of Hong KongHong KongChina Center for Advanced Robotics Technology Innovation School of Electrical and Electronic EngineeringNanyang Technological UniversitySingaporeSingapore

It is our great pleasure and honor to organize this special issue"Frontiers of Control and Automation"in honor of the 60th birthday of our long-time colleague and friend Professor Ben *** Chen obtained his *** in mathemat-ics and computer science in 1983 from Xiamen University,China;*** in electrical engineering in 1988 from Gonzaga University,Spokane,Washington,USA;and *** in electrical and computer engineering in 1991 from Washington State University,Pullman,Washington,USA.

关键词： computer Xiamen frontier

来源：评论

学校读者我要写书评

暂无评论

Gene Regulatory Network Model for Adaptive Flocking Patterns of Multi-Agent Systems 14

Gene Regulatory Network Model for Adaptive Flocking Patterns...

引用

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

作者： Li, Wenji Chen, Chuangbin Wang, Zhaojun Guan, Chaotao Wang, Boxi Wang, Dongliang Zhuang, Jiafan Fan, Zhun College of Engineering Shantou University International Cooperation Base of Evolution Intelligence and Robotics of Guangdong Province Shantou515063 China Shenzhen Institute for Advanced Study UESTC China

ISBN: (纸本)9798331506056

In unknown environments, it's crucial for a multi-agent system to perceive changes in the surroundings and automatically adjust its flocking shapes. To address this need, our study proposes a formation control strategy based on Gene Regulatory Networks (named FC-GRN). The FC-GRN abstracts key elements in generating formation patterns, such as targets, obstacles, agents, and their neighbors, as different types of 'cells' and efficiently generates and adjusts flocking shapes by simulating dynamic interactions among them. The FC-GRN ensures all agents sensitively perceive environmental changes and adjust their positions in the formation accordingly, thus achieving adaptive flocking shapes. This enables the system to effectively prevent individual dispersion or detachment, enhancing overall cohesion. Simulation results clearly demonstrate that the the FC-GRN strategy allows agents to flexibly rearrange their positions based on environmental changes, effectively maintaining formation compactness and coherence. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Improved time-optimal B-spline feedrate scheduling for NURBS tool paths in CNC machining

引用

Advances in Manufacturing 2023年第1期11卷 111-129页

作者： Yang Li Fu-Sheng Liang Lei Lu Cheng Fan School of Mechanic Engineering Northeast Electric Power UniversityJilin132012JilinPeople’s Republic of China Jiangsu Provincial Key Laboratory of Advanced Robotics and Collaborative Innovation Center of Suzhou Nano Science and Technology College of Mechanical and Electrical EngineeringSoochow UniversitySuzhou215021JiangsuPeople’s Republic of China

Feedrate scheduling in computer numerical control(CNC)machining is of great importance to fully develop the capabilities of machine tools while maintaining the motion stability of each *** and time-optimal feedrate scheduling plays a critical role in improving the machining efficiency and precision of complex surfaces considering the irregular curvature characteristics of tool paths and the limited drive capacities of machine *** study develops a general feedrate scheduling method for non-uniform rational B-splines(NURBS)tool paths in CNC machining aiming at minimizing the total machining time without sacrificing the smoothness of feed *** feedrate profile is represented by a B-spline curve to flexibly adapt to the frequent acceleration and deceleration requirements of machining along complex tool *** time-optimal B-spline feedrate is produced by continuously increasing the control points sequentially from zero positions in the bidirectional scanning and sampling *** required number of knots for the time-optimal B-spline feedrate can be determined using a progressive knot insertion *** improve the computational efficiency,the B-spline feedrate profile is divided into a series of independent segments and the computation in each segment can be performed *** proposed feedrate scheduling method is capable of dealing with not only the geometry constraints but also high-order drive constraints for any complex tool path with little computational *** and machining experiments are conducted to verify the effectiveness and superiorities of the proposed method.

关键词： B-spline feedrate Non-uniform rational B-splines(NURBS)tool path Knot insertion Bidirectional scanning Computer numerical control(CNC)machining

来源：评论

学校读者我要写书评

暂无评论

Antilock Braking System on Industrial Heavy Vehicle Using PID-Based Bang-Bang Control 6

Antilock Braking System on Industrial Heavy Vehicle Using PI...

引用

6th International Conference on Control and robotics, ICCR 2024

作者： Darajat, Anisa Ulya Murdika, Umi Yuniati, Yetti Istiqphara, Swadexi Ferdous, Mohammad Farhan Universitas Lampung Dept. of Electrical Engineering Lampung Indonesia Institut Teknologi Sumatera Dept. of Electrical Engineering Lampung Indonesia Japan-Bangladesh Robotics and Advanced Technology Research Center Fukui Japan

ISBN: (纸本)9798331518158

This paper presents a PID-Based Bang-bang control system for controlling an Antilock Braking System (ABS) in heavy vehicles, simulated on a computer. ABS aims to prevent skidding incidents during sudden braking at both low and high speeds. ABS control using the PID-Based Bang-bang control method was tested with various variations of P, I, and D parameters to determine which parameter performs the best. The results of the four types of tests indicate that utilizing the Proportional and Derivative (PD)-Based Bang-bang control method effectively manages slip without oscillation and prevents skidding incidents. The time required to stop on both wheels is also faster compared to the other methods, namely 4.57 seconds with a stopping distance of 98.6 meters. © 2024 IEEE.

关键词： Bang bang control systems

来源：评论

学校读者我要写书评

暂无评论

Process planning and contour-based error compensation for precision grinding of miniature scalpels

引用

先进制造进展（英文版） 2024年第1期12卷 108-123页

作者： Cheng Fan Cao-Yang Xue Jun Zhao Wei Jiang Wen-Ge Han Lei Zhang Li-Ning Sun Jiangsu Provincial Key Laboratory of Advanced Robotics School of Mechanical and Electrical EngineeringSoochow UniversitySuzhou 215021JiangsuPeople's Republic of China Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical and Electrical EngineeringZhejiang UniversityHangzhou 310027People's Republic of China State Key Laboratory of Intelligent Equipment and Manufacturing School of Mechanical EngineeringZhejiang University of TechnologyHangzhou 310023People's Republic of China

Miniature scalpels are mainly used in microsur-geries such as ophthalmic and cardiovascular *** size of a miniature scalpel is only a few millimeters,and the precision of the blade shape is high,which makes pro-duction of miniature scalpels extremely *** study proposes a new sharpening process for grinding miniature scalpels on a four-axis machine tool.A post-processing algo-rithm for a four-axis grinding machine based on a kinemat-ics model is *** then propose a corresponding parameter calibration method for the parameters used in the kinematics *** of possible errors in the param-eter calibration,a contour-based error compensation method is proposed for accurate adjustments to the edge shape fol-lowing *** can solve the problem of large devia-tions between the actual edge shape after grinding and the ideal edge *** effectiveness of the proposed process planning and error compensation method is verified experi-mentally,and the grinding process parameters of the minia-ture scalpel are optimized to improve its surface processing *** sharpness of the optimized miniature scalpel is less than 0.75 N,and the blade shape is symmetrical,which meets the technical requirements of miniature scalpels.

关键词： Miniature scalpel Sharpening Kinematics Error compensation Grinding

来源：评论

学校读者我要写书评

暂无评论

Robotic grasp detection toward unknown objects using 3D edge detection and Gaussian mixture model for clustering candidates

Robotic grasp detection toward unknown objects using 3D edge...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Shimotori, Haruki Jiang, Ping Ooga, Junichiro Sugahara, Atsushi Ito, Shun Koike, Atsuya Ueda, Ryuichi Chiba Institute of Technology Faculty of Advanced Engineering Department of Advanced Robotics 2-17-1 Tsudanuma Chiba Narashino Japan Toshiba Corporate Manufacturing Engineering Center Shin-Isogo-Cho Isogo-ku Yokohama Japan

ISBN: (纸本)9798350325706

We propose a novel grasp detection method for arbitrary shape objects. This method is applicable to multijoint manipulators with a two-finger hand and an RGB-D hand-eye camera. When a robot tries to grasp an unknown object with a camera as the only sensor, it must choose a position to grasp without mass distribution information. Moreover, even if the robot can find some candidates of locations for grasping, some of them will be false due to noise. The proposed method chooses an appropriate candidate by variational Bayesian clustering. In the clustering, the candidates are classified based on their closeness. Then the method chooses one existing at the center of the largest cluster since it may be uninfluenced by noise. This set of procedures does not require training unlike learning methods. The proposed method is evaluated with an actual robot. Though the method is a heuristic, it can choose suitable grasping locations from piles of objects. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Strain sensor on a chip for quantifying the magnitudes of tensile stress on cells

引用

Microsystems & Nanoengineering 2024年第3期10卷 305-315页

作者： Yuyin Zhang Yue Wang Hongze Yin Jiahao Wang Na Liu Songyi Zhong Long Li Quan Zhang Tao Yue School of Mechatronics Engineering and Automation Shanghai UniversityShanghaiChina School of Future Technology Shanghai UniversityShanghaiChina Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical EngineeringZhejiang UniversityHangzhouChina Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai UniversityShanghaiChina Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghaiChina

During cardiac development,mechanotransduction from the in vivo microenvironment modulates cardiomyocyte growth in terms of the number,area,and arrangement ***,the response of cells to different degrees of mechanical stimuli is ***-on-a-chip,as a platform for investigating mechanical stress stimuli in cellular mimicry of the in vivo microenvironment,is limited by the lack of ability to accurately quantify externally induced ***,previous technology lacks the integration of external stimuli and feedback sensors in microfluidic platforms to obtain and apply precise amounts of external ***,we designed a cell stretching platform with an in-situ *** in-situ liquid metal sensors can accurately measure the mechanical stimulation caused by the deformation of the vacuum cavity exerted on *** platform was applied to human cardiomyocytes(AC16)under cyclic strain(5%,10%,15%,20 and 25%),and we found that cyclic strain promoted cell growth induced the arrangement of cells on the membrane to gradually unify,and stabilized the cells at 15%amplitude,which was even more effective after 3 days of *** platform’s precise control and measurement of mechanical forces can be used to establish more accurate in vitro microenvironmental models for disease modeling and therapeutic research.

关键词： stress deformation arrangement

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：