检索结果-内蒙古大学图书馆

The hydrodynamics of self-rolling locomotion driven by the flexible pectoral fins of 3-D bionic dolphin

Journal of Ocean engineering and Science 2022年第1期7卷 29-40页

作者： Zhihan Li Dan Xia Xufeng Zhou Jiabo Cao Weishan Chen Xingsong Wang School of Mechanical Engineering Southeast UniversityNanjing 211189China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080China

The novel autonomous rolling performance is realized by the pair of pectoral fins of a three-dimensional(3-D)bionic dolphin in this paper numerically.3-D Navier-Stokes equations are employed to simulate the viscous fluid around the bionic *** effect of self-rolling manoeuvrability is ex-plored using the dynamic mesh technology and user-defined function(UDF).By varying the parameter ratios,the interaction of flexible pectoral fins is divided into two motion modes,amplitude differential and frequency differential *** the primary driving source,the differential motion of a pair of pec-toral fins can effectively provide the rolling torque,and the trajectory of the entire rolling process is approximately the clockwise *** results demonstrate that the rolling angular velocity and driving torque in the steady state can be improved by increasing parameter ratios,and the rolling efficiency can reach the maximum under the optimal parameter ***,different parameter ratios do not af-fect the rolling radius of the self-rolling *** evolution process around the pair of pectoral fins is shown by the flow structures in self-rolling swimming,reasonably revealing that self-rolling locomotion is produced by the pressure and wake vortices surrounding the pair of pectoral fins,and the wake struc-tures depend primarily on the variation of parameter *** properly turns out that the application of the pair of pectoral fins can realize the self-rolling performance through parameter differential modes.

关键词： Self-rolling dolphin Parameter differential mode Numerical simulation Hydrodynamic performance Flow structures

来源：评论

学校读者我要写书评

暂无评论

An MLP-CycleGAN-based data-driven model for soft dielectric elastomer actuators with minimal Sim2Real gap

引用

Science China Technological Sciences 2025年第7期 89-100页

作者： Xiazhi HU Huangwei JI Xiongfei FENG Jianing WU Kai LUO Xiangyang ZHU Feifei CHEN Robotics Institute School of Mechanical EngineeringShanghai Jiao Tong University State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University School of Materials Science and Engineering Huazhong University of Science and Technology Meta Robotics Institute Shanghai Jiao Tong University

Model-guided design of dielectric elastomer actuators（DEAs） is essential for enabling their application in soft robotics. However, current modeling methods primarily rely on the finite element method（FEM）, which suffers from low computational efficiency. Additionally, the simulation-to-reality（Sim2Real） gap, mainly arising from variations in material properties and manufacturing processes, poses a significant challenge. In this work, we propose a data-driven modeling framework aimed at accurately and rapidly predicting voltage-induced displacements while minimizing the Sim2Real gap. The framework integrates a multi-layer perceptron（MLP） model, which serves as a computationally efficient surrogate for the FEM model, and a cycle-generative adversarial network（CycleGAN） model, which mitigates the Sim2Real gap by leveraging adversarial learning to process both simulation and experimental data. Dimensional analysis is performed to extend the framework's applicability across different DEA scales. The surrogate model delivers global predictions in just 0.8 s, achieving linear coefficients of determination（R2） of 0.99106 for release distance prediction and 0.99375 for actuation distance prediction compared to experimental results. Our model can quickly identify the feasible range of biaxial prestretch ratios required for generating the desired deformation, thereby streamlining the design process. Finally, a soft robotic gripper is designed and fabricated, demonstrating versatile object-grasping capabilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

General closed-form inverse kinematics for arbitrary three-joint subproblems based on the product of exponential model

引用

Frontiers of Mechanical engineering 2022年第2期17卷 85-101页

作者： Tao SONG Bo PAN Guojun NIU Jiawen YAN Yili FU State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China School of Mechanical Engineering and Automation Zhejiang Sci-Tech UniversityHangzhou 310018China

The inverse kinematics problems of robots are usually decomposed into several Paden–Kahan subproblems based on the product of exponential model. However, the simple combination of subproblems cannot solve all the inverse kinematics problems, and there is no common approach to solve arbitrary three-joint subproblems in an arbitrary postural relationship. The novel algebraic geometric (NAG) methods that obtain the general closed-form inverse kinematics for all types of three-joint subproblems are presented in this paper. The geometric and algebraic constraints are used as the conditions precedent to solve the inverse kinematics of three-joint subproblems. The NAG methods can be applied in the inverse kinematics of three-joint subproblems in an arbitrary postural relationship. The inverse kinematics simulations of all three-joint subproblems are implemented, and simulation results indicating that the inverse solutions are consistent with the given joint angles validate the general closed-form inverse kinematics. Huaque III minimally invasive surgical robot is used as the experimental platform for the simulation, and a master–slave tracking experiment is conducted to verify the NAG methods. The simulation result shows the inverse solutions and six sets given joint angles are consistent. Additionally, the mean and maximum of the master–slave tracking experiment for the closed-form solution are 0.1486 and 0.4777 mm, respectively, while the mean and maximum of the master–slave tracking experiment for the compensation method are 0.3188 and 0.6394 mm, respectively. The experiments results demonstrate that the closed-form solution is superior to the compensation method. The results verify the proposed general closed-form inverse kinematics based on the NAG methods.

关键词： inverse kinematics Paden-Kahan subproblems three-joint subproblems product of exponential closed-form solution

来源：评论

学校读者我要写书评

暂无评论

Synergistic control of soft robotic hands for human-like grasp postures

引用

Science China(Technological Sciences) 2022年第3期65卷 553-568页

作者： ZHANG NingBin ZHAO Yi GU GuoYing ZHU XiangYang Robotics Institute School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghai 200240China

Although significant advances in the design of soft robotic hands have been made to mimic the structure of the human hands,there are great challenges to control them for coordinated and human-like *** on the principle of postural synergies in the human hand,we present a synergistic approach for coordinated control of a soft robotic hand to replicate the human-like grasp *** this end,we firstly develop a kinematic model to describe the control variables and the various postures of the soft robotic *** on the postural synergies,we use the developed model and Principal Component Analysis(PCA)method to describe the various postures of the soft robotic hand in a low-dimensional space formed by the synergies of actuator ***,the coordinates of these synergies can be used as low-dimensional control inputs for the soft robotic hand with a higher-dimensional postural ***,we establish an experimental platform on a customized soft robotic hand with6 pneumatical actuators to verify the effectiveness of the *** results demonstrate that with only a 2-dimensional control input,the soft robotic hand can reliably replicate 30 grasp postures in the Feix taxonomy of the human hand.

关键词： soft robotic hand synergistic control human-like grasp postures principal component analysis pneumatic actuation

来源：评论

学校读者我要写书评

暂无评论

Swarming magnetic photonic-crystal microrobots withon-the-fly visual pH detection and self-regulated drug delivery

引用

InfoMat 2023年第10期5卷 64-79页

作者： Zheng Yu Luolin Li Fangzhi Mou Shimin Yu Di Zhang Manyi Yang Qing Zhao Huiru Ma Wei Luo Tianlong Li Jianguo Guan State Key Laboratory of Advanced Technology for Materials Synthesis and Processing International School of Materials Science and Engineering Wuhan University of TechnologyWuhanthe People's Republic of China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbinthe People's Republic of China Wuhan Institute of Photochemistry and Technology Wuhanthe People's Republic of China

Swarming magnetic micro/nanorobots hold great promise for biomedical applications,but at present suffer from inferior capabilities to perceive and respond to chemical signals in local *** we demonstrate swarming magnetic photonic crystal microrobots(PC-bots)capable of sponta-neously performing on-the-fly visual pH detection and self regulated drug delivery by perceiving local pH *** magnetic PC-bots consist of pH-responsive hydrogel microspheres with encapsulated one-dimensional periodic assemblies of Fe3O4 *** programming extemnal rotating magnetic fields,they can self-organize into large swarms with much-enhanced collective velocity to actively find targets while shining bright“blinking”structural *** approaching the target with abnormal pH conditions(*** ulcerated superficial tumor lesion),the PC-bots can visualize local pH changes on the fly via pH-responsive structural colors,and realize self-regulated release of the loaded drugs by recognizing local *** work facilita tes the develop-ment of intelligent micro/nanorobots for active“motile-targeting”tumor diag-nosis and treatment.

关键词： collective behaviors drug delivery micro/nanorobots on-the-fly sensing responsivephotonic crystals

来源：评论

学校读者我要写书评

暂无评论

Hydrodynamics study of dolphin’s self-yaw motion realized by spanwise flexibility of caudal fin

引用

Journal of Ocean engineering and Science 2022年第3期7卷 213-224页

作者： Zhihan Li Dan Xia Jiabo Cao Weishan Chen Xingsong Wang School of Mechanical Engineering Southeast UniversityNanjingJiangsu 211189China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080China

The hydrodynamic performance of the virtual underwater vehicle under self-yaw is investigated numerically in this paper,we aim to explore the fluid laws behind this plane motion achieved by the bionic flexibility,especially the spanwise flexibility of the caudal *** kinematics of the chordwise flexible body and the spanwise flexible caudal fin are explored through dynamic mesh technology and user-defined functions(UDF).The 3-D Navier-Stokes equations are applied to simulate the viscid fluid surrounding the bionic *** study focuses on quantitative problems about the fluid dynamics behind the specific motion law,including speed of movement,energy loss and working *** current results show that the self-yaw can be composed of two motions,autonomous propulsion and active *** addition,the degree of the flexible caudal fin can produce different yaw *** chordwise phase differenceФis dominant in the propulsion function,while the spanwise phase differenceδhas a more noticeable effect on the steering *** pressure distribution on the surface of the dolphin and the wake vortex generated in the flow field reasonably reveal the evolution of *** properly turns out that the dolphin can combine the spanwise flexible caudal fin and the chordwise flexible body to achieve self-yaw motion.

关键词： Self-yaw dolphin Spanwise flexibility Caudal fin Numerical simulation Hydrodynamic performance

来源：评论

学校读者我要写书评

暂无评论

Towards semi-supervised myoelectric finger motion recognition based on spatial motor units activation

引用

Science China(Technological Sciences) 2022年第6期65卷 1232-1242页

作者： GUO WeiChao WANG Mian SHENG XinJun ZHU XiangYang State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Meta Robotics Institute Shanghai Jiao Tong UniversityShanghai 200240China

It is vital to recognize the intention of finger motions for human-machine interaction(HMI).The latest research focuses on fine myoelectric control through the decoding of neural motor unit action potential trains(MUAPt) from high-density surface electromyographic(sEMG) ***,the existing EMG decoding algorithms rarely obtain the spatial matching relationship between decoded motion units(MU) and designated muscles,and the control interface can only recognize the trained hand *** this study,a semi-supervised HMI based on MU-muscle matching(MMM) is proposed to recognize individual finger motions and even the untrained combined multi-finger *** automatic channel selection from high-density s EMG signals,the optimal spatial positions to monitor the MU activation of finger muscles are *** tapping experiment is carried out on ten subjects,and the experimental results show that the proposed s EMG decomposition algorithm based on MMM can accurately identify single finger motions with an accuracy of 93.1%±1.4%,which is comparable to that of state-of-the-art pattern recognition ***,the MMM allows unsupervised recognizing the untrained combined multi-finger motions with an accuracy of 73%±3.8%.The outcomes of this study benefit the practical applications of HMI,such as controlling prosthetic hand and virtual keyboard.

关键词： myoelectric control semi-supervised motor units activation channel selection template matching

来源：评论

学校读者我要写书评

暂无评论

Piezoelectric inertial robot for operating in small pipelines based on stick-slip mechanism:modeling and experiment

引用

Frontiers of Mechanical engineering 2022年第3期17卷 109-124页

作者： Jichun XING Chao NING Yingxiang LIU Ian HOWARD School of Mechanical Engineering Yanshan UniversityQinhuangdao066004China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150001China School of Civil and Mechanical Engineering Curtin UniversityPerth6001Australia

Small pipes exist in industrial and biomedical fields,and require microrobots with high operational precision and large load capacity to inspect or perform functional tasks.A piezoelectric inertial pipeline robot using a“stick-slip”mechanism was proposed to address this *** this study,the driving principle of the proposed robot was analyzed,and the strategy of the design scheme was presented.A dynamics model of the stick-slip system was established by combining the dynamics model of the driving foot system and the LuGre friction model,and the simulation analysis of the effect of system parameters on the operating trajectory was *** experimental system was established to examine the output characteristics of the proposed *** results show that the proposed pipeline robot with inertial stick-slip mechanism has a great load capacity of carrying 4.6 times(70 g)its own mass and high positioning *** speed of the pipeline robot can reach up to 3.5 mm/s(3 mm/s)in the forward(backward)direction,with a minimum step distance of 4µ*** potential application for fine operation in the pipe is exhibited by a demonstration of contactless transport.

关键词： pipeline robot piezoelectric inertial drive stick-slip large load capacity dynamics model small pipeline

来源：评论

学校读者我要写书评

暂无评论

Full Resolution Repetition Counting 16th

Full Resolution Repetition Counting

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Li, Jianing Chen, Bowen Wang, Zhiyong Liu, Honghai School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819964826

Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetitions regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. Besides, temporal self-similarity matrix is used in our model to represent the correlation of action, which contains much cycle information in time series. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal resolution. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based model for automated STN localization using local field potentials in Parkinson’s disease

引用

Soft Computing 2025年第4期29卷 2343-2362页

作者： Hosny, Mohamed Naeem, Mohamed A. Zhu, Minwei Gao, Wenpeng Elshenhab, Ahmed M. Fu, Yili Department of Electrical Engineering Benha Faculty of Engineering Benha University Benha Egypt State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin150080 China Department of Mechatronics and Robotics Engineering Faculty of Engineering South Valley University Qena Egypt First Affiliated Hospital Harbin Medical University Harbin150001 China School of Life Science and Technology Harbin Institute of Technology Harbin150080 China Department of Mathematics Faculty of Science Mansoura University Mansoura35516 Egypt

Accurate identification of the subthalamic nucleus (STN) borders is time-consuming, relying heavily on the neurosurgeon expertise in manually interpreting the electrophysiological signals. Local field potentials (LFPs) have garnered imperative attention due to their strong correlation with the STN. However, existing detection models often face challenges with high computational complexity, hyperparameter optimization and lack of explainability, making them unreliable for clinicians. Therefore, this study introduces an explanatory framework using convolutional neural networks (CNN) for detecting the STN region from LFPs. Continuous wavelet transform is employed to convert LFPs signals into scalogram images, which are then processed by sixteen CNN models. We evaluated our framework by examining the impact of various limiting factors on the classification performance, including model size, learning rate (LR), optimizers and data scaling. Deep features are extracted from the top-performing CNN architectures to capture rich representations of the scalograms. These features are then fused and classified using k-nearest neighbour algorithm. Gradient-weighted class activation mapping is used to explain the decisions made by the proposed model. Our approach achieved an accuracy of 99.61%, outperforming individual CNN models for STN localization. The experimental results revealed that CNN models, embedded with additional hyperparameters and layers, generally outperformed smaller models. Besides, low LR significantly enhanced the performance compared to high LR. Moreover, features extracted from untuned networks produced lower performance than tuned networks. The proposed system could revolutionize deep brain stimulation surgery by increasing efficiency and reducing reliance on clinician expertise for STN detection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Wavelet transforms

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

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

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：