检索结果-内蒙古大学图书馆

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

作者： Zhang, Zhongxin Yu, Bin Wang, Jinbao Song, Jingke Wei, Jun School of Mechanical Engineering Hebei University of Technology Tianjin300401 China Intelligent Rehabilitation Device and Detection Technology Engineering Research Center of the Ministry of Education Tianjin300130 China Key Laboratory of Robot Perception and Human–Machine Fusion Hebei Province Tianjin300130 China

ISBN: (纸本)9789819965007

The occurrence of diseases and accidental damage cause many people to have knee motion dysfunction, the synthesis design of the knee joint rehabilitation mechanism is of great significance. This paper proposes a new 4 DOF (degree-of-freedom) motion equivalent model of knee joint, and the limb synthesis and configuration synthesis of 4 DOF parallel rehabilitation mechanism of knee joint are carried out. Firstly, according to the physiological characteristics of the knee joint and the three non-negligible motion characteristics of the knee joint, a 4 DOF motion equivalent model of the knee joint that is more in line with the knee joint motion is obtained, and the motion screw system and constraint screw system of this model are obtained, Configuration synthesis conditions are proposed. Second, the type of limb constraint is obtained according to the configuration synthesis conditions, and the limb synthesis is carried out by using screw correlation and reciprocity. Finally, the constraint types of the moving platform are classified by using the constraint screw multiple set theory, and the configuration synthesis of each type is carried out, a large number of knee joint 4 DOF parallel rehabilitation mechanisms that meet the requirements are obtained. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Screws

来源：评论

学校读者我要写书评

暂无评论

Elastic Collision Based-Interactive Path Planning System for Vascular Intervention robots

Elastic Collision Based-Interactive Path Planning System for...

引用

International Conference on Biomimetic Intelligence and robotics & Medical robotics Forum, ICBIR+MRF 2024

作者： Cao, Sheng Guo, Shuxiang Guo, Jian Wang, Jian Wang, Bin Ding, Mingchao Aerospace Center Hospital The Key Laboratory of Convergence Medical Engineering System and Healthcare Technology School of Life Science Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China Shenzhen Institute of Advanced Biomedical Robot Company Limited Guangdong Province Shenzhen518000 China Department of Electronic and Electrical Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

As population aging intensifies, the incidence of cardiovascular and cerebrovascular diseases has continued to rise. Vascular interventional surgery, known for its minimal trauma, rapid recovery, and clear effectiveness, requires doctors to perform procedures in radiation environments while wearing lead aprons. The advent of vascular intervention robots has provided a system-level solution to protect doctors from radiation and enhance outcomes. Currently, preoperative path planning for these robots predominantly relies on automatically generated paths, calculated by setting constraints and minimizing costs. However, this method lacks incorporation of physicians' expertise and consideration of elastic collision. Therefore, this study has designed an interactive path planning system for vascular intervention robot based on elastic collision. By establishing a simulation environment, doctors can use a manipulator to control virtual catheters and guidewires. While considering deformations, they maneuver the guidewire to the target position and record the current motion trajectory to guide the procedure in actual surgeries. Experimental tests have been conducted, confirming the system's effectiveness and feasibility. © 2024 The Authors.

关键词： robot programming

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition of sEMG Based on Res-LSTM 17th

Gesture Recognition of sEMG Based on Res-LSTM

引用

17th International Conference on Intelligent robotics and Applications, ICIRA 2024

作者： Zhao, Yujia Zou, Chunlong Yun, Juntong Jiang, Du Huang, Li Liu, Ying Jiang, Guozhang Xie, Yuanmin Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430081 China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

sEMG (surface electromyography) signal control of bionic prostheses has been widely studied over the past few years. In particular, sparse sEMG signals are rapidly developing in the field of gesture recognition for their convenience, noninvasiveness, and ease of access. However, compared with high-density EMG signals, sparse EMG signals lack rich feature information, which in turn affects gesture recognition accuracy. In order to reduce the loss of feature information of sparse EMG signals in the spatio-temporal dimension, this paper proposes a hybrid neural network Res-LSTM combining residual network and long short-term memory network. The ordinary convolutional blocks in the CNN network are replaced with residual blocks, and the final fully connected layer is removed and a constant mapping layer is added to adequate extraction of spatial feature information of the data. The Res layer’s output is utilized as the input for the long and short-term memory (LSTM) network, which further extracts the features of the data in the temporal dimension, and finally completes the categorization output through a fully connected layer. The average accuracy of 91.11% for gesture-motion classification was verified by training on a homebrew dataset;and tested on a public dataset, NinaPro DB1, with an average accuracy of 91.03%. The experimental findings indicate that the proposed Res-LSTM network framework contributes to solving the problem of lack of feature information of sparse sEMG signals and improves the pattern recognition accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-branch low-light enhancement algorithm based on spatial transformation

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Wang, Wenlu Sun, Ying Zou, Chunlong Tang, Dalai Fang, Zifan Tao, Bo Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot010051 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Hydroelectric Design & amp Maintenance China Three Gorges University Yichang443002 China

Many state-of-the-art low-light image enhancement techniques now suffer from issues like color distortion, detail blurring, and the halo effect, hindering their ability to produce visual effects. This paper presents a multi-branch low-light enhancement algorithm based on spatial transformation to significantly improve the visual impact of images under low-light settings, overcoming the limitations of existing approaches. The process involves dividing the initial low-light picture into three distinct layers. Bootstrap filtering and Contrast Limited Adaptive Histogram Equalization are used to process the main feature layer. Primary feature extraction is used to extract features for the compensation layer, which is then integrated with Contrast Limited Adaptive Histogram Equalization and MSRCR. The auxiliary layer utilizes spatial transformation to apply gamma correction to the V-channel and performs color space transformation and additional processing. Ultimately, these three layers are combined and refined to create the final improved image. Based on the experimental results, the proposed method outperforms the standard MSRCR algorithm by 52.47%, 71.58%, and 12.10%, respectively, on the assessment metrics AG, SD, and IE. LOE declines by 22.3%. The processed image presents a good visual quality, effectively enhancing the image brightness while retaining a large amount of information and improving the image details. This paper proposes an effective method to deal with the problem of low illumination image enhancement, which provides a strong reference for future research and application in related fields. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Motion Controller based on NN-ARX and ARMAX Actuator Identification for 3-DoF Delta Parallel robot 11

Experimental Study on Motion Controller based on NN-ARX and ...

引用

11th RSI International Conference on robotics and Mechatronics, ICRoM 2023

作者： Jalali, Hasan Damavandi, Hossein Kalhor, Ahmad Masouleh, Mehdi Tale University of Tehran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering Tehran Iran Sadjad University Faculty of Computer Engineering and Information Technology Mashhad Iran University of Tehran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9798350308105

Today, system identification plays a pivotal role in control science and offering a myriad of applications. This paper places its focus on the identification of actuator models within real-world delta robots for informing controller design. Two identification methods, namely NN-ARX and ARMAX, have been employed to extract the dynamic characteristics of the robot actuators, resulting in dynamic models of these integral components being derived. These dynamic models have been utilized in simulations for controller design, and due to the disparities in the identification models, distinct controllers have been realized. Subsequently, these controllers have been practically implemented on delta robots, and their performances have been subjected to a comprehensive comparative analysis. The results demonstrate that controllers integrating the identified actuator models outperformed those designed without the incorporation of the identification models. In practice, the implementation of controllers based on NN-ARX yielded the most favorable results among all the tested controllers. This research not only underscores the importance of accurate actuator models in control system design but also highlights the superior performance of neural network-based controllers in real-world robotic applications. In particular, the practical results of NN-ARX-based controllers were able to achieve significantly lower RMSE of 2.3562, 1.9531, and 2.1185 for the three motors, respectively, as opposed to the 4.1369, 3.0125, and 3.0363 achieved by the ARMAX-based controllers. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Mobilenetv2-SSD Target Detection Method Based on Multi-scale Feature Fusion 8th

Mobilenetv2-SSD Target Detection Method Based on Multi-scale...

引用

8th International Conference on cognitive Systems and Information Processing, ICCSIP 2023

作者： Li, Boao Jiang, Du Tang, Xinjie Sun, Ying Weng, Yaoqing Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China Hubei Longzhong Laboratory Hubei Xiangyang441000 China

ISBN: (纸本)9789819980208

Most of the deep learning networks used in target detection algorithms are very complex, which poses difficulties for edge devices with limited storage capacity and computing power, such as mobile terminals. A MobileNetv2-SSD target detection algorithm based on multi-scale feature fusion is proposed in this paper. We use MobileNetv2 to improve the SSD algorithm by replacing the original network’s backbone network VGG16 with the lightweight network MobileNetv2 to perform the model streamlining. The problem of accuracy loss due to model compression is improved by the designed feature fusion module and finally tested on the dataset. The experimental results show that the mAP and FPS are 90.37% and 50FPS, respectively, and the detection accuracy is improved by 3.24% compared with the original SSD network, the detection speed is 1.9 times of the original one, and the size of the model is only 28.5M, which is only 30.5% of the original model. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Configuration Design and Kinematic Performance Analysis of a Novel 4-DOF Parallel Ankle Rehabilitation Mechanism with Two Virtual Motion centers

引用

Chinese Journal of Mechanical engineering 2023年第6期36卷 87-104页

作者： Jingke Song Jun Wei Bin Yu Chenglei Liu Cunjin Ai Jianjun Zhang School of Mechanical Engineering Hebei University of TechnologyTianjin 300401China Hebei Provincial Key Laboratory of Robot Perception and Human-Machine Fusion Tianjin 300130China Intelligent Rehabilitation Device and Detection Technology Engineering Research Center of the Ministry of Education Tianjin 300130China

Aiming at the problem that the existing ankle rehabilitation robot is difficult to fully fit the complex motion of human ankle joint and has poor human-machine motion compatibility,an equivalent series mechanism model that is highly matched with the actual bone structure of the human ankle joint is proposed and mapped into a parallel rehabilita-tion *** parallel rehabilitation mechanism has two virtual motion centers(VMCs),which can simulate the complex motion of the ankle joint,adapt to the individual differences of various patients,and can meet the reha-bilitation needs of both left and right feet of ***,based on the motion properties and physiological structure of the human ankle joint,the mapping relationship between the rehabilitation mechanism and ankle joint is determined,and the series equivalent model of the ankle joint is *** to the kinematic and con-straint properties of the ankle equivalent model,the configuration design of the parallel ankle rehabilitation robot is carried ***,according to the intersecting motion planes theory,the full-cycle mobility of the mechanism is proved,and the continuous axis of the mechanism is judged based on the constraint power and its ***,the kinematics of the parallel ankle rehabilitation robot is ***,based on the OpenSim biomechanical soft-ware,a human-machine coupling rehabilitation simulation model is established to evaluate the rehabilitation effect,which lays the foundation for the formulation of a rehabilitation strategy for the later prototype.

关键词： Ankle rehabilitation robot Double-VMCs mechanism Kinematic performance Human-machine rehabilitation simulation

来源：评论

学校读者我要写书评

暂无评论

Admittance Based robot Force Control Framework for Server Board Assembly 25

Admittance Based Robot Force Control Framework for Server Bo...

引用

25th IEEE International Conference on Industrial technology, ICIT 2024

作者： Ma, Yunlong Wang, Yaonan Jiang, Yiming Zhou, Xianen Zhu, Ge Zhu, Qing Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China Xiangjiang Laboratory Hunan China College of Electrical and Information Engineering Hunan University Changsha China School of Robotics Hunan University Changsha China National Engineering Research Center for Robot Vision Perception and Control Technology Hunan University Changsha China ZTE Corporation Shenzhen China

In server board assembly tasks, the effect of vision-based robot assembly schemes is not ideal due to the small installation gap and the blocking of vision. Adding force sensors and force controllers can be a good solution to the above problems and increase the flexibility in the assembly process. In this paper, we propose a force control strategy applied to a server board assembly task. The method is divided into two main parts. In the first part, the zero offset of the force sensor and the load gravity are calibrated and compensated, so that the external force on the load is accurately obtained. In the second part, the admittance controller is designed to achieve compliant behavior between the robot and the environment. Finally, the experimental verification of the board insertion is carried out on the experimental platform. Experimental results verify the effectiveness and practicability of the proposed method. © 2024 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

MorNet: Asymmetric UNet-like Network with Morphological Opening and Closing for Image Segmentation 17th

MorNet: Asymmetric UNet-like Network with Morphological Open...

引用

17th International Conference on Intelligent robotics and Applications, ICIRA 2024

作者： Li, Meng Yun, Juntong Jiang, Du Tao, Bo Li, Gongfa Liu, Rong Liu, Ying Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China School of Medicine Wuhan University of Science and Technology No. 1 Huangjia Lake University Town Wuhan430065 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

Image segmentation plays a crucial role in target recognition as it provides an essential prerequisite for identifying targets. However, UNet cannot acquire comprehensive information about the image, which limits its ability to effectively segment small and discrete objects. A new network structure, called MorNet, is proposed. It applies dilation and erosion operations in morphological opening and closing for connected and discrete region segmentation. MorNet effectively integrates global segmentation images, emphasizing small and discrete area segmentation and enhancing the segmentation of large continuous areas. This method enhances the understanding of the location of organs and diseased sites, enabling accurate segmentation. A side-out (SO) monitoring mechanism is introduced into the decoder to provide monitoring information for the original image and the predicted results. Compared with current UNet-like networks, our proposed method achieved the highest Dice scores (96.4635%, 94.0514%, 94.3444%) and PPV scores (94.2226%, 90.2361%, 91.5582%) for liver tumor, brain tumor, and liver segmentation tasks, respectively. The experimental results show that MorNet successfully combines the segmentation of connected and discrete regions. MorNet locates organs and lesions more accurately than current state-of-the-art medical image segmentation models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on the Process-based Generation Method of Multi-ships Collision Avoidance Test Scenarios Database for Maritime Autonomous Surface Ships 33rd

Research on the Process-based Generation Method of Multi-shi...

引用

33rd International Ocean and Polar engineering Conference, ISOPE 2023

作者： Wang, Xinyu Wang, Yihang Bian, Hui Ma, Jilin Zhao, Xuan Qinhuangdao Branch China Classification Society Hebei China School of Mechanical Engineering Yanshan University Hebei China Parallel Robot and Mechatronic System Laboratory Hebei Province Hebei China Key Laboratory of Advanced Forging & Stamping Technology and Science Hebei China Science & Technology Innovation and Test Center Beijing China

ISBN: (纸本)9781880653807

This paper proposes a process-based method for generating virtual test scenarios for near-shore maritime autonomous surface ships (MASS) collision avoidance tests. The method includes a scenario complexity index to provide different difficulty levels of virtual test scenarios for different test requirements, reducing the test volume while ensuring coverage and reliability requirements. The scenario database generated by this method reflects the frequency of real-world scenarios and meets the requirements of virtual test realism. This method can improve the efficiency and reliability of MASS testing, with potential future improvements in the complexity evaluation matrix and statistical analysis of vessel maneuvering ability. © 2023 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： Ships

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：