检索结果-内蒙古大学图书馆

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Tian, Wei Guo, Jian Guo, Shuxiang Fu, Qiang Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Intelligent Robot Laboratory Binshui Xidao Extension 391 Tianjin300384 China Shenzhen Institute of Advanced Biomedical Robot Co. Ltd. No.12 Ganli Sixth Road Jihua Street Longgang District Shenzhen518100 China Beijing Institute of Technology Key Laboratory of Convergence Medical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science No.5Zhongguancun South Street Beijing100081 China

ISBN: (纸本)9798350320831

Vascular interventional surgery is the main method for treating cardiovascular diseases. But navigating endovascular catheters through the vascular tree is a highly challenging task even for highly trained specialists. Automation of this task can reduce the burden on surgeons and is expected to improve the surgical outcomes. Although there have been relevant studies utilizing reinforcement learning algorithms to realize autonomous navigation of catheter in the virtual environment Cathsim. However, the kinematics model of the catheter in Cathsim does not conform to the operating mode of the catheter in real vascular interventional surgery. Besides, there are problems such as low success rates of catheter autonomous navigation tasks. To address these issues, this paper modifies the kinematics model of the catheter in Cathsim and designs a catheter autonomous navigation model based on reinforcement learning DDPG (Deep Deterministic Policy Gradient) algorithm. The experimental results show that the agents trained through DDPG in this paper performs better than the agents trained through PPO (Proximal Policy optimization) in other studies in terms of navigation task success rate, completion time, and contact force between the catheter and vascular wall during the navigation process. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Development of Small Intelligent Production Line for Cylinder Liner 5

Development of Small Intelligent Production Line for Cylinde...

引用

5th World Conference on Mechanical Engineering and Intelligent Manufacturing, WCMEIM 2022

作者： Shi, Yanhua Li, Zhenzhen Xu, Jiwen Chen, Bin Chen, Degen Wang, Siyong Li, Wanpeng Jiang, Xiaojun Guangdong University of Science and Technology DongGuan523083 China Harbin ZhiDi Robot Technology Co. Ltd. Harbin150000 China Dongguan Strong Laser Advanced Equipment Co. Ltd. DongGuan523000 China

ISBN: (纸本)9781665473699

Taking the cylinder liner as the carrier, a small intelligent production line integrating production and teaching has been developed. Intelligent and unmanned processing was realized through modules such as turning-milling compound machining center, stereoscopic warehouse, material conveying system, automatic loading and unloading system, and automatic detection and monitoring system. This paper introduced the mechanical structure of the stereoscopic warehouse and the automatic loading and unloading system of the production line and the software and hardware structure of the PLC control system in detail. Through on-site debugging and small batch production, the production line has reached the design expectations and better serves teaching and production. © 2022 IEEE.

关键词： Unloading

来源：评论

学校读者我要写书评

暂无评论

Design,Modeling and Experimentation of a Biomimetic Wall-climbing robot for Multiple Surfaces

引用

Journal of Bionic Engineering 2020年第3期17卷 523-538页

作者： Jinfu Liu Linsen Xu Jiajun Xu Tao Li Shouqi Chen Hong Xu Gaoxin Cheng Marco Ceccarelli Institute of Advanced Manufacturing Technology Hefei Institutes of Physical ScienceCASChangzhou 213164China Department of Precision Machinery and Precision Instrumentation University of Science and Technology of ChinaHefei 230026China Anhui Province Key Laboratory of Biomimetic Sensing and Advanced Robot Technology Hefei 230026China Department of Industrial Engineerings University of Rome Tor Vergata Via del Politecnico 100133RomaItaly

Wall-climbing robots can work on steep terrain and obtain environment information in three dimensions for human in real time,which can improve operation ***,traditional single-mode robots cannot ensure the stable attachment on complex wall *** by the structure characteristics of flies and clingfishes,three bionic structures including the flexible spine wheel,the adhesive material and the adsorption system are *** at task requirements on multiple walls and based on the above three bionic structures,a wall-climbing robot with the composed mode of“grabbing+adhesion+adsorption”is presented v/a the law of mechanism configuration *** static analysis,the safe attachment conditions for the robot on smooth and rough walls are that the adsorption force is 30 N or *** on Newton's Euler and Lagrange formulas,the dynamic equations of the robot on vertical walls are established to deduce that the maximum theoretical torque of the driving motor is 1.43 N·m at a uniform ***,the prototype of the wall-climbing robot is manufactured and tested on the vertical lime wall,coarse sandpaper wall and acrylic ceiling ***,experiment results imply that the average maximum moving speed and the corresponding load are 7.19 cm·s-1 and 0.8 kg on the vertical lime wall,7.78 cm·s-1 and 0.6 kg on the coarse sandpaper wall,and 5.93 cm·s-1 and 0.2 kg on the acrylic ceiling wall *** findings could provide practical reference for the robot’s application on walls.

关键词： wall-climbing robot spine wheel adhesive material adsorption system

来源：评论

学校读者我要写书评

暂无评论

Study on an Adaptive Clamping Device for Passive Safety Delivery of Vascular Intervention robot

Study on an Adaptive Clamping Device for Passive Safety Deli...

引用

IEEE International Conference on Mechatronics and Automation

作者： Sheng Cao Shuxiang Guo Jian Guo Jian Wang Chunying Li Huiyin Xu Bin Wang Mingchao Ding 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 Beijing China Shenzhen Institute of Advanced Biomedical Robot Company Limited Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China National Engineering Laboratory of Computer Technology for Big Data Systems Shenzhen University Shenzhen China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In practical clinical applications, vascular intervention surgical robots have developed sophisticated human-machine interaction systems, enabling assistance to physicians in performing remote surgeries and providing intelligent visual feedback. However, regarding surgical safety, current research predominantly focuses on force feedback and robot control logic, with clamping mechanisms targeting the locking of catheters and guide wires. Excessive clamping force may lead to surface damage to intervention instruments, while insufficient force delivery may result from slippery surfaces. Therefore, addressing these issues, this study proposed a passive, compliant safety strategy for an adaptive clamping device based on a vascular intervention surgical robot platform. This device can accommodate different diameter catheters and maintain a constant delivery force during the intervention process. Finally, through experimentation, the effectiveness, safety, and stability of the device were demonstrated.

关键词： Visualization Medical robotics Force Wires robot control Surgery Safety

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis for the Axe Foot of Bio-inspired Anchoring robot 17

Design and Analysis for the Axe Foot of Bio-inspired Anchori...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Liu, Lei Xu, Linsen Liu, Jinfu Xu, Jiajun Chen, Shouqi Cheng, Gaoxin Xu, Hong Shi, Jia University of Science and Technology of China Hefei China Anhui Province Key Laboratory of Biomimetic Sensing and Advanced Robot Technology Hefei China

ISBN: (纸本)9781728164151

Mooring location has become increasingly important with the rapid development and utilization of marine resources. The mooring system of the underwater mobile robot is required to be efficient and intelligent. This paper proposes a novel anchoring robot by imitating the excellent inhabitation functions and physiological structure of the razor clam. This bio-inspired robot can autonomously dig holes, anchor, and detach to improve the efficiency of mooring location in marine operations. Specifically, the axe foot of the robot plays an important role in these movements. It contains a screw-cone drill and two soft parts. The screw-cone drill is the main forced part while the robot is in the digging state and the rationality of drill design is proved by mechanics analysis. Moreover, the soft part, which is connected with the upper end of the drill, is analyzed to show the capability of obstacle avoidance. The rationality of the structural design and a good submarine anchoring function of the axe foot are verified by the above analysis. © 2020 IEEE.

关键词： Drills

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional recognition method of fruit target based on PointNet++ 5

Three-dimensional recognition method of fruit target based o...

引用

5th World Conference on Mechanical Engineering and Intelligent Manufacturing, WCMEIM 2022

作者： Wu, Xiangxiang Tan, Libin Xu, Xiangrong Anhui University of Technology AnHui Province Key Laboratory of Special Heavy Load Robot Ma'anshan China Beijing Institute of Technology Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing China School of Mechanical Engineering Anhui University of Technology Ma'anshan China

ISBN: (纸本)9781665473699

Aiming at the problem that the conventional target recognition algorithm is highly dependent on light and has a poor fruit recognition effect in low light and dark environments, this paper proposes a three-dimensional fruit recognition method based on PointNet++. First, a depth camera is used to obtain point clouds to construct a dataset, and then the network is trained using the dataset. Finally, the fruit point cloud is recognized by the trained network. The experimental results show that the PointNet++ algorithm can recognize both unoccluded and partially occluded fruit point clouds, and the IoU of the predicted and real results are 0.92 and 0.89, respectively, which meets the actual production requirements. © 2022 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Visual Based robot Trajectory Teaching Method for Traditional Chinese Medical Moxibustion Therapy 6

A Visual Based Robot Trajectory Teaching Method for Traditio...

引用

6th IEEE International Conference on Computer and Communications, ICCC 2020

作者： Liu, Jiaxun Lei, Qujiang Qiao, Yukai Gui, Guangchao Li, Xiuhao Jin, Jintao Wang, Weijun Intelligent Robot Equipment Center Guangzhou Institute of Advanced Technology Chinese Academy of Sciences Guangzhou 511458 China

ISBN: (纸本)9781728186351

At present, Chinese traditional physiotherapy is more and more trusted and valued by people, among which moxibustion is a very effective treatment. In order to improve the efficiency of human-computer interaction and help physiotherapists to use robots to replace human power, this paper proposes a visual based robot arm trajectory teaching method. The physiotherapy staff only needs to use an optical marker to demonstrate the therapeutic trajectory on the patient's back, and the robotic arm can pick up the expected trajectory and repeat the same work. We use LK optical flow algorithm to obtain marker's motion trajectory, and then smoothen the trajectory through SG filter, which is more executable for robot arm. Finally, we design an experiment and simulate it on MATLAB to obtain the accuracy of the trajectory and the results is impressive. © 2020 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Actuator-Constrained Reinforcement Learning for High-Speed Quadrupedal Locomotion

arXiv

引用

arXiv 2023年

作者： Shin, Young-Ha Song, Tae-Gyu Ji, Gwanghyeon Park, Hae-Won Humanoid Robot Research Center Department of Mechanical Engineering Korea Advanced Institute of Science and Technology Yuseonggu Daejeon34141 Korea Republic of

This paper presents a method for achieving high-speed running of a quadruped robot by considering the actuator torque-speed operating region in reinforcement learning. The physical properties and constraints of the actuator are included in the training process to reduce state transitions that are infeasible in the real world due to motor torque-speed limitations. The gait reward is designed to distribute motor torque evenly across all legs, contributing to more balanced power usage and mitigating performance bottlenecks due to single-motor saturation. Additionally, we designed a lightweight foot to enhance the robot’s agility. We observed that applying the motor operating region as a constraint helps the policy network avoid infeasible areas during sampling. With the trained policy, KAIST Hound, a 45 kg quadruped robot, can run up to 6.5 m/s, which is the fastest speed among electric motor-based quadruped robots. Copyright © 2023, The Authors. All rights reserved.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

FLASH: Low-Latency Serverless Model Inference with Multi-Core Parallelism in Edge

FLASH: Low-Latency Serverless Model Inference with Multi-Cor...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yanbo Li Yanying Lin Shijie Peng Yingfei Tang Tian Xiang Wei Song Kejiang Ye Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Southern University of Science and Technology University of Chinese Academy of Sciences Zhejiang Laboratory Intelligent Robot Research Center

Low response latency holds a pivotal role in the landscape of edge deep learning model inference, yet the constrained resources within edge computing environments often limit its full potential. Within the scope of this paper, we substantiate that even amid the resource limitations inherent to edge computing environments, it remains feasible to curtail model response latency by elevating multi-core parallel efficiency. Our research encompasses a comprehensive analysis of the parallel acceleration effects observed across models featuring diverse parameter magnitudes during the inference process. This analysis culminates in the development of FLASH, an online deep model inference system tailored for Serverless edge inference, strategically optimized through the utilization of multi-core parallelism. FLASH exhibits dynamic adaptability by modulating the number of CPU cores within computational instances in accordance with traffic request loads. It also employs a dynamic scaling mechanism to finely adjust model placement, ultimately facilitating inference acceleration and mitigating the concomitant cold start overhead. Empirical experimentation conducted across a spectrum of burst-level workloads serves to underscore FLASH’s capacity, resulting in an average reduction in response latency by 33% and a maximum reduction of 75%, while concurrently realizing a throughput enhancement of 2.94x.

关键词：

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 Scenarios Database for Maritime Autonomous Surface Ship Test 7

Research on the Process-based Generation Method of Scenarios...

引用

2022 7th International Conference on Electronic technology and Information Science, ICETIS 2022

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

ISBN: (纸本)9783800757794

In recent years, Maritime Autonomous Surface Ship (MASS) has been developed rapidly and has demonstrated many new capabilities, which poses a challenge to the testing methods of autonomous ships. Currently, traditional test methods is no longer sufficient to support comprehensive testing and verification. For virtual testing, there is still a lack of a reliable virtual test scenario generation process. Therefore, this paper proposes a method for generating virtual test scenarios for autonomous ships. It is based on the scenario generation frame of the intelligent car and comprehensively considers the feature of the operating environment of the MASS. This process develops an element database by deconstructing the real scenes. For generating, it reconstructs and assigns the elements according to the test task (functional scenario) and the logical relationship between the elements (logical scenario) to reconstruct the new scenario. The new scenarios obtained in this way are optimized and supplemented to be the test scenarios database. In addition, a prototype following this frame was designed and loaded with the "automatic pathfinding task of the Wuhan section of the Yangtze River under good navigation conditions" for testing. The experiment generated 48 different scenarios, proving that this generator can output a comprehensive test scenario database to meet test requirements. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Database systems

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：