检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2021年第5期2卷 394-403页

作者： Dong, Zhipeng Gao, Yi Yan, Yunhui Chen, Fei The School of Mechanical Engineering and Automation Northeastern University Shenyang110819 China The Smart Manipulation Robots Laboratory Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong

Analog meters equipped with one or multiple pointers are wildly utilized to monitor vital devices' status in industrial sites for safety concerns. Reading these legacy meters autonomously remains an open problem since estimating pointer origin and direction under imaging damping factors imposed in the wild could be challenging. Nevertheless, high accuracy, flexibility, and real-time performance are demanded. In this work, we propose the vector detection network (VDN) to detect analog meters' pointers given their images, eliminating the barriers for autonomously reading such meters using intelligent agents like robots. We tackled the pointer as a 2-D vector, whose initial point coincides with the tip, and the direction is along tail-to-tip. The network estimates a confidence map, wherein the peak pixels are treated as vectors' initial points, along with a two-layer scalar map, whose pixel values at each peak form the scalar components in the directions of the coordinate axes. We established the Pointer-10 K dataset composing of real-world analog meter images to evaluate our approach due to no similar dataset is available for now. Experiments on the dataset demonstrated that our methods generalize well to various meters, robust to harsh imaging factors, and run in real-time. Impact Statement-From the automatic meter recognition perspective, this work proposes an accurate, flexible, and ready-to-use pointer detection algorithm that contributes to dealing with legacy pointer-type meters, which still serve in industrial sites to date and require extensive human inspection. Adopting this technique to automatic agents could save human labor and promote the effectiveness and efficiency of getting data. It also inspires particular object detection problems, wherein the object could be considered a vector whose position is concerned, and its orientation also matters. The proposed VDN is agnostic to the semantic meaning of the vectors it detects. Thus it could also be used to

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Robot device for ankle joint rehabilitation: A review 55

Robot device for ankle joint rehabilitation: A review

引用

55th International Conference on Vibroengineering

作者： Zhetenbayev, Nursultan Zhauyt, Algazy Balbayev, Gani Shingissov, Beibit Department of Robotics and Engineering Tools of Automation Satbayev University Almaty050013 Kazakhstan Department of Electronics and Robotics Almaty University of Power Engineering and Telecommunications Almaty050013 Kazakhstan Academy of Logistics and Transport Almaty050012 Kazakhstan Space Engineering and Technology Almaty University of Power Engineering and Telecommunications Almaty050013 Kazakhstan

The purpose of this review document is to summarize the latest developments and research in the field of robotics related to the field of ankle joint rehabilitation, review new results, and determine the actual state of the art. The literature search was carried out using scientific and medical databases and other websites related to robots used in the field of ankle rehabilitation, analyzing research from the 1950s to the present. © 2022 JVE International. All rights reserved.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Intuitive Teleoperation Control for Flexible Robotic Endoscopes Under Unkonwn Environmental Interferences

Intuitive Teleoperation Control for Flexible Robotic Endosco...

引用

International Conference on Control and automation (ICCA)

作者： Wei Chen Yiang Lu Bin Li Jianshu Zhou Hanwen Cao Fei Chen Yun-Hui Liu Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Hong Kong Center for Logistics Robotics Hong Kong

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Teleoperation control has been taken a pivotal role in robot-assisted surgical interventions. Unlike hand-eye coordination employed in the conventional laparoscopic systems, the eye-head coordination challenge arises with flexible robotic endoscopes, necessitating a distinct intuitive decision-making approach. In this paper, we introduce an intuitive teleoperation control scheme to address the eye-head coordination intricacies inherent in continuum endoscopic robots. The method achieves field of view (FOV) control consistent with surgeons' intuition for the robots based on the modelling of a virtual workspace (VW). By leveraging accurate shape feedback from embedded multi-core fiber Bragg gratings (FBGs), an observer-based anti-interference algorithm is implemented allowing a stable line of sight for robust motion control, even in challenging operational conditions with unknown disturbances. A class of robotic flexible endoscopes commonly used is analyzed specifically and deployed to validate the proposed approach. The efficacy and superiority of the proposed algorithm have been demonstrated through experimental results performed on a urology robotic system, encompassing trajectory tracking and disturbance resistance tasks.

关键词： Resistance Endoscopes Trajectory tracking Shape Robot kinematics Surgery Fiber gratings

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Model Predictive Control (MPC) Based Pressure Regulation System for a Precision Agricultural Sprayer

Design and Implementation of Model Predictive Control (MPC) ...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Adrees Khan Fazal Nasir Muhammad Tufail Muhammad Haris Muhammad Tahir Khan Zhang Dong Department of Mechatronics Engineering University of Engineering and Technology Peshawar Pakistan Advanced Robotics and Automation Lab National Center of Robotics and Automation Peshawar Pakistan Institute of Automation Qilu University of Technology (Shandong Academy of Sciences) Jinan China

Model Predictive Control (MPC) is a control scheme that involves predicting the future behavior of a system and optimizing control actions to accomplish the desired objective. In this study, we develop an intelligent control algorithm, based on MPC to regulate the target pressure in variable-rate agriculture sprayer robots. Modeling and simulation steps of the spraying system are developed using MATLAB/Simulink environment, before passing to the description of the MPC algorithm. Real-time implementation of the MPC algorithm was conducted on an Arduino Mega 2560 controller board by using Simulink Support Package for Arduino Hardware in MATLAB/Simulink to experimentally validate the preliminary results of simulations. The work evaluates MPC to regulate the pressure in the system and compares the results with a traditional PID control system. Moreover, MPC is a novel method for nonlinear system control that achieves zero steady-state error, low transient response, and reduces peak overshoot compared to the results obtained with a PID controller, thereby reducing the waste of chemicals, and minimizing the toxicology and environmental risk.

关键词： Transient response Toxicology Software packages Spraying Agriculture Regulation Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of Plant Disease Identification Methodology Based on Improved Classification and Deep Learning Principle

Experimental Analysis of Plant Disease Identification Method...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Shibu, S. Priyadharshini, S. Madhini, M. Radha, K. Giri, Pallavi Samhan, Ahmad A. Ali Panimalar Engineering College Department of Ece Chennai India Karpaga Vinayaga College of Engineering and Technology Department of Robotics and Automation Tamil Nadu Chengalpattu India S.A. Engineering College Department of Ece Chennai India Dr. Mahalingam College of Engineering and Technology Department of Cse Pollachi Coimbatore India Laxminarayan Innovation Technological University Department of Civil engineering Nagpur India Zarqa University Faculty of Information Technology Deoartment of Software Engineering Zarqa Jordan Universityof Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

The agriculture industry is essential for providing excellent food and significantly contributes to the growth of economies and people. Plant diseases can result in substantial reductions in food output and diminish species diversity. The prompt identification of plant diseases by precise or automated detection methods can improve food production quality and save economic losses. In recent years, deep learning has significantly enhanced the identification accuracy of image categorization and object detection systems. In this paper, a novel method termed Learning Enabled Disease Detection Logic (LDDL) is introduced for the efficient identification of plant diseases, which is cross-validated against the traditional Convolutional Neural Network (CNN) to assess the efficacy of the proposed scheme. The report delineates the specific crop illnesses addressed, the models utilized, the data sources referenced, and the overall efficacy as measured by the performance criteria applied in each study for plant disease diagnosis. The findings demonstrate that the proposed model, LDDL, achieves superior accuracy compared to prevalent illness detection methods and identifies the primary parameters influencing the efficacy of deep learning-based tools. The research offers significant insights for researchers, practitioners, and industry professionals in plant disease detection by addressing challenges and limitations, presenting a thorough understanding of the current research landscape, elucidating the advantages and drawbacks of various methods, and suggesting potential solutions to facilitate their implementation. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

PRISM: A Polyhedral Reflective Imaging Scanning Mechanism for Hyperspectral Applications

PRISM: A Polyhedral Reflective Imaging Scanning Mechanism fo...

引用

IEEE International Conference on robotics and Biomimetics

作者： Zheng Sun Zhipeng Dong Shixiong Wang Fei Chen Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong SAR

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Hyperspectral imaging has become essential in fields such as waste sorting and agriculture due to its ability to capture detailed spectral information. However, conventional hyperspectral imaging systems typically rely on mechanical movements, such as conveyor belts or linear stages, to scan the target objects, which limits their applicability in environments with static targets or space constraints. To address these challenges, we present PRISM (Polyhedral Reflective Imaging Scanning Mechanism), a novel system that facilitates rapid and high-precision imaging of stationary objects by leveraging a polyhedral reflective structure, thereby eliminating the need for external relative motion. Experimental evaluations demonstrate that PRISM can achieve full spatial-spectral data of 512 by 727 pixels with 448 bands in 2.01 seconds, while maintaining high spectral accuracy, with a reflectance standard deviation of 0.015. We further validate PRISM's effectiveness through textile waste sorting experiments, where PRISM accurately differentiates between various material types at both the pixel and object levels, showcasing its potential for practical applications in industrial settings.

关键词： Reflectivity Accuracy Service robots Cameras Belts Robustness Standards Hyperspectral imaging Sorting Textiles

来源：评论

学校读者我要写书评

暂无评论

Quantitative Progress Evaluation of Post-stroke Patients Using a Novel Bimanual Cable-driven Robot

引用

Journal of Bionic engineering 2021年第6期18卷 1331-1343页

作者： Thiago Alves Rogério Sales Gonçalves Giuseppe Carbone Laboratory of Automation and Robotics School of Mechanical EngineeringFederal University of UberlândiaUberlândia38400-902Brazil Department of Mechanical Energy and Management EngineeringUniversity of Calabria87036RendeItaly

Rehabilitation is the most effective way to reduce motor impairments in post-stroke *** process demands several hours with a specialized *** resources and personnel shortages,the literature reports a high interest in robotic assisted rehabilitation ***,cable-driven robotic architectures are attracting significant research interest for post-stroke ***,the existing cable-driven robots are mostly unilateral devices allowing the rehabilitation only of the most affected *** leaves unaddressed the rehabilitation of bimanual activities,which are predominant within the common Activities of Daily Living(ADL).Thus,this paper presents a specific novel design to achieve bimanual rehabilitation tasks that has been named as BiCAR ***,this paper provides a full insight on the BiCAR system as well as on its dedicated developed software *** particular,BiEval software has been developed as based on a serious game strategy and a virtual reality environment to track the patient exercising duration,motion ranges,speeds,and forces over time for achieving a quantitative assessment of the rehabilitation ***,the paper presents the BiCAR/BiEval capabilities by referring to a pilot Randomized Controlled Trial(RCT).The clinical trials have been used to validate the BiCAR/BiEval in terms of engineering feasibility and user acceptance to achieve an innovative cost-oriented integrated hardware/software device for the bimanual assistive rehabilitation of post-stroke patients.

关键词： Cable-driven robots Low cost Stroke rehabilitation Bimanual Progress tracking Serious games

来源：评论

学校读者我要写书评

暂无评论

Real-Time Motion Generation and Data Augmentation for Grasping Moving Objects with Dynamic Speed and Position Changes

Real-Time Motion Generation and Data Augmentation for Graspi...

引用

IEEE/SICE International Symposium on System Integration

作者： Kenjiro Yamamoto Hiroshi Ito Hideyuki Ichiwara Hiroki Mori Tetsuya Ogata Robotics Research Department Connective Automation Innovation Center R&D Group Hitachi Ltd. Institute for AI and Robotics Future Robotics Organization Faculty of Science and Engineering Waseda University

While deep learning enables real robots to perform complex tasks had been difficult to implement in the past, the challenge is the enormous amount of trial-and-error and motion teaching in a real environment. The manipulation of moving objects, due to their dynamic properties, requires learning a wide range of factors such as the object's position, movement speed, and grasping timing. We propose a data augmentation method for enabling a robot to grasp moving objects with different speeds and grasping timings at low cost. Specifically, the robot is taught to grasp an object moving at low speed using teleoperation, and multiple data with different speeds and grasping timings are generated by down-sampling and padding the robot sensor data in the time-series direction. By learning multiple sensor data in a time series, the robot can generate motions while adjusting the grasping timing for unlearned movement speeds and sudden speed changes. We have shown using a real robot that this data augmentation method facilitates learning the relationship between object position and velocity and enables the robot to perform robust grasping motions for unlearned positions and objects with dynamically changing positions and velocities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Magnetically Driven Capsule Robot for Multi-Targeted Biopsy and Drug Delivery in Stomach

Magnetically Driven Capsule Robot for Multi-Targeted Biopsy ...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Xu, Zhihui Wei, Tanyong Li, Zongze Huang, Ding Liu, Shoubin Hu, Chengzhi Southern University of Science and Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Shenzhen China Southern University of Science and Technology Guangdong Prov. Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen China

ISBN: (纸本)9798350325706

Capsule robots have emerged as a promising solution for non-invasive and painless screening of gastrointestinal diseases, offering significant advantages in patient comfort and reduced risk of cross-infection. Despite these advantages, existing capsule robots fall short in their ability to conduct targeted biopsies and deliver drugs to specific gastric lesions. To address this limitation, this paper presents the design and development of a magnetically driven capsule robot that leverages visual feedback to achieve accurate targeting for biopsy and drug administration in gastric lesions. Internal magnets, responsive to an external gradient magnetic field, enable the controlled propulsion of the capsule robot. A kinetic model of the capsule robot is analyzed, allowing it to recognize lesion contours through the endoscopic camera. This recognition determines the rotation angle or small adjustments required for the capsule robot's attitude and positioning. Experimental results in a simplified in vitro stomach model showcase the capability of the capsule robot to achieve targeted biopsy and drug delivery. These results highlight the potential feasibility of the proposed capsule robot in enhancing diagnostic accuracy and treatment efficacy with broader applications within the realm of gastric healthcare. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Control of High Precision Buoyancy Adjustment System for Small AUVs

Design and Control of High Precision Buoyancy Adjustment Sys...

引用

Computer Science, Electronic Information engineering and Intelligent Control Technology (CEI), IEEE International Conference on

作者： Yongyao Wang Tao Sui Shuxue Yan Cong Chen Zhigang Li School of Automation and Electrical Engineering Shenyang Ligong University Shenyang China Marine Robotics Department Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

This paper addresses the issue of buoyancy variation caused by differences in seawater density at varying operational depths for small AUVs working within 200 meters. To tackle this, a buoyancy adjustment system is designed that uses a piston-type oil cylinder to take in and release oil. The system integrates a digital-to-analog converter with a cable sensor to achieve precise measurement and control of the oil volume by accurately measuring the piston position. A mathematical model of the buoyancy adjustment system is established, and a fuzzy PID control strategy optimized by the Beetle Antennae Search (BAS) algorithm is proposed. Through Simulink simulation analysis, the system's precision adjustment capability and stability are validated. The simulation results demonstrate that the system exhibits good control performance in terms of adjustment time, overshoot, and disturbance rejection, thereby proving its reliability and feasibility.

关键词： Pistons PI control Oils Volume measurement Sea measurements Buoyancy Position measurement Bladder Stability analysis PD control

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：