检索结果-内蒙古大学图书馆

DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexterity

IEEE robotics and Automation Letters 2024年第12期9卷 10772-10779页

作者： Lee, Kang-Won Qin, Yuzhe Wang, Xiaolong Lim, Soo-Chul Dongguk University Department of Mechanical Robotics and Energy Engineering Seoul04620 Korea Republic of University of California San Diego CA United States

The sense of touch is an essential ability for skillfully performing a variety of tasks, providing the capacity to search and manipulate objects without relying on visual information. In this paper, we introduce a multi-finger robot system designed to manipulate objects using the sense of touch, without relying on vision. For tasks that mimic daily life, the robot uses its sense of touch to manipulate randomly placed objects in dark. The objective of this study is to enable robots to perform blind manipulation by using tactile sensation to compensate for the information gap caused by the absence of vision, given the presence of prior information. Training the policy through reinforcement learning in simulation and transferring the trained policy to the real environment, we demonstrate that blind manipulation can be applied to robots without vision. In addition, the experiments showcase the importance of tactile sensing in the blind manipulation tasks. Our project page is available at https://***/dextouch/ © 2016 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Engine Performance Using Blended Fuels of Biodiesel and Eco Diesel

引用

Energy engineering 2023年第1期120卷 107-123页

作者： Muhammad Idris IHusin Indra Hermawan Uun Novalia RDBatubara Nugroho Agung Pambudi Alfan Sarifudin Study Program of Mechanical Engineering Universitas Medan AreaMedan20156Indonesia Study Program of Mechanical Engineering Politeknik Negeri MedanMedan20156Indonesia Study Program of Industrial Engineering Universitas Harapan MedanMedan20156Indonesia Department of Mechanical Engineering Education Universitas Sebelas MaretSurakarta57126Indonesia

Diesel engines is an internal combustion engine with high thermal efficiency,which also uses biodiesel fuel,an environmentally friendly,non-toxic,and low sulfur *** has been around for a long time due to its similar characteristics to diesel fuels which has limited ***,several disadvantages are associated with biodiesel,such as poor volatility and high viscosity,which reduces engine ***,this study was carried out to improve the diesel engine performance by mixing biodiesel with ecodiesel(ED),an additive produced from natural ingredients that is dissolvable in *** biodiesel fuel properties used are density 860 kg/m3,dynamic viscosity 4.50E-06 m2/s,cetane number 45,and flashpoint 52°*** results showed that biodiesel-ED mixture could improve engine performance and the optimum performance was at a speed of 3000 rpm on 43.30(kW),124.93(N.m)of the engine torque,and 2.45E–5(kg/kW.s)of the specific fuel *** to paired sample t-test,the difference in the engine performance is only experienced in the torque,which has a significant increase in the composition of the biodiesel+ED by 0.07 gr mixture.

关键词： Car vehicle experiment combustion ED renewable energy

来源：评论

学校读者我要写书评

暂无评论

Advancements and Performance Analysis of Feature Detection and Matching Methods in Visual Odometry

引用

Journal of Institute of Control, robotics and Systems 2025年第3期31卷 231-236页

作者： Choi, Ji Hun Kang, Chang Ho Kim, Sun Young Department of Artificial Intelligence Sejong University Korea Republic of Department of AI Robotics Sejong University Korea Republic of School of Mechanical Engineering Kunsan National University Korea Republic of

This study presents a comprehensive performance analysis of feature detectors and descriptors in visual odometry (VO) based on four key metrics: absolute trajectory error (ATE), relative pose error (RPE), cumulative drift, and frames per second (FPS). Five algorithm-based methods (SIFT, ROOTSIFT, ORB, KAZE, and AKAZE) and five AI-based methods (SuperPoint, DISK, ALIKED, D2NET, and Xfeat) are evaluated using two matching strategies: Brute-Force and LIGHTGLUE. Performance assessment is conducted on the KITTI dataset, demonstrating that KAZE achieves the best results in ATE and cumulative drift, while ALIKED outperforms in RPE and FPS. These findings offer valuable insights for selecting the optimal feature detection and description techniques in real-world VO applications. © ICROS 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A trajectory-level robot skill learning method based on fuzzy systems

引用

Science China(Information Sciences) 2025年第5期68卷 38-52页

作者： Chao ZENG Zhen DENG Boyang TI Yongsheng GAO Department of Computer Science University of Liverpool School of Mechanical Engineering and Automation Fuzhou University State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences State Key Laboratory of Robotics and System Harbin Institute of Technology

Learning from demonstration(LfD) allows for the effective transfer of human manipulation skills to a robot by building a model that represents these skills based on a limited number of demonstrated ***,a skilllearning model that can comprehensively satisfy multiple requirements,such as computational complexity,modeling accuracy,trajectory smoothness,and robustness,is still ***,this work aims to provide such a model by employing fuzzy ***,we introduce an LfD model named Takagi-Sugeno-Kang fuzzy system-based movement primitives(TSKFMPs),which exploits the advantages of the fuzzy theory for effective robotic imitation learning of human *** work formulates the TSK fuzzy system and gradient descent(GD) as imitation learning models,leveraging recent advancements in GD-based optimization for fuzzy *** study takes a two-step strategy.(ⅰ) The input-output relationships of the model are established using TSK fuzzy systems based on demonstration *** this way,the skill is encoded by the model parameter in the latent space.(ⅱ) GD is used to optimize the model parameter to increase the modeling accuracy and trajectory *** further explain how learned trajectories are adapted to new task scenarios through local *** conduct multiple tests using an open dataset to validate our method,and the results demonstrate performance comparable with those of other ***,we implement it in a real-world case study.

关键词： robot skill learning movement primitives TSK fuzzy systems gradient descent robotics

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Response and Control of a Flapping-Wing Aerial Robot Under Wind Gusts

引用

Journal of Bionic engineering 2024年第1期21卷 209-223页

作者： Kazuki Shimura Hikaru Aono Chang-kwon Kang Graduate School of Science and Technology Shinshu University3-15-1 TokidaUedaNagano 3868567Japan Department of Mechanical Engineering and Robotics 3-15-1 TokidaUedaNagano 3868567Japan Department of Mechanical and Aerospace Engineering University of Alabama in HuntsvilleTechnology Hall N266HuntsvilleAL35899USA

Bioinspired flapping-wing micro-air-vehicles(FWMAVs)have the potential to be useful aerial tools for gathering information in various *** recent advancements in manufacturing technologies and better understanding of aerodynamic mechanisms behind of the flapping flight,outdoor flights have become a ***,to fully realize the potential of FWMAVs,further improvements are necessary,particularly in terms of stability and robustness under gusty *** this study,the response and control of a tailless two-winged FWMAV under the wind gusts are *** experiments are conducted with a one-degree-of-freedom gimbal to focus on effects of wind gusts on the rotational motion of the ***-derivative and sliding-mode controls are adopted for the attitude *** present that the body angles changed in time and reached approximately 50°at the maximum due to the wing *** sliding-mode controller can more effectively control the rotational angle in the presence of disturbances and both the wing speed and changes in wind speed have an impact on the effectiveness of attitude *** results contribute to the development of of tailless two-winged,single-motor driven FWMAVs in terms of the design of attitude controller and testing apparatus.

关键词： Flapping-wing micro-air vehicles Sliding-mode control Pitch and roll angle-Wind gus

来源：评论

学校读者我要写书评

暂无评论

Prediction of directivity characteristics of piezoelectric macro-fiber composite interdigital transducers: a semi-analytical approach 11

Prediction of directivity characteristics of piezoelectric m...

引用

11th European Workshop on Structural Health Monitoring, EWSHM 2024

作者： Raorane, Siddhesh Ambrozinski, Lukasz Stepinski, Tadeusz Packo, Pawel Department of Robotics and Mechatronics Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology Krakow30-059 Poland

The employment of guided waves for structural health monitoring applications has attracted substantial attention in recent years. Piezoelectric transducers are frequently employed in these systems for elastic wave generation and acquisition. Their dynamic properties, i.e., direction-dependent frequency characteristics such as directivity patterns, are an important feature for designing a reliable monitoring strategy. Although analysis of the transducer directivity pattern can be performed using finite element models, these usually tend to be computationally very expensive, especially for parametric and optimization studies. In this paper, a semi-analytical framework is proposed that can predict the far-field directivity patterns of complex transducers of arbitrary shape and structure mounted on a substrate. The framework described in this paper integrates analytical far-field predictions with a local finite element model evaluating the traction field produced by the transducer. Consequently, the FE model accurately captures near-field responses, whereas the analytical component predicts the far-field responses. The implementation of this semi-analytical framework requires the development of analytical and numerical approaches. The former includes computation of dispersion curves of the inspected plate, the stress and displacement profiles of wave modes, and ultimately, the excitability relations, while the latter includes estimation of the traction field between the transducer and the plate using the FE model. Owing to the popularity of piezoelectric macro-fiber composite (MFC) transducers, in this paper, we apply the proposed method to predict the directivity patterns of MFC M2807-P2 transducer. To validate the reliability of the proposed method, the predicted patterns are compared with experimental results obtained using Laser Doppler Vibrometer. © 2024 11th European Workshop on Structural Health Monitoring, EWSHM 2024. All rights reserved.

关键词： Piezoelectric transducers

来源：评论

学校读者我要写书评

暂无评论

Development and Experimental Evaluation of an Endoscopic Capsule Robot Equipped With a Fail-safe Biopsy Mechanism 12

Development and Experimental Evaluation of an Endoscopic Cap...

引用

12th RSI International Conference on robotics and Mechatronics, ICRoM 2024

作者： Zarifi Khameneh, M.R. Tolouei, Z. Yousefi, M. Pishkenari, H. Nejat Alasty, A. Sharif University of Technology Micro/Nano Robotics Laboratory Department of Mechanical Engineering Tehran Iran Sharif University of Technology Department of Mechanical Engineering Tehran Iran

ISBN: (纸本)9798331529734

Endoscopic capsule robots (ECRs) have introduced feasible and painless gastrointestinal diagnostics to endoscopic procedures. To further enhance the capability of these revolutionary devices, many research groups have attempted to equip ECRs with functions such as active locomotion, drug delivery, and biopsy. This study addresses the challenges related to the biopsy functionality of ECRs by introducing a remote biopsy mechanism adapted from the magnetic spring concept. The mechanism consists of one axial permanent magnet (PM) fixed inside the ECR's body, a radial PM free to translate along the device length and rotate perpendicular to its magnetization direction, and conventional biopsy forceps. The presented ECR can locomote directly using external gradient magnetic fields or through rotation via external uniform magnetic fields. Additionally, the proposed biopsy mechanism ensures reliable actuation and a fail-safe design. To evaluate the performance of this design, a prototype with a diameter of 12 mm and a length of 30 mm was fabricated, and its functionality in active rotational locomotion, orientation control, and biopsy actuation was demonstrated through experiments. © 2024 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Automatic Cataract and Cholesterol Detection System Based on Recurrent Neural Network (RNN): A Comparison with Convolutional Neural Network (CNN) and Siamese Neural Network (SNN) 1

引用

19th International Conference of Intelligent Unmanned Systems, ICIUS 2023

作者： Lie, Zener S. Widodo, Jatmiko A. F. Hanesi, Isabel K. P. Moningka, Matthew R. N. Mariana, Y. Astuti, Winda Akmeliawati, Rini Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Product Design program Industrial Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Robotics and Automation Research Group School of Electrical and Mechanical Engineering The University of Adelaide North Terrace Campus Adelaide Australia

ISBN: (数字)9789819765911

ISBN: (纸本)9789819765904

In Indonesia, the majority of blindness cases, approximately 81%, are attributed to cataract. Additionally, 35% of the population has higher cholesterol levels than the standard normal range. The lack of specialized medical equipment, such as the slit-lamp (Ruparelia in Dalhousie Med J 49(1), [1]) bio-microscope, and trained professionals, especially in rural areas, make it difficult to detect these conditions through eye examinations. To address this issue, a supervised machine learning method, the Recurrent Neural Network (RNN), has been utilized to create an iris scanner system that can identify cataract and high cholesterol in a patient. This system will classify eyes into three categories, i.e., cataract, high cholesterol, and normal iris. The computer simulations indicate that this technique is more accurate and requires less training time compared to the existing Convolutional Neural Network (ANN) and Siamese Neural Network (SNN)-based method, while achieving 100% accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bending results of graphene origami reinforced doubly curved shell

引用

Defence Technology（防务技术） 2024年第5期35卷 198-210页

作者： Nan Yang Yunhe Zou Mohammad Arefi School of Architecture and Civil Engineering Qiqihar UniversityQiqihar 161006HeilongjiangChina School of Mechanical Engineering Inner Mongolia University of TechnologyHohhot 010051Inner MongoliaChina Inner Mongolia Key Laboratory of Special Service Intelligent Robotics Hohhot 010051Inner MongoliaChina Faculty of Mechanical Engineering Department of Solid MechanicsUniversity of KashanKashan87317-51167Iran

The present work investigates higher order stress,strain and deformation analyses of a shear deformable doubly curved shell manufactures by a Copper(Cu)core reinforced with graphene origami auxetic metamaterial subjected to mechanical and thermal *** effective material properties of the graphene origami auxetic reinforced Cu matrix are developed using micromechanical models cooperate both material properties of graphene and Cu in terms of temperature,volume fraction and folding *** principle of virtual work is used to derive governing equations with accounting thermal *** numerical results are analytically obtained using Navier's technique to investigate impact of significant parameters such as thermal loading,graphene amount,folding degree and directional coordinate on the stress,strain and deformation responses of the *** graphene origami materials may be used in aerospace vehicles and structures and defence technology because of their low weight and high stiffness.A verification study is presented for approving the formulation,solution methodology and numerical results.

关键词： Graphene origami Copper matrix Doubly curved Shear deformable Auxetic metamaterial

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an Internet of Things (IoT)-Based Application and System to Detect Stunting in Infants and Toddlers 10

Design and Development of an Internet of Things (IoT)-Based ...

引用

10th International HCI and UX Conference in Indonesia, CHIuXiD 2024

作者： Tiffany, Theresa Jeremia, James Lie, Zener Sukra Bina Nusantara University Binus Aso School of Engineering Automotive and Robotics Engineering Program Computer Engineering Department Jakarta11480 Indonesia

ISBN: (纸本)9798350380439

Currently, the process of monitoring children's growth in Indonesia relies on manual methods for collecting anthropometric data. These methods pose a risk of data recording errors. Additionally, the ratio of healthcare workers to children in Indonesia is 1:90, a significant disparity that hinders efforts to reduce the prevalence of stunting in the country. To support the third Sustainable Development Goal (SDG), which emphasizes 'Good Health and Well-being,' it is crucial to address issues in the stunting management process, from data collection to monitoring. The design and development of this iOS-based mobile application aim to assist in monitoring child growth and provide guidance and steps for prevention and treatment. Besides application development, it also involves the design and development of an Internet of Things (IoT) system to aid in the collection of children's anthropometric data. The research methodology includes studying stunting cases in Indonesia, anthropometric data calculation methods, stunting prevention and management steps, application design and development, automatic anthropometric data collection, and online data storage and transmission using IoT technology. The developed application and system have been tested and successfully integrated. The IoT device has an accuracy rate of 99.83% for weight measurement calibration and 98.68% for height or length measurement calibration. From the testing results of the child condition calculation method in the application, an accuracy rate of 100% was achieved. © 2024 IEEE.

关键词： Anthropometry

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：