检索结果-内蒙古大学图书馆

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024

作者： Bouzid, Rania Narayan, Jyotindra Gritli, Hassène Tunis Borj Cedria1164 Tunisia Indian Institute of Technology Guwahati Mechatronics and Robotics Laboratory Department of Mechanical Engineering Assam Guwahati781039 India Le Belvédère Tunis1002 Tunisia

ISBN: (纸本)9798350372229

In the field of robotics and automation, the precise determination of manipulator positions is a fundamental aspect with widespread applications. Despite the significance of analytical methods, solving the Forward Kinematics (FK) for Selective Compliance Assembly Robot Arm (SCARA) manipulator robots can be complex and computationally intensive. Our research introduces a method to address the FK problem for the four degrees of freedom (4-DoF) SCARA manipulator through Artificial Neural Networks (ANNs). We utilize two different generated datasets, one with a fixed step size and another one based on a sinusoidal signal, for training the ANNs. This choice of datasets allows us to assess the ANN s' generalization capabilities across a range of operating conditions. Thereafter, the study is planned to investigate the ANN's performance while employing three distinct training algorithms: Levenberg-Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG). Through a comprehensive comparison of the performance of different ANN models, different training algorithms, and the two adopted generated datasets, this study provides valuable insights into selecting the most optimal training configurations for the SCARA robot's FK solutions. We employ the Mean Squared Error (MSE) and the error histogram as two performance metrics to assess the accuracy of various ANNs. The results reveal that optimal MSE outcomes were obtained when utilizing a balanced architecture with three hidden layers in the analysis of the sinusoidal-signal-based datasets. © 2024 IEEE.

关键词： Artificial Neural Network Fixed-step- and sinusoidal-signal-based datasets Forward kinematics SCARA manipulator robot Training optimizers

来源：评论

学校读者我要写书评

暂无评论

Model-Based Estimation of Active and Passive Muscle Forces Using MRE in Forearm Muscles During 2-DOF Wrist Tasks

Model-Based Estimation of Active and Passive Muscle Forces U...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Cody A Helm Fabrizio Sergi Department of Biomedical and Mechanical Engineering Human Robotics Laboratory University of Delaware Newark DE

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Magnetic resonance elastography (MRE)-based muscle force estimation methods have been proposed to estimate individual muscle forces based on measurements of shear wave speed and joint torque in multiple postures. To estimate both the slope and offset parameters of the relationship between shear wave speed and muscle force, it is necessary to collect measurements in a plethora of postures in case of substantial muscle redundancy. However, anisotropic MRE requires a structural and diffusion-tensor imaging scan in each posture, which is infeasible given the time constraints of MRI imaging. The objectives of this work were to develop a muscle force estimator with sufficient accuracy that would only require a limited set of postures, and to evaluate its effectiveness under a variety of measurement conditions. We developed a novel MRE-based muscle force estimator, which decouples shear wave speed into its active and passive components and solves for the slope and offset parameters, independently. We assessed the effectiveness of the proposed estimator under different simulated measurement conditions, with varying levels of noise, and compared it to the original MRE-based estimator. The proposed estimator results in a reduction in the estimation error for the offset parameter, for all muscles, without significant degradation in the estimation error for the slope parameter. However, the proposed muscle force estimator does not improve the goodness-of-fit or the cross-validation error compared to the original estimator. In conclusion, the proposed MRE-based muscle force estimator improves the estimation of muscle-specific parameters and may yield increased muscle force estimation performance.

关键词： Wrist Estimation error Force measurement Torque Force Muscles Biomedical measurement Time measurement Torque measurement Time factors

来源：评论

学校读者我要写书评

暂无评论

Design of a 3 Degree-of-Freedom Upper-Limb Active Exoskeleton with Cable-Driven Actuators for Neuromotor Rehabilitation 1

Design of a 3 Degree-of-Freedom Upper-Limb Active Exoskeleto...

引用

1st IEEE Colombian Caribbean Conference, C3 2023

作者： Dias, Eduardo Ulhoa, Pedro Andrade, Rafhael Universidade Federal Do Espírito Santo Department of Mechanical Engineering. Vitória Brazil Universidade Federal Do Espírito Santo Department of Electrical Engineering Vitória Brazil Universidade Federal Do Espírito Santo Graduate Program in Mechanical Engineering Vitória Brazil

ISBN: (纸本)9798350341799

Exoskeletons are wearable mechanisms which, parallel to the wearer's joints, modulate movements through active or passive torque application. While existing upper-limb exoskeletons offer benefits in strength augmentation and therapy, they often suffer from limited degrees of freedom and excessive bulk, hindering their utility in neuromotor rehabilitation. This study introduces a three degree-of-freedom active upper-limb exoskeleton optimized for neuromotor rehabilitation. Employing anthropometric data and rigorous kinematic analysis, the design accommodates elbow flexion/extension, forearm pronation/supination, and hand gripping. The upper limb dynamics, kinematics, and physiology were evaluated to provide adequate joint ranges of motion. Cable-driven actuators in the elbow and forearm joints were designed to provide low worn weight through the relocation of the motor units away from the user's joints. The result is a lightweight, compact exoskeleton that provides optimal conditions for neuromotor rehabilitation. Finally, a preliminary control strategy was tested using myoelectric signals to trigger motion. © 2023 IEEE.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

Estimation of Mediolateral Gait Postural Stability using Time-Series Pelvis Angular Velocities 11

Estimation of Mediolateral Gait Postural Stability using Tim...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Liu, Ziqi Kuroda, Tomohito Okamoto, Shogo Akiyama, Yasuhiro Tokyo Metropolitan University Department of Computer Science Hino Japan Shinshu University Department of Mechanical Engineering and Robotics Ueda Japan

ISBN: (纸本)9781665492324

Gait stability indices play an important role in both clinical and commercial applications and are effective for estimating an individual's fall risk. In general, the computation of gait stability indices requires motion-capture systems to measure the positions and angles of multiple body segments. If the stability indices can be estimated from the time-series data of a single body segment, they can be easier to access. We used principal motion analysis to estimate the margin of stability, which is a popular gait stability index, based on the time series of the angular velocities of the pelvis during walking. The linear combination of three principal motions could estimate the minimum margin of stability along the mediolateral direction with a correlation coefficient of 0.58. The angular velocities of the pelvis can be used to estimate gait stability independently or in conjunction with other kinematic information. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Development of a Portable Face Recognition System with GPS Integration Using Raspberry Pi

Development of a Portable Face Recognition System with GPS I...

引用

Computer Sciences, engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Muhammad Nurul Puji Winda Astuti Rahmanda Wulandari William Jonathan Edwards Telaumbanua Computer Engineering Department Automotive & Robotics Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Industrial Engineering Department Business Engineering Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

Face recognition systems are a rapidly evolving computer vision technology capable of accurately identifying faces. Additionally, the development of SBCs (Single Board Computers) has advanced significantly, enabling fast computational processing. The integration of face recognition systems on SBCs enables the creation of embedded face recognition systems. With the addition of GPS devices, it is possible to develop a mobile embedded face recognition system, which can contribute to enhancing infrastructure security and sustainability. This research demonstrates that A portable face recognition system based on Raspberry Pi 5 and a GPS module has been successfully developed. The system successfully detects target faces and able to send location coordinates through the Telegram application. Testing results show that the system's effective range is 1 to 4 meters, with an effective angle of 80° to 100° (from the left horizontal). The tests also indicate that systems without video output generally have higher FPS compared to systems displaying video.

关键词： Meters Computer vision Technological innovation Face recognition Streaming media Real-time systems Sustainable development Optimization Global Positioning System Testing

来源：评论

学校读者我要写书评

暂无评论

Learning to Detect Slip Through Tactile Estimation of the Contact Force Field and its Entropy Properties

SSRN

引用

SSRN 2024年

作者： Hu, Xiaohai Venkatesh, Aparajit Wan, Yusen Zheng, Guiliang Jawale, Neel Kaur, Navneet Chen, Xu Birkmeyer, Paul Department of Mechanical Engineering University of Washington United States Amazon Robotics United States

Slip detection during object grasping and manipulation plays a vital role in object handling. Visual feedback can help devise a strategy for grasping. However, for robotic systems to attain a proficiency comparable to humans, integrating artificial tactile sensing is increasingly essential, especially in consistently handling unfamiliar objects. We introduce a novel physics-informed, data-driven approach to detect slip continuously for control-oriented tasks. Our work leverages the inhomogeneity of tactile sensor readings during slip events to develop distinct features and formulates slip detection as a classification problem. We test multiple data-driven models on 10 common objects under different loading conditions, textures, and materials to evaluate our approach. The resulting best classification algorithm achieves a high average accuracy of 95.61%. Practical application in dynamic robotic manipulation demonstrates the effectiveness of the proposed real-time slip detection and prevention. © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Mechatronics Design of Wheeled Mobile Robotic System for Gutter Maintenance 30

Mechatronics Design of Wheeled Mobile Robotic System for Gut...

引用

30th IEEE International Conference on Electronics, Electrical engineering and Computing, INTERCON 2023

作者： Arbulu, Mario Arias, Geyni Iniguez, Brayan Dussan, Sofia Barreto, Ricardo Cornejo, Jose CORHUILA Mechatronics Engineering Program Colombia CORHUILA Industrial Engineering Program Colombia Robotics 4.0 R and D Department Colombia Universidad Nacional de Ingeniería Center for Space Emerging Technologies Lima Peru Universidad Tecnológica Del Perú Lima Peru

ISBN: (纸本)9798350315578

This paper deals with the challenges involved on roof building gutter maintenance robot design, from the problem statement of secure teleoperated semiautonomous navigation on confined gutter spaces, and the best selection of right mechatronics brush to remove the waste on gutter surface;Two concept design have been tested: Passive Brush with Parallel locomotion (PBP), and Active Brush Axial (ABA). The results on our development are shown, as following: secure robot lifting regulation, simulation environment, HMI to teleoperate, mechatronics design. Finally, some tests on simulations and current prototypes are shown, to validate our proposal, and the conclusion that the ABA design allows to remove until 85% gutter waste, instead of PBP design;furthermore, the ABA allows independent brush rotation velocity, instead of PBP design. © 2023 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

Electrochemically Modulated Metasurfaces

Electrochemically Modulated Metasurfaces

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Eaves-Rathert, Janna Kovalik, Elena Ugwu, Chibuzor Fabian Pint, Cary L. Valentine, Jason G. Department of Mechanical Engineering Vanderbilt University NashvilleTN37212 United States Interdisciplinary Materials Science Program Vanderbilt University NashvilleTN37212 United States Department of Mechanical Engineering Iowa State University AmesIA50011 United States

Electrochemical intercalation of lithium in titanium dioxide and silicon-based metasurfaces is used to initiate phase changes in a continuously tunable, reversible, and bistable manner for dynamic control over structu... 详细信息

ISBN: (纸本)9781957171258

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Nullspace Adaptive Identification of Plant and Actuator Model Parameters for Underactuated Ground Vehicles: Theory and Experimental Evaluation ⁎

引用

IFAC-PapersOnLine 2024年第28期58卷 1097-1102页

作者： Allan H. Elsberry Jeremy J. Dawkins Annie M. Mao Louis L. Whitcomb Department of Weapons Robotics and Control Engineering United States Naval Academy Annapolis MD 21401 USA Department of Mechanical Engineering Johns Hopkins University Baltimore MD 21218 USA

This paper reports a novel Nullspace Adaptive Identification (NSAID) algorithm to estimate plant and actuator model parameters for an underactuated ground vehicle with dynamics represented by a 3 degree-of-freedom second-order dynamic model, and reports an evaluation of its performance in simulation and experiments. Precise identification of ground vehicle plant and actuator model parameters is critical for physically realistic model-based simulation, control, navigation, and fault detection. However, ground vehicle plant model parameters, such as vehicle mass, moments of inertia, tire cornering stiffness and actuator model parameters such as motor torque constants are generally not possible to estimate a priori from first principles, and can change with varying payloads, configurations, and driving environments, and thus must be determined experimentally. Some parameter identification methods such as least squares regression depend on acceleration measurements, and most identification methods assume a priori knowledge of actuator parameters. In contrast, NSAID estimates plant and actuator parameters simultaneously, does not require acceleration measurements, can be utilized offline or online during vehicle operation, and can be applied with open or closed-loop control.

关键词： Nonlinear Adaptive Control Vehicle Dynamics Model Parameter Identification

来源：评论

学校读者我要写书评

暂无评论

HITTING THE GYM: REINFORCEMENT LEARNING CONTROL OF EXERCISE-STRENGTHENED BIOHYBRID ROBOTS IN SIMULATION

arXiv

引用

arXiv 2024年

作者： Schaffer, Saul Pamu, Hima Hrithik Webster-Wood, Victoria A. Mechanical Engineering Department Carnegie Mellon University United States Mechanical Engineering Department Biomedical Engineering Department McGowan Institute for Regenerative Medicine Robotics Institute Carnegie Mellon University United States

Animals can accomplish many incredible behavioral feats across a wide range of operational environments and scales that current robots struggle to match. One explanation for this performance gap is the extraordinary properties of the biological materials that comprise animals, such as muscle tissue. Using living muscle tissue as an actuator can endow robotic systems with highly desirable properties such as self-healing, compliance, and biocompatibility. Unlike traditional soft robotic actuators, living muscle biohybrid actuators exhibit unique adaptability, growing stronger with use. The dependency of a muscle’s force output on its use history endows muscular organisms the ability to dynamically adapt to their environment, getting better at tasks over time. While muscle adaptability is a benefit to muscular organisms, it currently presents a challenge for biohybrid researchers: how does one design and control a robot whose actuators’ force output changes over time? Here, we incorporate muscle adaptability into a many-muscle biohybrid robot design and modeling tool, leveraging reinforcement learning as both a co-design partner and system controller. As a controller, our learning agents coordinated the independent contraction of 42 muscles distributed on a lattice worm structure to successfully steer it towards eight distinct targets while incorporating muscle adaptability. As a co-design tool, our agents enable users to identify which muscles are important to accomplishing a given task. Our results show that adaptive agents outperform non-adaptive agents in terms of maximum rewards and training time. Together, these contributions can both enable the elucidation of muscle actuator adaptation and inform the design and modeling of adaptive, performant, many-muscle robots. © 2024, CC BY.

关键词： Biocompatibility

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：