检索结果-内蒙古大学图书馆

IEEE Workshop on Advanced robotics and its Social Impacts, ARSO

作者： Yuwei Du Xin Zhang Mattia Leonori Pietro Balatti Jing Jin Qiang Wang Arash Ajoudani Department of Control Science and Engineering School of Astronautics Harbin Institute of Technology Heilongjiang China Human-Robot Interfaces and Interaction (HRI2) Lab Istituto Italiano di Tecnologia Genova Italy State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

Cooperative human-robot systems are the key technology to improve efficiency in agile production. In this work, a novel on-shoulder supernumerary robotic limb (SRL) is developed for human-robot collaboration. The SRL system is mainly composed of a 6-degree-of-freedom (DoF) lightweight robotic arm and a wearable and adjustable base, which allows different users to regulate the arm installation position to fit their physical dimensions and expand their workspace. As the SRL is close to the human head, nullspace-based collision avoidance is designed to achieve safe motion planning. Meanwhile, a Kalman filter is designed to actively predict human hand position and yield anticipatory motion control of our SRL in handover tasks. Furthermore, we conduct a bi-directional handover case study to verify the capability of the SRL system and the effectiveness of the proposed collaborative handover. The result shows that our control method can guarantee intuitive and natural handover behavior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

robots Learn Visual Pouring Task Using Deep Reinforcement Learning with Minimal human Effort

Robots Learn Visual Pouring Task Using Deep Reinforcement Le...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Homayoun Moradi Mehdi Tale Masouleh Behzad Moshiri Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781665420952

In this paper, the entire pipeline for teaching a robot to perform the visual pouring task is addressed with a minimal human supervision. In this task the robot’s arm that carrying a glass, and the target container are initialized in an arbitrary position. The reinforcement learning approach is employed without the use of reward engineering where the reward function is approximated by a Convolutional Neural Network. This network, which is trained on a little set of goal images (positive samples), takes a raw RGB image as input. In data gathering step, only goal conditions are established by an expert, and positive samples are collected in a self-supervised manner. The major contribution of this paper consists in using only the RGB image, without 3D analysis which is not possible by classical approaches, and self-supervised positive sample gathering which has not been addressed in recent RL studies. Moreover, the deep metric learning approach is utilized to train the reward network in order to obtain increased robustness against unseen negative samples. The foregoing is applied since this approach classifies the negative samples as ignore class and prevents the network from being fooled by the RL algorithm. Soft Actor-Critic is the RL algorithm employed in this study. A fixed monocular camera is the single sensor used for perception and RGB image is used as the representation of the state for action selection, value estimation, and input of reward network. The action-space is defined such a way that reduces convergence time, and in this approach, the policy network generates the desired 3D position in each step. This method of defining the action-space resulted in a reduction in training steps from 100k-1M to 1k. The provided method is compared to joint-based action-space and sparse-reward to validate the good effect of this combination of action-space and reward , i.e., position-based action-space, and continuous reward. Some experiments are designed as case studies

关键词： Training Visualization Three-dimensional displays Mechatronics Pipelines Reinforcement learning robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Extraction method for fluorescence information from droplet digital PCR images

引用

Guangxue Jingmi Gongcheng/Optics and Precision engineering 2022年第7期30卷 821-829页

作者： Li, Shanshan Wang, Zichao Yu, Chengzhuang Wei, Chunyang Li, Junwei School of Mechanical Engineering Hebei University of Technology Tianjin300401 China Hebei Key Laboratory of Robotic Sensing and Human-Robot Interactions Tianjin300130 China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin300132 China Institute of Biophysics Hebei University of Technology Tianjin300401 China

Droplet digital polymerase chain reaction (ddPCR) is one of the main methods used in nucleic acid detection. Counting the droplets in ddPCR experiments can be difficult if the number of droplets is too high or low, the fluorescence intensity is uneven, or the droplets are too closely arranged. We propose an image analysis method in which the image information is collected via the gray traversal method and droplets are classified and counted by differential analysis. Noise is removed from the image using the convolution algorithm, and the gray contrast of the image is enhanced by gray distribution equalization. The image is then converted to binary form by the gray traversal method with the geometric conditions taken as screening conditions, and the number of droplets is counted by differential analysis. Experiments with human gDNA (genomic DNA) as a detection sample, with approximately 20 000 droplets, showed an average detection accuracy of 99.36 % as compared to those conducted using commercial instrument algorithms or similar, with an average improvement of 2.24 % and 2.53 %, respectively, in the detection accuracy. The developed method can therefore be considered to provide reliable results and is suitable for use in ddPCR experiments. © 2022, Science Press. All right reserved.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Reconstructing 3-D Graphical Model Using an Under-Constrained Cable-Driven Parallel robot

Reconstructing 3-D Graphical Model Using an Under-Constraine...

引用

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Soroush Zare Mohammad Ghanatian Mohammad Reza Hairi Yazdi Mehdi Tale Masouleh School of Mechanical Engineering Human and Robot Interaction Laboratory University of Tehran Tehran Iran School of Mechanical Engineering University of Tehran Tehran Iran School of Electrical and Computer Engineering Human and Robot Interaction Laboratory University of Tehran Tehran Iran

ISBN: (数字)9781728186290

ISBN: (纸本)9781728186306

In this paper, a novel application of an under-constrained cable-driven parallel robot is introduced. By this application, the 3D model of any object with any size limited to the workspace of the robot can be reconstructed, which is a definite asset for creating the 3D model in such an easy and cost-efficient way despite other methods like a laser scanner. The most significant problem of an under-constrained cable-driven robot is the orientations of the end-effector which cannot be controlled regardless of its position, i.e., the orientation and position of the end-effector are not independent. In this paper, the foregoing problem was solved by using a stabilizer to capture a video in prescribed orientations. The results demonstrate that the end-effector can be controlled with high precision by a PID controller to reconstruct the 3D model of an object based on the captured videos of a camera which is mounted on the end-effector of the robot. In this paper, the object is a social robot called Sanbot that has a shiny surface, which decreases the 3D model reconstruction precision. However, the results reveal that the 3D model of the Sanbot robot has a very clear view, and the experimental results confirm the efficiency of the proposed method. This method provides an easy way to reconstruct the 3D model of an object which cannot be reconstructed by other methods.

关键词： Solid modeling Parallel robots Three-dimensional displays robot vision systems Cameras End effectors Sports

来源：评论

学校读者我要写书评

暂无评论

Kinematic Analysis of an Under-constrained Cable-driven robot Using Neural Networks

Kinematic Analysis of an Under-constrained Cable-driven Robo...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Soroush Zare Morteza Shahamiri Haghighi Mohammad Reza Hairi Yazdi Ahmad Kalhor Mehdi Tale Masouleh School of Mechanical Engineering Human and Robot Interaction Laboratory University of Tehran Tehran Iran School of Electrical and Computer Engineering Human and Robot Interaction Laboratory University of Tehran Tehran Iran School of Mechanical Engineering University of Tehran Tehran Iran

ISBN: (数字)9781728172965

ISBN: (纸本)9781728172972

In this paper, three types of neural networks including, multilayer perceptron, radial basis function, and Local Linear Model Trees, are considered based on adaptability with the significant behavior of data to solve the forward and inverse kinematics of the under-constrained cable-driven parallel robot. The practical workspace of the robot is a rectangular cube with dimensions of 360cm × 220c× 160cm. Forward kinematics problem of the under-constrained cable-driven parallel robot is challenging to solve by reason of complexity and nonlinearity of the robot kinematic equations. The typical approach utilizes a numerical method to solve these equations, which are computationally expensive and very time-consuming. Resorting to the neural network approaches results in the feasible orientation, which confirms that all the cables are in tension. The trained neural network gives a feasible inverse kinematic problem solution and the running time of the optimal trained neural network in the control loop, obtained about 12 microseconds, pales in comparison to the sampling time of the control loop that facilitates the real-time control of the robot. Obtained results reveal that the multilayer perceptron has the mean average error order of about 2 millimeters for the position and 0.78 degrees for orientation, which makes a case for precise control in the high-speed motion of the robot.

关键词： Artificial neural networks robots Mathematical model Parallel robots Neural networks Kinematics Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of Adaptive and Sliding Mode Control for a 3-DOF Delta Parallel robot

Design and Evaluation of Adaptive and Sliding Mode Control f...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Faraz Abed Azad Saeed Rahimi Mohammad Reza Hairi Yazdi Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Mechanical Engineering University of Tehran Tehran Iran School of Mechanical Engineering College of Engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (数字)9781728172965

ISBN: (纸本)9781728172972

In this paper, simulation, kinematics analysis, and control of a 3-DOF Delta parallel robot have been investigated. Delta parallel robots are one of the most popular manipulators for industrial applications. The kinematic equations of the robot have been established by the screw theory, in which, the position and velocity analyses have been carried out. In SimScape simulation environment, the kinematic model of the robot has been verified and subsequently, an inverse kinematic model was adopted for control purposes. In order to improve the tracking ability of the robot, three important control approaches, consisting in PID, adaptive control, and a Sliding Mode Control (SMC) have been implemented. Afterwards, the effectiveness of each approach has been investigated by employing the root mean square error (RMSE) index. By comparing the obtained index values, the SMC demonstrates the best performance with the RMSE value of 0.4188 in comparison to other methods. Simulation results were illustrated to show the ability of the controllers to reject white noise disturbance added to the system's input signals.

关键词： robots Kinematics Mathematical model Service robots Fasteners Actuators Parallel robots

来源：评论

学校读者我要写书评

暂无评论

Organization and understanding of a tactile information dataset tacact during physical human-robot interactions

arXiv

引用

arXiv 2021年

作者： Wang, Peng Liu, Jixiao Hou, Funing Chen, Dicai Xia, Zihou Guo, Shijie school of Mechanical Engineering Hebei University of Technology China School of Academy for Engineering&Technology Fudan University China Hebei Key Laboratory of Smart Sensing and Human-Robot Interaction Hebei University of Technology Tianjin300132 China

Advanced service robots require superior tactile intelligence to guarantee human-contact safety and to provide essential supplements to visual and auditory information for human-robot interaction, especially when a robot is in physical contact with a human. Tactile intelligence is an essential capability of perception and recognition from tactile information, based on the learning from a large amount of tactile data and the understanding of the physical meaning behind the data. This report introduces a recently collected and organized dataset "TacAct" that encloses real-time pressure distribution when a human subject touches the arms of a nursing-care robot. The dataset consists of information from 50 subjects who performed a total of 24,000 touch actions. Furthermore, the details of the dataset are described, the data are preliminarily analyzed, and the validity of the collected information is tested through a convolutional neural network LeNet-5 classifying different types of touch actions. We believe that the TacAct dataset would be more than beneficial for the community of human interactive robots to understand the tactile profile under various circumstances. Copyright © 2021, The Authors. All rights reserved.

关键词： human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Hybrid Nucleic Acid Detection Approach for Ion Concentration Polarization Enabled Polymerase Chain Reaction with Reduced Cycle Numbers

SSRN

引用

SSRN 2024年

作者： Yu, Chengzhuang Li, Junwei Meng, Jiyu Qiu, Xinchen Bu, Tianxi Dai, Shijie Li, Shanshan Hebei Key Laboratory of Robotic Sensing and Human-robot Interactions School of Mechanical Engineering Hebei University of Technology Tianjin300132 China Institute of Biophysics School of Science Hebei University of Technology Tianjin300401 China College of Mechanical Engineering Tianjin University of Science and Technology Tianjin300222 China Arizona College of Technology Hebei University of Technology Tianjin300132 China School of Energy and Environmental Engineering Hebei University of Technology Tianjin300132 China Engineering Research Center of the Ministry of Education for Intelligent Rehabilitation Equipment and Detection Technologies Hebei University of Technology Tianjin300132 China

Polymerase chain reaction (PCR) plays important roles in the detection and quantification of nucleic acid targets. To cut-off the detection time, and also to reduce any potential by-products during the thermal cycles, it is required to keep the cycle numbers as few as possible. Here, in this work, a hybrid PCR microfluidic device is proposed to perform a PCR test with only 25 thermal cycles, which are much lower than 35 or 40 cycles in standard operations. With a novel hybrid design, the target nucleic acid molecules were amplified by 25 thermal cycles to avoid any potential by-products. And then the amplified nucleic acid molecules were actively enriched by ion concentration polarization (ICP) effects to increase the local concentration significantly. Owe to the hybrid function of "amplification and active concentration", the PCR- ICP device enables the nucleic acid detection more credible and allows to take a faster PCR test with less thermal cyclings. As a demonstration, meat adulteration experiments were taken to show the sensitivity and lower limit of detection of the hybrid device, verifying the performance of the proposed method. © 2024, The Authors. All rights reserved.

关键词： Polymerase chain reaction

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication of a Flexible Pressure-Sensitive Insole Based on Barometric Tactile Sensors

Design and Fabrication of a Flexible Pressure-Sensitive Inso...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Arsalan Amralizadeh Trifa Marjani Mehdi Tale Masouleh Ahmad Kalhor Human & Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Human & Robot Interaction Laboratory University of Tehran Tehran Iran

ISBN: (数字)9781728172965

ISBN: (纸本)9781728172972

Plantar pressure measurement plays an important role in gait analysis which is a multidisciplinary field of study in medicine, rehabilitation, sports and robotics. The design and fabrication procedure of a novel pressure-sensitive shoe insole instrument is described in this study. The usage of this instrument is in sensing and real-time monitoring of the force pattern applied to the foot during gait. This system consists of a flexible circuit board with ten soft force sensing elements mounted on it, a custom data pre-process unit, a wireless transmission unit and a software for data monitoring. The soft force sensing components are designed based on barometer sensors covered by silicone layer in a specified shape to obtain about 300N supportable force range applied on each element. In order to evaluate the reliability and effectiveness of the proposed system, a healthy subject executed some preliminary tests during both static and dynamic activities. Conforming to the primitive results, the insole platform presented a rapid and accurate response in measurement of reaction force during different experimental attitudes. Thereupon, the fabricated insole is comfortable to wear, lightweight enough to use in daily activities simultaneously and it is a feasible instrument for plantar pressure mapping. Moreover, variety of parameters could be obtained by processes on the collected data and be used in related studies such as activity recognition or gait disorder detection.

关键词： Sensors Force Tactile sensors Foot Data visualization Software Monitoring

来源：评论

学校读者我要写书评

暂无评论

Kinematic and Dynamic Analysis of 3-DOF Delta Parallel robot Based on the Screw Theory and Principle of Virtual Work 5

Kinematic and Dynamic Analysis of 3-DOF Delta Parallel Robot...

引用

5th IEEE Conference on Knowledge Based engineering and Innovation, KBEI 2019

作者： Azad, Faraz Abed Reza Hairi Yazdi, Mohammad Masouleh, Mehdi Tale Human Robot Interaction Laboratory University of Tehran Tehran Iran School of Mechanical Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781728108728

The linear form of dynamic equation of parallel robots can be used to implement a wide variety of nonlinear adaptive control schemes in real time. Also, in parallel manipulators, linearizing the complex dynamic equation of motion is time consuming as well as complicated, but it is highly rewarding, since it can contribute to the achievement of fast and precise dynamic performance capabilities of the foregoing manipulators. Therefore, in this paper, instead of finding the nonlinear form of the dynamic equation of delta parallel robot by means of virtual work method, a linear form of the dynamic equation is calculated. To this end, kinematic analysis has been performed by resorting to the screw theory, as it provides more compact formulation of Jacobian matrices and facilitates the employment of virtual work principle. After finding the Jacobian matrices of input-output, and the Jacobian matrices between each link and end-effector's kinematics parameters, the full dynamic equation of motion of robot has been written. The twists comprising the equation has been determined separately and linear form of dynamic equation of robot has been computed. Afterwards, the SimMechanics model of 3-DOF. Delta parallel robot has been constructed and a simulation is performed in order to verify the validity of proposed equations of motion, and the corresponding error of computed torques of actuators comparing with Simscape's direct results is given. © 2019 IEEE.

关键词： Kinematics

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：