检索结果-内蒙古大学图书馆

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

作者： Saeed Rahimi Hasan Jalali Mohammad Reza Hairi Yazdi Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Mechanical Engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Mechanical Engineering College of Engineering University of Tehran Tehran Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781665420952

This paper investigates the problem of actuator identification of a 3-DoF Delta parallel robot, by means of linear AutoRegressive Moving Average with eXogenous input (ARMAX) and nonlinear dynamic Neural Network AutoRegressive with eXogenous input (NN-ARX) methods. To this end, the ARMAX and NN-ARX approaches are used to develop a scheme which is capable of identifying a model for each actuator. Based on the ARMAX structure, an accurate model of the actuation system is derived. The model is then trained and tested using the data collected from a real robotic setup. Using a dynamic neural network capabilities, an identification and prediction scheme is designed for modeling the nonlinear dynamic behavior of the system. The NN-ARX is trained based on the collected data from the system, and the new trajectory data is used to validate both methods. By considering the results of experimental implementations, three servo motors are demonstrated to have different dynamical behavior which was expected to happen from the outset, due to uncertainty in fabrication of motors component and gearbox. In the identification and prediction stages, the Root Mean Square Errors (RMSE) index is used to validate and analyze the performance of each method using the validation data from new trajectories. In terms of predicting the output of the system, NN-ARX performed better than ARMAX with RMSE of 0.001441, compared to ARMAX with RMSE of 0.0886. Due to the high accuracy of the obtained models. thus they can be used in the design of motion controllers and modelling disturbances in the system.

关键词： Actuators Parallel robots Artificial neural networks Predictive models Mathematical models Trajectory Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

human robot interaction: Identifying Resembling Emotions Using Dynamic Body Gestures of robot

Human Robot Interaction: Identifying Resembling Emotions Usi...

引用

Artificial Intelligence (ICAI), International Conference on

作者： Sara Ali Faisal Mehmood Khawaja Fahad Iqbal Yasar Ayaz Muhammad Sajid Muhammad Baber Sial Muhammad Faiq Malik Kashif Javed Department of Robotics and Artificial Intelligence Human Robot Interaction Lab (SINES) Intelligent Field Robotics Lab (NCAI) National University of Sciences and Technology H-12 Islamabad Pakistan Department of Robotics and Artificial Intelligence National University of Sciences and Technology H-12 Islamabad Pakistan School of Automation Science and Electrical Engineering Beihang University Beijing China

Natural social interaction between a human and robot requires perception ability of robot for complex social behaviors and in turn displaying the learnt emotional behavior during interaction. The emotions expressed with body language are one of the key parameters during human-robot interaction (HRI). This research focuses on extending the concept of affective non-verbal human-robot interaction using full body gestures for closely resembling emotion in absence of intricate facial expressions. The movements of head, torso, legs, and arms are used to link body movements and gestures of a bi-pedal humanoid robot with 28 closely resembling emotions. Variation of speed, frequency, and joint angles of the robot are the key features used for expressing a specific emotion. This research uses Russell's circumplex model to define 8 primary emotional categories which are further grouped into closely associated emotions resembling each other. 33 participants were involved in experimentation to authenticate different emotions using body gestures of robot. Each participant performed 28 trials in which emotions were displayed at random to recognize the state of robot. The results showed an average accuracy of 79.69%. The study authenticates that perceived emotions are highly dependent on body movements, postures, and selected features. This design model can therefore be used for even conveying the closely resembling emotions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Imitation of human Head Motions, Blinks and Emotions by Nao robot: A Closed-Loop Approach

arXiv

引用

arXiv 2025年

作者： Rayati, Keyhan Feizi, Amirhossein Beigy, Alireza Shahverdi, Pourya Masouleh, Mehdi Tale Kalhor, Ahmad Louie, Wing-Yue Geoffrey Human and Robot Interaction Lab Electrical and Computer Engineering University of Tehran Tehran Iran Department of Electrical Engineering Shahrood University of Technology Shahrood Iran Intelligent Robotics Laboratory Oakland University Michigan United States

—This paper introduces a novel approach for enabling real-time imitation of human head motion by a Nao robot, with a primary focus on elevating human-robot interactions. By using the robust capabilities of the MediaPipe as a computer vision library and the DeepFace as an emotion recognition library, this research endeavors to capture the subtleties of human head motion, including blink actions and emotional expressions, and seamlessly incorporate these indicators into the robot’s responses. The result is a comprehensive framework which facilitates precise head imitation within human-robot interactions, utilizing a closed-loop approach that involves gathering real-time feedback from the robot’s imitation performance. This feedback loop ensures a high degree of accuracy in modeling head motion, as evidenced by an impressive R2 score of 96.3 for pitch and 98.9 for yaw. Notably, the proposed approach holds promise in improving communication for children with autism, offering them a valuable tool for more effective interaction. In essence, proposed work explores the integration of real-time head imitation and real-time emotion recognition to enhance human-robot interactions, with potential benefits for individuals with unique communication needs. © 2025, CC BY-NC-ND.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "DSTF: A diversified spatio-temporal feature extraction model for traffic flow prediction" [Neurocomputing 621 (2025) 129280] (Neurocomputing (2025) 621, (S0925231224020514), (10.1016/***.2024.129280))

引用

Neurocomputing 2025年 638卷

作者： Wang, Xing Wang, Xiaojun Huang, Faliang Zou, Fumin Liao, Lyuchao Zeng, Ruihao Fujian Normal University College of Computer and Cyber Security China Fujian Normal University Digital Fujian Institute of Big Data Security Technology China Nanning Normal University Guangxi Key Lab of Human-machine Interaction and Intelligent Decision China Fujian University of Technology Fujian Key Laboratory of Automotive Electronic and Electrical Drive Technology China The University of Sydney School of Civil Engineering Sydney Australia

The authors regret to inform that: (1) During the resubmission stage of the revised manuscript, in compliance with reviewers' recommendations to show standard deviations in the experimental results (In Section 5. Experiment implementation), a batch replacement operation (intended to replace "+" with "±" for data formatting) inadvertently replaced the "+" symbols in the mathematical formulas and the explanatory text with "±" symbols (In Section 3. Problem statement and Section 4. Methodology). (2) In proof stage, we sincerely apologize for failing to identify this issue during the final proofreading stage. Correction statement and details: As this error may affect readers' understanding, we request a corrigendum to rectify this error. In Section 3. Problem statement and Section 4. Methodology, all instances of "±" symbols within mathematical formulas and their explanatory text should be reverted to the original "+" symbols. The authors would like to apologize for any inconvenience caused. © 2025 The Authors

关键词：

来源：评论

学校读者我要写书评

暂无评论

A General Geometric Index for Solving the Forward Kinematics of Planar Parallel Manipulators

A General Geometric Index for Solving the Forward Kinematics...

引用

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

作者： Amir Hashemi Dastjerdi Maryam Valipour Mehdi Tale Masouleh School of Mechanical Engineering University of Shahid Rajaee Teacher Training University (SRTTU) 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: (纸本)9781665420952

In this paper, a new geometrical method is proposed to solve the forward kinematics of planar parallel manipulators exhibiting two translational and one rotational DOF which leads to high-order system polynomial expressions. The main idea has arisen from a geometrical interpretation of the intersection among the vertex space of each kinematic chain. From the type synthesis performed for planar parallel manipulators with identical kinematic structure, it has been revealed that the number of every possible configuration for this type of manipulators is eighteen, which the solution of the forward kinematic problem can be expressed using a univariate polynomial expression. However, among these eighteen configuration only six of them lead to high order polynomials and therefore do not have closedform solutions. The proposed method in this paper is based on an index representing the intersection of the circles which are extracted from the vertex space of each kinematic limb of the manipulator. In this approach, the orientation angle of the moving platform is selected from an interval; and based on the selected orientation angle, the circles obtained from the vertex space of each limb are determined. The forward kinematic solution happens where all the circles intersect at one common point where this geometrical phenomenon is expressed using the proposed index. In order to illustrate the performance of the proposed approach, three examples are solved. It should be noted that the foregoing method succeeded even in solving examples such as manipulators with six real solutions, manipulators with degenerate answers, which are reported in the literature as special cases.

关键词： Mechatronics Kinematics Manipulators Classification algorithms Indexes

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 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

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

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

Semantic Visual Simultaneous Localization and Mapping: A Survey

arXiv

引用

arXiv 2022年

作者： Chen, Kaiqi Xiao, Junhao Liu, Jialing Tong, Qiyi Zhang, Heng Liu, Ruyu Zhang, Jianhua Ajoudani, Arash Chen, Shengyong Institute of Computer Vision College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Human-Robot Interfaces and Interaction Lab Istituto Italiano di Tecnologia Genoa Italy National University of Defense Technology China Università di Genova Genoa Italy School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Institute of Computer Vision School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

Visual Simultaneous Localization and Mapping (vSLAM) has achieved great progress in the computer vision and robotics communities, and has been successfully used in many fields such as autonomous robot navigation and AR/VR. However, vSLAM cannot achieve good localization in dynamic and complex environments. Numerous publications have reported that, by combining with the semantic information with vSLAM, the semantic vSLAM systems have the capability of solving the above problems in recent years. Nevertheless, there is no comprehensive survey about semantic vSLAM. To fill the gap, this paper first reviews the development of semantic vSLAM, explicitly focusing on its strengths and differences. Secondly, we explore three main issues of semantic vSLAM: the extraction and association of semantic information, the application of semantic information, and the advantages of semantic vSLAM. Then, we collect and analyze the current state-of-the-art SLAM datasets which have been widely used in semantic vSLAM systems. Finally, we discuss future directions that will provide a blueprint for the future development of semantic vSLAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

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：