检索结果-内蒙古大学图书馆

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

作者： Parsa Namazian Mehdi Tale Masouleh Mohammad Reza Zakerzadeh Human and Robot Interaction Laboratory School of Mechanical Engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory School of Eletrical & Computer Engineenng University of Tehran Tehran Iran School of Mechanical Engineering University of Tehran Tehran Iran

This paper aims at a preliminary research on designing a hybrid mechanism inspired by human leg’s musculoskeletal architecture and locomotion capabilities. Complexity of the workspace solution in serial-parallel mechanisms limits the design approach. In order to have an estimation from the human leg geometry and reachable workspace, a dataset is collected from the human leg of 10 females and 10 males. In addition to the measurements done on the dimensions of this population, the reachable workspace of their leg is observed using MediaPipe pose estimation model. This is done by capturing full movement of the human leg for each person in front of two cameras. On the other hand, the musculoskeletal system of the human leg reveals that two serially attached parallel mechanisms are well-suited for the design. The upper mechanism, which is the thigh mechanism, includes 6 UPS links as the actuators, and a US constraint link to avoid elongation in the leg. Similarly, 3 UPS and a S constraint link form the lower mechanism. Two mathematical models based on geometric approaches are derived for the mechanisms. In order to reach a workspace fitted to that of human leg, an optimization process is performed on the mechanism. Due to the complexity of the whole model’s workspace, the optimization process is done on the upper mechanism to reach its maximum workspace. Based on the ratios between thigh and calf dimensions, the lower mechanism’s design parameters are obtained, and its workspace is verified to be optimal. Afterwards, a simple geometric calculation of the whole mechanism is done and compared with the results of workspace observation using MediaPipe. A brief simulation is done on the upper mechanism in two different movements in order to select suitable actuators based on the required forces. Finally, forward kinematics problem of the mechanism is solved and validated by performing simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing Controller for the 2-DoF Cable-Driven Serial robot with Variable Configuration based on Adaptive Neuro-Fuzzy Systems

Designing Controller for the 2-DoF Cable-Driven Serial Robot...

引用

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

作者： Vahid Bahrami Ahmad Kalhor Mehdi Tale Masouleh School of Electrical and Computer Engineering University of Tehran Human and Robot Interaction Laboratory Tehran Iran

ISBN: (纸本)9781665454537

This paper addresses the problem of actuation and design of a controller for a 2-DoF Cable-Driven Serial Chain (CDSC) with variable configuration based on adaptive neuro-fuzzy systems. The mentioned structure uses several light cables to actuate rigid links of a passive planar serial robot, performing a 2-DoF motion pattern, which can apply tensile forces for moving the links and thus produce the necessary torque to track the desired reference model by the robot’s end-effector. Additionally, cable attachment point coordinates of the CDSC are considered variable configurations. So, a novel concept is expressed in the calculation of the CDSC’s Jacobian matrix. In this mechanism, upon formulating the sliding mode error dynamics, an Adaptive Neural Network (ANN) is used to cope with complex mathematical calculations of the CDSC dynamics. Then, the coordinates of cables are considered as variables that depend on the main states of the plant. These co-states are adaptively determined by applying an appropriate fuzzy system. As a result, an Adaptive Neuro-Fuzzy Controller (ANFC) algorithm is introduced for the mentioned redundant mechanism. Finally, by defining a new Cost of Redundancy (CoR), an optimal configuration of the cables is found, so the maximum Degrees of Redundancy (DoR) is obtained. The simulation results indicate that using the ANFC algorithm leads to a reduction of 2.23% in the CoR for the 2-DoF CDSC.

关键词： Adaptive systems Costs Torque Tracking robot kinematics Heuristic algorithms Simulation

来源：评论

学校读者我要写书评

暂无评论

Safe Deep Learning-Based Global Path Planning Using a Fast Collision-Free Path Generator

SSRN

引用

SSRN 2022年

作者： Chehelgami, Shirin Ashtari, Erfan Basiri, Mohammad Amin Masouleh, Mehdi Tale Kalhor, Ahmad Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran

In this research, a global path planning method based on recurrent neural networks by means of a new loss function is presented, which regardless of the complexity of the configuration space, generates the path in a relatively constant time. The new loss function is defined in such a way that in addition to learning the input data of the network, it creates an adjustable safety margin around the obstacles and ultimately creates a safe path. Moreover, a new global path planning method is also introduced, which is used to create the dataset needed to train the proposed neural network. The convergence of this method is mathematically proven and it is shown that this method can also produce a suboptimal path in a much shorter time than the common methods of global path planning reported in the literature. In short, the main purpose of this research consists in providing a method which can create a suboptimal, fast and safe path for a mobile robot from any random starting point to any random destination in a known environment. First, the proposed methods will be implemented for different two-dimensional environments consisting of convex and non-convex obstacles, considering the robot as a pointmass, and then it will be implemented in a 3D simulation environment, *** to classical global path planning algorithms, such as RRT and A*, the proposed approach demonstrates better performance in complex and challenging environments. © 2022, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vision-based robotic Grasping of Household Objects: A Practical Case Study

Autonomous Vision-based Robotic Grasping of Household Object...

引用

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

作者： Asal Roudbari Mahdi Dalvand Navid Pasiar Navid Asadi Mohammad Yousefi Mehdi Tale Masouleh Electrical Engineering Department Sharif University of Technology Tehran Iran Human & Robot Interaction Lab University of Tehran Tehran Iran Human & Robot Interaction Lab School of Electrical&Computer Engineering University of Tehran Tehran Iran

Autonomous robotic grasping has emerged as a valuable capability for automating everyday household tasks like table setting (bossing), cleaning, and meal preparation. Still, accurately detecting and manipulating diverse everyday objects in unstructured home environments remains a significant challenge. In this study, an integrated robotic system combining YOLOv8s-seg deep learning for object detection and segmentation with computer vision techniques to determine optimal grasping points is proposed. The accuracy of this model has also been compared with other models through their mAP0.5, mAP.05-.95, precision and recall. A custom dataset of over 1000 images containing common household objects was created, with manual annotation and augmentation to train the YOLOv8s-seg segmentation model. The approach processes input images to understand desired arrangements and identify target objects and their locations for grasping. The detected objects are localized using camera-to-robot calibration and aligned with estimated orientations from computer vision techniques. Extensive tests have proven that representative household objects in cluttered arrangements have a grasping success rate of over 90% using a 3DOF Delta Parallel robot with a 2-finger gripper guided entirely by visual perception. By overcoming real-world challenges like transparent and reflective materials, the perception-guided robots provide precise and efficient robotic grasping in unstructured home environments. This integrated approach combines robust perception and localization, providing promising evidence for reliable automation of repetitive household organization tasks 1 . 1 A video of real-time grasp performance is uploaded as supplementary material.

关键词：

来源：评论

学校读者我要写书评

暂无评论

State Definition in Deep Reinforcement Learning: A Smoothness Index Approach

State Definition in Deep Reinforcement Learning: A Smoothnes...

引用

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

作者： Soroosh Dehdasthian Ahmad Kalhor Mehdi Tale Masouleh School of Electrical and Computer Engineering Department Human and Robot Intraction Laboratory University of Tehran

In the pursuit of developing autonomous agents capable of learning optimal behaviors, reinforcement learning has emerged as a foundational frame-work. This paper introduces a novel approach for state definition in deep reinforcement learning systems, with a focus on solving pixel-based control scenarios. The proposed frame-work harnesses the capabilities of Convolutional Variational Auto-Encoders to extract compact and meaningful latent representations from high-dimensional pixel observations. These representations serve as the foundation for constructing an efficient state space for reinforcement learning agents. To further enhance the state construction process, the concept of the Smoothness Index is introduced. Smoothness index acts as a criterion for feature selection within the latent space, facilitating the identification of the most relevant and informative states. Demonstrating the effectiveness of iterative smoothness index-based forward selection, this process notably compresses the observation space while retaining essential information. This compression enables the creation of more efficient reinforcement learning agents. The procedure involves collecting and preprocessing observation data given by the OpenAI Gym car racing environment, encoding observations using a convolutional variational auto-encoder, and iteratively selecting features based on smoothness index. Subsequently, the Proximal Policy Optimization algorithm is employed as a policy-based controller to evaluate the effectiveness of the proposed frame-work. Results indicate that this approach yields a remarkably compact state space that either maintains or enhances reinforcement learning agent performance. This innovative frame-work paves the way for the development of more efficient and adaptive reinforcement learning agents in real-world image-based applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In Vivo Bioelectronic Nose Based on a Bioengineered Rat for the Explosive Odors with Benzene Ring Detection and Identification 24

In Vivo Bioelectronic Nose Based on a Bioengineered Rat for ...

引用

11th International Conference on Biomedical and Bioinformatics engineering, ICBBE 2024

作者： Ma, Jing Wang, Yimeng Yang, Jun Sun, Biao Yang, Qing Zheng, Chenguang Academy of Medical Engineering and Translational Medicine Medical College Tianjin University Tianjin China College of Precision Instruments & Optoelectronics Engineering Tianjin University Tianjin China School of Electrical and Information Engineering Tianjin University Tianjin China Tianjin Key Laboratory of Brain Science and Neuroengineering Tianjin China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin China

ISBN: (纸本)9798400718274

Accidents caused by explosives occur frequently, which seriously threaten people's lives and health, so it is urgent to develop new technologies for sensitively and rapidly detecting trace explosives. In this study, a bioengineered rat with the olfactory receptor (OR3) overexpression in the olfactory epithelium (OE) was successfully developed, and the unique features of three representative explosives (NT, DNT, and TNT) were conducted by recording electrophysiological-responsive signals from the olfactory bulb (OB) with implanted multichannel microelectrodes during awake-state-independent sniffing behavior induced by explosives and non-explosives. These three explosives were regarded as goal odors, while citral and air were no-goal odors. The analysis of local field potential (LFP) power changes revealed that, goal, and no-goals could be distinguished in both the vector group and the OR3 group at concentrations as low as 10-12 mol/L, and the classification performance of the OR3 group was superior to that of the vector group overall. Our findings suggest that OR3 bioengineered rats can reliably and accurately identify trace explosives, which provides a novel approach for detecting and identifying explosives with promising applications in odor discrimination in complex environments. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Electronic nose

来源：评论

学校读者我要写书评

暂无评论

SIVD: Dataset of Iranian Vehicles for Real-Time Multi-Camera Video Tracking and Recognition

SIVD: Dataset of Iranian Vehicles for Real-Time Multi-Camera...

引用

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Farbod Siahkali Seyed Amirmahdi Alavi Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Human and Robot Interaction Laboratory School of Computer Science Islamic Azad University Central Tehran Branch Tehran Iran

ISBN: (纸本)9781665476249

In this paper, a new publicly available 1 web-Scraped Iranian Vehicle Dataset (SIVD) for simultaneous real-time vehicle tracking and recognition is proposed. The datasets provided for Iranian cars in the literature have two fundamental problems. First, the lack of images from different angles, and second, the small number of classes compared to the dispersion of car models in the real world. Therefore, for the purposes of this paper, Iranian vehicle images from car sales websites are collected, and the SIVD dataset is proposed which contains 29 classes and 36,705 images. This paper aims at developing a classification network for Iranian vehicle recognition and implement a real-time tracking system using the YOLOv5 network to perform real-time vehicle model recognition and tracking tasks simultaneously. The ResNet50 achieved an accuracy of 99.29%, the highest among the investigated classification networks. 1 https://***/Farbod-Siahkali/Iranian-Vehicle-Tracking-and-Recognition

关键词： Representation learning Image recognition Video tracking Machine learning algorithms Neural networks Real-time systems Automobiles

来源：评论

学校读者我要写书评

暂无评论

Deep-HFID: Deep Neural Network Based Hands and Face bio-metric Identification System Using Metric Learning

Deep-HFID: Deep Neural Network Based Hands and Face bio-metr...

引用

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

作者： Zahra Parvin Ashtyani Sara Ghanbari Navid Zare Mehdi Tale Masouleh Ahmad Kalhor School of Electrical and Computer Engineering Human and Robot Interaction Laboratory University of Tehran Tehran Iran School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781665454537

This paper presents a device for person identification based on hand bio-metrics. The main objective of a person recognition device is to perform accurate identification at a reasonable production cost. The so-called Deep-HFID device is designed to meet these objectives as well as to provide users with ease of use. For the purpose of identifying individuals, this device uses hand and face bio-metrics. In terms of dimensions, this device has been designed to facilitate the use of a variety of individuals. For ease of deployment, the Deep-HFID system relies on a server for most of its processes. The routine tasks, like showing the graphical user interface are handled by a Raspberry Pi board. A dataset from the palm side of both hands from 110 individuals has been created. Using transfer learning, the six pre-trained state-of-the-art neural network architecture was fine-tuned and calibrated based on the F1 score and precision criteria. An augmented dataset containing samples from the palm side of 30 individuals with between fingers angles variation is collected. By applying the main and augmented dataset and using the center-based separation index as a complexity measure algorithm to rank pre-trained deep neural networks, a compression on the last layer of the best performed neural network, EfficientNetV2B1, is done which results in a more robust system without reducement in accuracy.

关键词： Performance evaluation Training Face recognition Neurons Liquid crystal displays Libraries Servers

来源：评论

学校读者我要写书评

暂无评论

Collaborative Multi-Agent Reinforcement Learning Control of Parallel robots

Collaborative Multi-Agent Reinforcement Learning Control of ...

引用

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

作者： Amirhossein Afkhami Ardekani Mehdi Tale Masouleh Mohammad Reza Hairi Yazdi 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

ISBN: (纸本)9781665454537

In this paper, a novel algorithm based on Multi-Agent Reinforcement Learning for controlling parallel robots has been suggested. The dynamic models of parallel robots are complex and full of uncertainties, and deriving them requires deep knowledge of the mechanism of the robot. Therefore, the proposed algorithm is designed model-free to be independent of prior knowledge about the system from the outset. Moreover, this algorithm comprises two primary components, making it efficient in training and convergence. The proposed algorithm takes each loop or limb in parallel robots as a separate agent. These agents then learn to collaborate to fulfill the robot’s defined task by producing appropriate control signals from a decentralized point of view. For studying the performance of the proposed algorithm, a 3-DOF parallel robot called Agile Eye is taken into account as a case study which is simulated in CoppeliaSim simulation environment for the task of reference tracking. Two other controllers, including the classic Proportional Integral Derivative (PID) controller and the single-agent counterpart of the suggested algorithm, have been implemented for a better performance comparison of the proposed algorithm. Using the Root Mean Square Error (RMSE) index, the recommended algorithm with an RMSE value of 0.0553 is superior to its single-agent counterpart with an RMSE of 0.1105. On the other hand, the proposed algorithm is inferior to the PID controller with an RMSE of 0.0275, mainly due to the fact that the PID Controller is in velocity control mode, while the proposed algorithm manipulates the robot in torque control mode, which is less stable.

关键词： Training Parallel robots Torque Uncertainty Heuristic algorithms Torque control Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Motion Controller based on NN-ARX and ARMAX Actuator Identification for 3-DoF Delta Parallel robot

Experimental Study on Motion Controller based on NN-ARX and ...

引用

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

作者： Hasan Jalali Hossein Damavandi Ahmad Kalhor Mehdi Tale Masouleh Human and Robot Interaction Laboratory School of Electrical and Computer Engineering University of Tehran Tehran Iran Faculty of Computer Engineering and Information Technology Sadjad University Mashhad Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

Today, system identification plays a pivotal role in control science and offering a myriad of applications. This paper places its focus on the identification of actuator models within real-world delta robots for informing controller design. Two identification methods, namely NN-ARX and ARMAX, have been employed to extract the dynamic characteristics of the robot actuators, resulting in dynamic models of these integral components being derived. These dynamic models have been utilized in simulations for controller design, and due to the disparities in the identification models, distinct controllers have been realized. Subsequently, these controllers have been practically implemented on delta robots, and their performances have been subjected to a comprehensive comparative analysis. The results demonstrate that controllers integrating the identified actuator models outperformed those designed without the incorporation of the identification models. In practice, the implementation of controllers based on NN-ARX yielded the most favorable results among all the tested controllers. This research not only underscores the importance of accurate actuator models in control system design but also highlights the superior performance of neural network-based controllers in real-world robotic applications. In particular, the practical results of NN-ARX-based controllers were able to achieve significantly lower RMSE of 2.3562, 1.9531, and 2.1185 for the three motors, respectively, as opposed to the 4.1369, 3.0125, and 3.0363 achieved by the ARMAX-based controllers.

关键词：

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：