检索结果-内蒙古大学图书馆

Sustainable Technologies for Industry 4.0 (STI), International Conference on

作者： Abdul Monaf Chowdhury Ahsan Imran Md Mehedi Hasan Dept. of Robotics and Mechatronics Engineering University of Dhaka Bangladesh

Unmanned aerial vehicles (UAVs) have emerged as a transformative technology for human action recognition, providing a birds-eye view and unlocking new possibilities for precise and comprehensive support in surveillance systems. While substantial advances in ground-based human action recognition have been achieved, the unique characteristics of UAV footage present new challenges that require tailored solutions. Specifically, the reduced scale of humans in aerial perspectives necessitates the development of specialised models to accurately recognize and interpret human actions. Our research focuses on modifying the well-established C3D model and incorporating Fast Fourier Transform (FFT)-based object disentanglement (FO) and space-time attention (FA) mechanisms. By leveraging the power of FFT, our model effectively disentangles the human actors from the background and captures the spatio-temporal dynamics of human actions in UAV footage, enhancing the discriminative capabilities and enabling accurate action recognition. Through extensive experimentation on a subset of the UAV-Human dataset, our proposed FFT-UAVNet (m-C3D+FO&FA+FC) model demonstrates remarkable improvements in performance. We achieve a Top-1 accuracy of 64.86% and a Top-3 accuracy of 83.37%, surpassing the results obtained by the standard C3D and X3D methods, which achieve only a Top-1 accuracy of 28.05% and 31.33%, respectively. These findings underscore the efficacy of our approach and emphasize the significance of the proposed model for UAV datasets in maximizing the potential of UAV-based human action recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unleashing the potential of morphotropic phase boundary based hybrid triboelectric–piezoelectric nanogenerator

引用

Journal of Materiomics 2024年第4期10卷 792-802页

作者： Sugato Hajra Aneeta Manjari Padhan Basanta Kumar Panigrahi Phakkhananan Pakawanit Zvonko Jagličić Naratip Vittayakorn Yogendra Kumar Mishra Sanghoon Lee Hoe Joon Kim Department of Robotics and Mechatronics Engineering Daegu Gyeongbuk Institute of Science and TechnologyDaegu42988Republic of Korea Department of Electrical Engineering Siksha O Anusandhan UniversityBhubaneswar751030India Synchrotron Research and Applications Division Synchrotron Light Research InstituteNakhon Ratchasima30000Thailand Institute of Mathematics Physics and Mechanics&Faculty of Civil and Geodetic EngineeringUniversity of LjubljanaJadranska191000LjubljanaSlovenia Advanced Materials Research Unit Department of ChemistrySchool of ScienceKing Mongkut's Institute of Technology LadkrabangBangkok10520Thailand Mads Clausen Institute NanoSYDUniversity of Southern DenmarkAlsion 26400SønderborgDenmark Robotics and Mechatronics Research Center Daegu Gyeongbuk Institute of Science and Technology(DGIST)Daegu42988Republic of Korea

Morphotropic phase boundary(MPB)-based ceramics are excellent for energy harvesting due to their enhanced physical properties at phase boundaries,broad operating temperature range,and ability to customize properties for efficient conversion of mechanical energy into electrical *** this work,Bi_(1–x)Na_(x)Fe_(1–x)Nb_(x)O_(3)(x=0.20,0.30,0.32 and 0.40,BNFNO abbreviation)based ceramics were synthesized using a solid-state route and blended with Polydimethylsiloxane(PDMS)to achieve flexible *** material characterization and energy harvesting were performed by designing a hybrid piezoelectric(PENG)-triboelectric(TENG)*** voltage and current of PENG,TENG,and hybrid bearing same device area(2 cm×2 cm)were recorded as 11 V/0.3μA;60 V/0.7μA;110 V/2.2μ*** strategies for enhancing the output performance of the hybrid device were evaluated,such as increased surface area(creating micro-roughness and porous morphology)and increasing electrode size and multi-layer hybrid device *** self-powered acceleration monitoring was demonstrated using the hybrid ***,the low-frequency-based wave energy is converted into electrical energy,confirming the usage of hybrid PENG-TENG devices as a base for battery-free sensors and blue energy harvesting.

关键词： Lead-free Acceleration Wave energy Morphotropic

来源：评论

学校读者我要写书评

暂无评论

A Gaze-Speech System in Mixed Reality for Human-Robot Interaction

A Gaze-Speech System in Mixed Reality for Human-Robot Intera...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： John David Prieto Prada Myung Ho Lee Cheol Song Department of Robotics and Mechatronics Engineering DGIST Daegu South Korea

Human-robot interaction (HRI) demands efficient time performance along the tasks. However, some interaction approaches may extend the time to complete such tasks. Thus, the time performance in HRI must be enhanced. This work presents an effective way to enhance the time performance in HRI tasks with a mixed reality (MR) method based on a gaze-speech system. In this paper, we design an MR world for pick-and-place tasks. The hardware system includes an MR headset, the Baxter robot, a table, and six cubes. In addition, the holographic MR scenario offers two modes of interaction: gesture mode (GM) and gaze-speech mode (GSM). The input actions during the GM and GSM methods are based on the pinch gesture and gaze with speech commands, respectively. The proposed GSM approach can improve the time performance in pick-and-place scenarios. The GSM system is 21.33 % faster than the traditional system, GM. Also, we evaluated the target- to-target time performance against a reference based on Fitts' law. Our findings show a promising method for time reduction in HRI tasks through MR environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disaster Area Recognition from Aerial Images with Complex-Shape Class Detection

Disaster Area Recognition from Aerial Images with Complex-Sh...

引用

IEEE International Workshop on Safety, Security, and Rescue robotics (SSRR)

作者： Rubén González-Navarro Dahui Lin-Yang Ricardo Vázquez-Martín Alfonso Garcia-Cerezo Robotics and Mechatronics Group Institute of Mechatronics Engineering and Cyber-physical Systems University of Malaga Spain

This paper presents a convolutional neural network (CNN) model for event detection from Unmanned Aerial Vehicles (UAV) in disaster environments. The model leverages the YOLOv5 network, specifically adapted for aerial images and optimized for detecting Search and Rescue (SAR) related classes for disaster area recognition. These SAR-related classes are person, vehicle, debris, fire, smoke, and flooded areas. Among these, the latter four classes lead to unique challenges due to their lack of discernible edges and/or shapes in aerial imagery, making their accurate detection and performance evaluation metrics particularly intricate. The methodology for the model training involves the adaptation of the pre-trained model for aerial images and its subsequent optimization for SAR scenarios. These stages have been conducted using public datasets, with the required image labeling in the case of SAR-related classes. An analysis of the obtained results demonstrates the model's performance while discussing the intricacies related to complex-shape classes. The model and the SAR datasets are publicly available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Practical and Low-Cost Grasping Detection Module for Multi-Fingered Robotic Hands

A Practical and Low-Cost Grasping Detection Module for Multi...

引用

International Conference on mechatronics Technology (ICMT)

作者： Ki Hong Im Seung Hwan Kim Jongwon Park Jinyi Lee Dongwon Yun Extreme Robotics Section KAERI Daejeon Korea Robotics and Mechatronics engineering DGIST Daegu Korea

A grasping detection module is presented to measure normal contact force on each link of the finger in robotic hand. A compact and embeddable design for detecting the grasping force on the contact surface is addressed...

关键词：

来源：评论

学校读者我要写书评

暂无评论

RL-based Control of UAS Subject to Significant Disturbance

arXiv

引用

arXiv 2025年

作者： Chakraborty, Kousheek Hof, Thijs Alharbat, Ayham Mersha, Abeje Smart Mechatronics and Robotics Research Group Saxion University of Applied Science Enschede Netherlands Robotics and Mechatronics Research Group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede Netherlands

This paper proposes a Reinforcement Learning (RL)-based control framework for position and attitude control of an Unmanned Aerial System (UAS) subjected to significant disturbance that can be associated with an uncertain trigger signal. The proposed method learns the relationship between the trigger signal and disturbance force, enabling the system to anticipate and counteract the impending disturbances before they occur. We train and evaluate three policies: a baseline policy trained without exposure to the disturbance, a reactive policy trained with the disturbance but without the trigger signal, and a predictive policy that incorporates the trigger signal as an observation and is exposed to the disturbance during training. Our simulation results show that the predictive policy outperforms the other policies by minimizing position deviations through a proactive correction maneuver. This work highlights the potential of integrating predictive cues into RL frameworks to improve UAS performance. © 2025, CC BY-NC-ND.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-driven System Decoupling Algorithm with Transfer Function Decoupling Matrix

Data-driven System Decoupling Algorithm with Transfer Functi...

引用

Annual Conference of Industrial Electronics Society

作者： Jegwon Yoon Taejune Kong Hanul Jung Sehoon Oh Department of Robotics and Mechatronics Engineering DGIST Daegu South Korea

A Multi-Input-Multi-Output (MIMO) system has complex interactions between inputs and outputs, resulting in a coupling effect that can lead to undesired motions. To effectively control MIMO systems, decoupling is necessary. This paper introduces a decoupling method that uses a transformation matrix modeled as a transfer function using Frequency Response Function (FRF). Unlike the conventional decoupling method uses constant transformation matrix obtained through Canonical Polyadic Decomposition (CPD) and shows performance degradation in certain frequency bands, the proposed method creates transformation matrix as a transfer function and demonstrates better decoupling performance across the entire frequency band. The performance of the proposed method is validated through simulations on a hybrid dual-drive gantry stage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of graphene oxide?silk fibroin bionanofilms via nanoindentation experiments and finite element analysis

引用

Friction 2022年第2期10卷 282-295页

作者： Hyeonho CHO Joonho LEE Hyundo HWANG Woonbong HWANG Jin-Gyun KIM Sunghan KIM School of Mechanical Engineering Chung-Ang UniversitySeoul 06974Republic of Korea Department of Mechanical Engineering(Integrated Engineering) Kyung Hee UniversityGyeonggi 17104Republic of Korea Department of Mechanical Engineering POSTECHPohang 37673Republic of Korea Department of Robotics&Mechatronics.Korea Institute of Machinery&Materials Daejeon 34103Republic of Korea

Understanding the mechanical properties of bionanofilms is important in terms of identifying their *** primary focus of this study is to examine the effect of water vapor annealed silk fibroin on the indentation modulus and hardness of graphene oxide-silk fibroin(GO-SF)bionanofilms through nanoindentation experiments and finite element analysis(FEA).The GO-SF bionanofilms were fabricated using the layer-by-layer *** water vapor annealing process was employed to enhance the interfacial properties between the GO and SF layers,and the mechanical properties of the GO-SF bionanofilms were found to be affected by this *** employing water vapor annealing,the indentation modulus and hardness of the GO-SF bionanofilms can be ***,the FEA models of the GO-SF bionanofilms were developed to simulate the details of the mechanical behaviors of the GO-SF *** difference in the stress and strain distribution inside the GO-SF bionanofilms before and after annealing was *** addition,the load-displacement curves that were obtained by the developed FEA model conformed well with the results from the nanoindentation *** summary,this study presents the mechanism of improving the indentation modulus and hardness of the GO-SF bionanofilms through the water vapor annealing process,which is established with the FEA simulation models.

关键词： graphene oxide silk fibroin layer-by-layer(LbL) nanoindentation finite element analysis(FEA)

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Four Different Chaotic Communication Systems with the Aim of Secure Communication 21st

Synchronization of Four Different Chaotic Communication Syst...

引用

21st Polish Control Conference, PCC 2023

作者： Abadi, Ali Soltani Sharif Hosseinabadi, Pooyan Alinaghi Ordys, Andrew Institute of Automatic Control and Robotics Faculty of Mechatronics Warsaw University of Technology Warsaw Poland School of Engineering and Information Technology The University of New South Wales CanberraACT Australia

ISBN: (纸本)9783031351693

The synchronization of systems with the goal of securing communications is a very interesting and recent topic. This paper proposes the Fast Terminal Sliding Mode Control (FTSMC) method to design control inputs for synchronizing four different communication systems, Volta, Coullet, Chen and ***. Synchronization of these systems can be used in a variety of applications. Some of the key features of the proposed designs are that these inputs are robust against the variety of uncertainties of the system model and external disturbances. Also, the finite time stability of these systems is guaranteed by using designed inputs. Additionally, these inputs eliminate destructive and undesirable chattering phenomena thoroughly. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

A Sensorless Speed Control of High-Speed BLDC Motor Using Variable Slope SMO

A Sensorless Speed Control of High-Speed BLDC Motor Using Va...

引用

作者： Ok, Sangjae Xu, Zhenyao Lee, Dong-Hee Department of Mechatronics Engineering Kyungsung University Busan48434 Korea Republic of State Key Laboratory of Robotics Shenyang Institute of Automation The Chinese Academy of Sciences Shenyang110016 China

Low-power and high-speed BLDC(Brushless DC) motor is widely used in vacuum cleaners. This paper presents a sensorless speed control scheme for a high-speed BLDC motor of a hand-stick vacuum cleaner using a variable slope sliding mode observer(SMO). The SMO using the signum function is very effective for the sensorless estimation of the BLDC motor. However, the chattering effect on the slide surface from the signum function decreases the sensorless performance in the wide speed range. The sigmoid function instead of the signum function can reduce the chattering effect. However, the convergence is inversely proportional to the reduced chattering effect. In order to reduce the chattering effect and keep the proper convergence performance, the proposed method uses a variable acceleration slope of the sigmoid function. In the low-speed range, the acceleration slope of SMO is decreased to reduce the chattering. And, it is increased to improve the convergence in the high-speed region. The acceleration slope of the sigmoid function is designed as a function of the estimated speed to keep the constant convergence with reduced chattering in the sensorless speed and position estimation. In order to verify the proposed sensorless control scheme, 115 krpm speed 540W BLDC motor for a vacuum cleaner is tested with various SMO methods. In the experimental results, the proposed method shows better sensorless speed control performance in the wide speed range. © 2023 IEEE.

关键词： Sensorless control

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：