检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Humt, Matthias Winkelbauer, Dominik Hillenbrand, Ulrich Bäuml, Berthold The DLR Institute of Robotics and Mechatronics Germany Germany Germany

Grasping objects with limited or no prior knowledge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem, especially when it comes to only partial observability and versatile grasping with multi-fingered hands. We present a novel, fast, and high fidelity deep learning pipeline consisting of a shape completion module that is based on a single depth image, and followed by a grasp predictor that is based on the predicted object shape. The shape completion network is based on VQDIF and predicts spatial occupancy values at arbitrary query points. As grasp predictor, we use our two-stage architecture that first generates hand poses using an autoregressive model and then regresses finger joint configurations per pose. Critical factors turn out to be sufficient data realism and augmentation, as well as special attention to difficult cases during training. Experiments on a physical robot platform demonstrate successful grasping of a wide range of household objects based on a depth image from a single viewpoint. The whole pipeline is fast, taking only about 1 s for completing the object’s shape (0.7 s) and generating 1000 grasps (0.3 s). (https://***/2023-humanoids-completion/) Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Stereo Vision Based Robot for Remote Monitoring with VR Support

arXiv

引用

arXiv 2024年

作者： Fazil, M.S. Mohamed Selvakumar, A. Arockia Schilberg, Daniel Design and Automation Research Group SMBS Vellore Institute of Technology Chennai India Mechatronics and Research Head of Institute of Robotics Mechatronics University of Applied Sciences Bochum Germany Mechatronics and Robotics Tandon School of Engineering New York University United States

The machine vision systems have been playing a significant role in visual monitoring systems. With the help of stereovision and machine learning, it will be able to mimic human-like visual system and behaviour towards the environment. In this paper, we present a stereo vision based 3-DOF robot which will be used to monitor places from remote using cloud server and internet devices. The 3-DOF robot will transmit human-like head movements, i.e., yaw, pitch, roll and produce 3D stereoscopic video and stream it in Real-time. This video stream is sent to the user through any generic internet devices with VR box support, i.e., smartphones giving the user a First-person real-time 3D experience and transfers the head motion of the user to the robot also in Real-time. The robot will also be able to track moving objects and faces as a target using deep neural networks which enables it to be a standalone monitoring robot. The user will be able to choose specific subjects to monitor in a space. The stereovision enables us to track the depth information of different objects detected and will be used to track human interest objects with its distances and sent to the cloud. A full working prototype is developed which showcases the capabilities of a monitoring system based on stereo vision, robotics, and machine learning. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Extending the Functionality of a Haptic Glove for Controlling a Robotic Platform

Extending the Functionality of a Haptic Glove for Controllin...

引用

International Carpathian Control Conference (ICCC)

作者： Florina-Luminita Petcu Stefan-Irinel Cismaru Horatiu Roibu Ionut-Cristian Resceanu Andrei-Costin Trasculescu Nicu-George Bizdoaca Mechatronics and Robotics Department Faculty of Automation Computers and Electronics University of Craiova Craiova Romania

ISBN: (数字)9798331501273

ISBN: (纸本)9798331501280

In the era of advanced technologies, haptic interfaces gained popularity due to their ability to provide users with an intuitive and immersive interactive experience. Haptic gloves, originally used for virtual reality applications, are a notable example, allowing precise control of virtual objects through natural gestures. In this context, the present study explores the integration of an adapted haptic glove with the humanoid robot NAO in order to use it as a control interface. The haptic glove initially developed and used for virtual reality applications demonstrated high reliability in precise control of virtual objects, providing users with an immersive experience and intuitive control. Originally intended for virtual simulations, the glove was tested and optimized, which facilitated direct interaction with objects in a virtual environment. The success achieved in underlining the potential of this technology is to be extended to real-world applications, especially for the control of robotic devices. Therefore, the research focused on integrating the haptic glove with the humanoid robot NAO in order to use it as a control interface. This integration allows the transfer of the user's movements to the robot, providing a natural and intuitive method of manipulating the robot's functions, with the study focusing on hand movements. Preliminary tests have highlighted that the glove can successfully render user movements in real-time, ensuring precise synchronization and prompt robot response. The integration was facilitated by the adaptation of the glove for the control of the external system represented by the NAO robot and the flexibility of the platform, and the results obtained suggest that this combination represents an important step towards the development of advanced solutions for gesture-based robotic control.

关键词： Hands Solid modeling Protocols Scalability Humanoid robots Human-robot interaction Virtual environments Haptic interfaces Sensors Synchronization

来源：评论

学校读者我要写书评

暂无评论

Peripheral Neuromodulation for Bionic limbs and Electroceuticals

Peripheral Neuromodulation for Bionic limbs and Electroceuti...

引用

Pan American Health Care Exchanges, PAHCE

作者： Youngjun Cho Heejae Shin Minseok Kang Yongwoo Kim Jinwoong Jeong Sanghoon Lee Robotics and Mechatronics Engineering DGIST Rep. of Korea

Modulation of nerve signals in the peripheral nervous system (PNS) is a promising research field for interfacing with bionic limbs and for therapeutic applications. To achieve this, peripheral neural interfaces should be improved in terms of biocompatibility and functionality of recording and stimulation. This presentation introduces shape memory polymer neural interfaces, which have been developed for use in bionic limbs and bladder modulation. Furthermore, this paper introduces triboelectric neurostimulators for modulating peripheral nerves.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electro-humidity responsive soft actuators based on cellulose nanofibers-nanocrystals for bioinspired applications

引用

Science China Technological Sciences 2025年

作者： Fan WANG Ruibin QI Yujiao WU Qinchuan LI Junhui ZHANG Sukho PARK School of Mechanical Engineering Zhejiang Sci-Tech University State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Department of Robotics and Mechatronics Engineering Daegu Gyeongbuk Institute of Science and Technology (DGIST)

Multifunctional responsive actuators have garnered considerable attention for their potential applications in soft robots, wearable devices, smart displays, environmental sensing, and biomimetic systems. Herein, we present a multifunctional color-changing ionic soft actuator that integrates electrical actuation and humidity-induced color-changing functionalities,fabricated using carboxylated cellulose nanofibers, ionic liquids, polyvinyl alcohol, cellulose nanocrystals, and poly(ethylene glycol) diacrylate. The electro-humidity responsive actuator exhibited remarkable actuation performance, including a maximum tip displacement(10.2 mm), low driving voltage(as low as 1.0 V), high operational stability(95.2% reliability after 2000actuation cycles), broad working frequency range(0.2–3.0 Hz), and exceptional tolerance to humid environments(90% relative humidity). In addition, the actuator showcased reversible and integrated color-changing capabilities. These features enabled the design of innovative devices, such as biomimetic flowers and smart color-changing windows with tunable optical ***, this multifunctional actuator provides a promising platform for applications in soft robots, optical anti-counterfeiting systems, information storage materials, and intelligent home technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimation of Respiratory Rate from Photoplethysmogram Signal Using Maximal Overlap Discrete Wavelet Transform

Estimation of Respiratory Rate from Photoplethysmogram Signa...

引用

Emerging Frontiers in Electrical and Electronic Technologies (ICEFEET), International Conference on

作者： Syed Mujibul Islam Anshuman Vikram Tanmay Pal School of Mechatronics & Robotics IIEST Shibpur Howrah India

Respiratory Rate (RR) abnormality is often an early indicator of critical illness. Reliable estimation of RR continuously from other physiological signals is an active area of research. Direct measurement of RR can be done by measuring oronasal airflow. However, this is an uncomfortable process for the patient. Hence, conventional approaches use the electrocardiogram (ECG) signal to analyze respiratory sinus arrhythmia. Photoplethysmogram (PPG) waveform analysis provides an alternate, non-invasive method of estimation, which is suitable for patients of all ages and health conditions. In this work, various techniques available in the literature regarding RR estimation from the PPG waveform have been studied. A methodology based on Maximal Overlap Discrete Wavelet Transform (MODWT) is proposed for Multi-Resolution Analysis (MRA) to provide the RR estimate. Comparison of the proposed technique with the existing algorithms demonstrates better accuracy for estimating RR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Planar Metastructure-based Gas Sensors for High Stretchability and Stable NO2 Sensing

Planar Metastructure-based Gas Sensors for High Stretchabili...

引用

International Conference on Solid State Sensors and Actuators (TRANSDUCERS)

作者： Jeonhyeong Park Hyeoncheol Lim Chaehyun Ryu Soon In Jung Il Ryu Jang Hoe Joon Kim Department of Robotics and Mechatronics Engineering DGIST South Korea

The paper presents a flexible and stretchable carbon nanotube (CNT) based gas sensor fabricated on a planar metastructure, kirigami substrate with anatase TiO 2 functionalization for improved NO 2 sensing performances with high stretchability. The developed kirigami-based sensor possesses a network of notches with high softness and stretchability, ensuring a stable sensor operation of up to 80% strain. Such a high strain range overcomes the current limitation of gas sensors, which generally utilize rather brittle and rigid sensing materials. The innovative claims include (1) the utilization of kirigami architecture to mitigate the uniaxial strain effect and (2) the enhancement of sensor performance regarding the sensitivity and recovery time owing to TiO 2 functionalization. Mechanical properties of the kirigami structure can be analyzed via stress-strain relation, and the sensing material properties are characterized using Fourier-transform infrared spectroscopy (FT-IR) and Raman spectroscopy. The suggested kirigami-based gas sensors could be applied to wearable and stretchable gas sensing applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PIβDα Controller in the Human Machine Systems

PIβDα Controller in the Human Machine Systems

引用

International Conference on System Theory, Control, and Computing (ICSTCC)

作者： Mircea Ivanescu Mircea Nitulescu Department of Mechatronics and Robotics University of Craiova Craiova Romania

This paper investigates the control of an electric vehicle by a human operator and the techniques needed to compensate for the operator’s control deficiencies. Several classes of human operators, of various ages and health conditions, are analyzed. It is shown that the human operator can be characterized by an integrator model with the fractional exponent $\beta\in[0.8-1.6]$. Particular attention is paid to people with Parkinson’s disability for whom the exponent $\beta$ tends to value of1.5. The fractional model of the human-machine system is determined. Control systems based on the use of observers for the estimation of human state components and hierarchical control systems are studied. The stability conditions are obtained by Lyapunov techniques. Experiments on a wheelchair driven by a person with Parkinson’s disability confirm the correctness of the proposed solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of HRI System for Mobile Manipulator to be Operated in the Elevator

引用

Journal of Institute of Control, robotics and Systems 2022年第8期28卷 714-723页

作者： Kang, Min-Woo Kim, Tae-Hyeon Suh, Hyun-Uk Kim, Donghan Department of Electronics Engineering Kyung Hee University Korea Republic of Department of Robotics and Mechatronics Korea Institute of Machinery Materials Korea Republic of Kyung Hee University Korea Republic of

Unlike conventional industrial robots that operate in a limited manufacturing environment, service robots should be able to operate in various environments. Where there are many complex high-rise buildings, service robots require the ability to ride and control elevators. Furthermore, a human-robot interaction (HRI) approach is critical because service robots have the characteristics of interacting directly with humans. Therefore, this paper proposes an HRI system that enables direct elevator button manipulation to enable mobile manipulator robots to perform tasks in various high-rise building environments. The system is divided into three subsystems: Elevator button recognition, command reception through voice recognition, and elevator button operation. Elevator button recognition and command reception through voice recognition receive the required topics and communicate with the lower end of the elevator button operation. Although the three distinct substructures interact with each other and are independent, they can be replaced by different algorithms at any time. Because of the same characteristics, the system can be applied to various mobile manipulators with different specifications. The experiment proceeds with pressing the button on floors B1-4 through voice recognition in a simulation environment and pressing the button on floors 5-7 without voice recognition. The experimental results compared the central positions of the button and end effector’s x, y, and z coordinates after control. The system, verified through simulation, has since been applied to real robots. © ICROS 2022.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Full-body Exoskeleton Designed for Robot Teleoperation through VR Application

Full-body Exoskeleton Designed for Robot Teleoperation throu...

引用

International Carpathian Control Conference (ICCC)

作者： Stefan-Irinel Cismaru Florina-Luminita Petcu Horatiu Roibu Florin-Alexandru Dita Ionut-Cristian Resceanu Nicu-George Bizdoaca Mechatronics and Robotics Department Faculty of Automation Computers and Electronics University of Craiova Craiova Romania

ISBN: (数字)9798331501273

ISBN: (纸本)9798331501280

The concept of teleoperation for robots and mechatronic platforms, increasingly present in current activities, is expanded through the integration of a virtual reality environment that facilitates natural interaction between the user and technology. This study builds upon previous research that explored the development of upper-limb exoskeleton suitable for controlling the humanoid robot NAO, emphasizing the possibility of transmitting the user’s natural movements to mechatronic platforms. The novelty lies in the use of a Virtual reality (VR) application together with the exoskeleton as a means of teleoperation that enables not only precise control but also replication of human gestures, thereby enhancing the fluidity of human-machine interaction. The study demonstrates that virtual reality can become a complex interface for controlling mechatronic platforms, opening significant perspectives in fields such as robotics, rehabilitation, and advanced teleoperation systems. This methodological advancement reinforces the potential of virtual reality to redefine how we, as humans, interact with advanced technology.

关键词： Human computer interaction Bridges Visualization Technological innovation mechatronics Exoskeletons Humanoid robots Virtual reality Programming Complexity theory

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：