检索结果-内蒙古大学图书馆

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Guotao Gou Kong Hoi Cheng Jinxin Sun Chengyu Lin Wei Pan Guojing Huang Yuquan Leng Yixuan Guo Chenglong Fu Department of Mechanical and Energy Engineering Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems and Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China Guangxi Human Physiological Information Non Invasive Detection Engineering Technology Research Center School of Life and Environmental Sciences Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Stroke survivors frequently face the challenge of regaining hand-grasping functions, which are crucial for performing daily activities. While Functional Electrical Stimulation (FES) has demonstrated promise for hand function recovery, the application of online control methods tailored to varied daily grasps remains underexplored. In response, our study presents a refined framework utilizing an inertial measurement unit (IMU) for the real-time recognition of grasp intentions in stroke patients. Data on arm trajectories and orientations preceding diverse grasping actions were gathered from three healthy individuals, segmented by acceleration to determine high-accuracy intervals for grasp prediction. The Support Vector Classification (SVC) model emerged as a superior method for intent recognition. By segmenting data based on acceleration, our model’s general accuracy improved. Moreover, the time required to achieve a stable accuracy rate exceeding 95% was reduced from 0.8 s to 0.2 s. This research lays the groundwork for future advancements in online gesture recognition systems. The successful implementation of FES based on SVC-model predictions mark a significant step toward intuitive and adaptive rehabilitation therapies for stroke patients.

关键词： Accuracy Static VAr compensators Grasping Stroke (medical condition) Real-time systems Iron Data models Trajectory Neuromuscular stimulation Context modeling

来源：评论

学校读者我要写书评

暂无评论

MMG-HCI: A Non-contact Non-intrusive Real-Time Intelligent Human-Computer Interaction System 1st

MMG-HCI: A Non-contact Non-intrusive Real-Time Intelligent H...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Gong, Peixian Wang, Chunyu Zhang, Lihua Institute of AI and Robotics Fudan University Shanghai China Ji Hua Laboratory Foshan China Shanghai Engineering Research Center of AI and Robotics Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Beijing China Engineering Research Center of AI and Unmanned Vehicle Systems of Jilin Province Changchun China

ISBN: (纸本)9783030930455

With the continuous development of science and technology, human-computer interaction (HCI) technology has been paid more and more attention by researchers. Traditional HCI methods, such as torch-screen, speech recognition and so on, have the problem of inconvenient application in some scenarios. The research of HCI technology based on millimeter-wave radar makes up for the deficiency of current HCI, and plays a very important role in its development. The main tasks of this paper are as follows: 1, Design of non-contact and non-invasive real-time human activity recognition system MMG-HCI. By analyzing the working features of millimeter-wave radar and combining them with the principle of computer multi-process synchronization, we designed a real-time system which integrates millimeter-wave radar data acquisition, point cloud data visualization, deep learning model inference and HCI. 2, Construction of millimeter-wave radar gesture dataset. Since there is no suitable open-source dataset at present, we collect and build our own dataset through the real-time system. 3, Training graph neural network (GNN) for HAR based on millimeter-wave radar. In order to classify the mmWave radar point cloud more accurately, we use the best performance MMPointGNN as the deep learning inference model of a real-time system. Experiments and demonstration show that we have designed an efficient, accurate, non-contact and non-invasive real-time HCI system. © 2021, Springer Nature Switzerland AG.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

E-3DGS: Gaussian Splatting with Exposure and Motion Events

arXiv

引用

arXiv 2024年

作者： Yin, Xiaoting Shi, Hao Bao, Yuhan Bing, Zhenshan Liao, Yiyi Yang, Kailun Wang, Kaiwei State Key Laboratory of Modern Optical Instrumentation Zhejiang University China School of Robotics National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Information Science and Electronic Engineering Zhejiang University China The Chair of Robotics AI and Real-Time Systems Technical University of Munich Germany

Estimating Neural Radiance Fields (NeRFs) from images captured under optimal conditions has been extensively explored in the vision community. However, robotic applications often face challenges such as motion blur, insufficient illumination, and high computational overhead, which adversely affect downstream tasks like navigation, inspection, and scene visualization. To address these challenges, we propose E-3DGS, a novel event-based approach that partitions events into motion (from camera or object movement) and exposure (from camera exposure), using the former to handle fast-motion scenes and using the latter to reconstruct grayscale images for high-quality training and optimization of event-based 3D Gaussian Splatting (3DGS). We introduce a novel integration of 3DGS with exposure events for high-quality reconstruction of explicit scene representations. Our versatile framework can operate on motion events alone for 3D reconstruction, enhance quality using exposure events, or adopt a hybrid mode that balances quality and effectiveness by optimizing with initial exposure events followed by high-speed motion events. We also introduce EME-3D, a real-world 3D dataset with exposure events, motion events, camera calibration parameters, and sparse point clouds. Our method is faster and delivers better reconstruction quality than event-based NeRF while being more cost-effective than NeRF methods that combine event and RGB data by using a single event sensor. By combining motion and exposure events, E-3DGS sets a new benchmark for event-based 3D reconstruction with robust performance in challenging conditions and lower hardware demands. The source code and dataset will be available at https://***/MasterHow/E-3DGS. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

STRONG: Synchronous and asynchronous RObust Network localization, under Non-Gaussian noise

arXiv

引用

arXiv 2021年

作者： Soares, Cláudia Gomes, João Institute for Systems and Robotics Laboratory for Robotics and Engineering Systems IST Universidade de Lisboa Portugal

Real-world network applications must cope with failing nodes, malicious attacks, or nodes facing corrupted data — data classified as outliers. Our work addresses these concerns in the scope of the sensor network localization problem where, despite the abundance of technical literature, prior research seldom considered outlier data. We propose robust, fast, and distributed network localization algorithms, resilient to high-power noise, but also precise under regular Gaussian noise. We use a Huber M-estimator, thus obtaining a robust (but nonconvex) optimization problem. We convexify and change the problem representation, to allow for distributed robust localization algorithms: a synchronous distributed method that has optimal convergence rate and an asynchronous one with proven convergence guarantees. A major highlight of our contribution lies on the fact that we pay no price for provable distributed computation neither in accuracy, nor in communication cost or convergence speed. Simulations showcase the superior performance of our algorithms, both in the presence of outliers and under regular Gaussian noise: our method exceeds the accuracy of alternative approaches, distributed and centralized, even under heavy additive and multiplicative outlier noise. Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Modeling and simulation of a mechanism for suppressing the flipping problem of a jumping robot

arXiv

引用

arXiv 2024年

作者： Li, Qi Peng, Liang Wu, Zhiyuan Ye, Pengda Zhang, Weitao Xu, Yi Shi, Qing Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China The Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing100081 China

To improve the environmental adaptability of small-sized robots, jumping is widely used to achieve high moving efficiency and obstacle surmounting ability. However, the flipping problem commonly existing in jumping robots will limit their application prospects. Instead of attaching additional control mechanisms and actuators, we propose an elastic passive joint (EPJ) to prevent the robot from flipping. By integrating a revolute joint, a switch and a spring at the root of the hindleg, the leg can rotate around the body during take-off phase, in which the large angular velocity will be inhibited due to the absorbed angular kinetic energy by the spring. Then, dynamic modeling and series of simulation are carried out to optimize the position and stiffness of EPJ. The simulation results reveal that, with EPJ worked, the zero-point of the angular velocity will appear when changing the position of the axis slightly. Meanwhile, the optimal spring stiffness of 1566 N/m will ensure a non-flipping jumping motion, in which the jumping height is reduced but the jumping distance is improved. Copyright © 2024, The Authors. All rights reserved.

关键词： Angular velocity

来源：评论

学校读者我要写书评

暂无评论

Design of a Mesh Crawling Robot with Beetle-Inspired Variable Stiffness Tarsus

Design of a Mesh Crawling Robot with Beetle-Inspired Variabl...

引用

IEEE International Conference on robotics and Biomimetics

作者： Hao Chen Kai Hu Longlong Hu Ziqi Zhou Yao Li Bing Li Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Key University Laboratory of Mechanism & Machine Theory and Intelligent Unmanned Systems of Guangdong Shenzhen China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Compared with large robots, micro-robots have the advantages of small size, low power consumption, and high concealment. For complex terrain, the crawling performance of micro-robots will be significantly reduced. In this study, the mesh surface was used as the crawling base of the robot, and a variable stiffness tarsus was designed with the beetle as a reference. This tarsus composed of multiple bending parts achieves a large range of stiffness changes, 0.07~0.495 N/mm. We have achieved stiffness control of the tarsus in a single actuation by trajectory planning of the claw ends. The proposed robot can achieve a big stiffness of the tarsus to resist the deformation of the tarsus due to external forces, which means that the robot can increase the adhesion ability when crawling at the stance phase. Therefore, even when the load was increased from 10g to 40g, the average crawling speed of the robot was not significantly reduced. This new tarsus can improve the crawling performance of the micro-robot on the mesh.

关键词： Legged locomotion Power demand Trajectory planning Force Kinematics Resists Bending Robots Substrates Trajectory optimization

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Hand Movement Recognition: Feature Domain and Level of Decomposition 1

引用

13th National Conference on Industrial Problems on Machines and Mechanism, IPRoMM 2020

作者： Phukan, Nabasmita M. Kakoty, Nayan Gupta, Nipun Baruah, Neelanjana Jorhat Engineering College Jorhat India Embedded Systems and Robotics Laboratory Tezpur University Tezpur India Madhav Institute of Technology and Science Gwalior India

ISBN: (数字)9789811617690

ISBN: (纸本)9789811617683

This manuscript reports feature domains for the recognition of right and left hand movements using Electroencephalogram (EEG). A 21-channel EEG dataset of seven subjects during right and left hand fist open and close movements was collected from PhysioNet of the BCI2000 Instrumentation system. Features in time, frequency, and time-frequency domains have been explored. Support vector machine with radial basis function kernel was used for the recognition of right and left hand fist open and close movements. The recognition with time, frequency, and time-frequency domain features resulted in an accuracy of 90%, 92%, 97.5%, respectively. Time-frequency domain features obtained through discrete wavelet transform (DWT) at four decomposition levels have resulted in maximum recognition rate. The highest recognition rate of 98.6 ± 0.6 % has resulted in DWT features at level 2. This was substantiated by the fact that DWT features at level 2 establish maximum correlation with pre-processed EEG. Experimental result shows that time-frequency is the best performing feature domain among the three. Further, correlation measure of time-frequency domain features with EEG are established as a benchmark for selecting DWT decomposition level. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Pose Estimation of Rats Based on Stereo Vision Embedded in a Robotic Rat

Real-Time Pose Estimation of Rats Based on Stereo Vision Emb...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Xiaowen Guo Guanglu Jia Mohamed Al-Khulaqui Zhe Chen Toshio Fukuda Qing Shi Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China

In this paper, we propose a system for real-time rat pose estimation based on stereo vision. The system is dedicated to robot-rat interaction research. First, we design a lightweight, high-resolution network (RRKDNet) for keypoint detection of the rat. The network is trained on a dataset of rat images, which are captured by the robotic rat in first-person view. Second, based on the keypoint detection results, the pose of the rat is obtained by stereo vision model calculation and robot coordinate transformation. At last, we complete a real-time simulation experiment to reproduce the pose of the rat and the robotic rat. The system has been subjected to a series of experiments and the results demonstrate that our network performs better in speed and performance than similar networks. Compared to similar networks, our network has about one-third the number of parameters, while the detection rate increases by 45.25% (the detection rate is 71.57%). The inference speed (34.42 FPS with dual model simultaneous inference) is also faster. The validation error is only 13.85 pixels on the homemade dataset, which is lower than all backbones in Deeplabcut (a toolbox more frequently used for rat keypoint detection). Thus, this work is a significant step in the autonomous intelligent interaction between robots and rats.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toward Process Controlled Medical Robotic System

arXiv

引用

arXiv 2023年

作者： Liu, Yihao Kheradmand, Amir Armand, Mehran The Biomechanical- and Image-Guided Surgical Systems Laboratory Laboratory for Computational Sensing & Robotics Department of Computer Science Johns Hopkins University BaltimoreMD21218 United States The Department of Neurology Department of Neuroscience Laboratory for Computational Sensing & Robotics Johns Hopkins University BaltimoreMD21218 United States The Biomechanical- and Image-Guided Surgical Systems Laboratory Laboratory for Computational Sensing & Robotics Department of Orthopaedic Surgery Department of Mechanical Engineering Department of Computer Science Applied Physics Laboratory Johns Hopkins University BaltimoreMD21218 United States

Medical errors, defined as unintended acts either of omission or commission that cause the failure of medical actions, are the third leading cause of death in the United States. Medical errors can include communication breakdowns, diagnostic errors, poor judgment, and inadequate skills. The application of autonomy and robotics can alleviate some causes of medical errors by improving accuracy and providing means to accurately follow planned procedures. However, for the robotic applications to improve safety, they must maintain constant operating conditions in the presence of disturbances, and provide reliable measurements, evaluation, and control for each state of the procedure. This article addresses the need for process control in medical robotic systems, and proposes a standardized design cycle toward its automation. Monitoring and controlling the changing conditions in a medical or surgical environment necessitates a clear definition of workflows and their procedural dependencies. We propose integrating process control into medical robotic workflows using hierarchical Finite State Machines (hFSM) to identify changes in states of the system and environment, and execute possible operations or transitions to new states. Therefore, the system translates clinician experiences and procedure workflows into machine-interpretable languages. The design cycle using hFSM formulation can be a deterministic process, which opens up possibilities for higher-level automation in medical robotics. Shown in our work, with a standardized design cycle and software paradigm, we pave the way toward controlled workflows that can be automatically generated. Additionally, a modular design for a robotic system architecture that integrates hFSM can provide easy software and hardware integration. This article discusses the system design, software implementation, and example application to Robot-Assisted Transcranial Magnetic Stimulation (RATMS) and robot-assisted femoroplasty. We also provide

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

Object Detection Methods for a Robot Soccer

Object Detection Methods for a Robot Soccer

引用

Information, Control, and Communication Technologies (ICCT), International Conference on

作者： Ramir Sultanov Roman Lavrenov Shifa Sulaiman Yang Bai Mikhail Svinin Evgeni Magid Laboratory of Intelligent Robotics Systems (LIRS) Institute of Information Technology and Intelligent Systems Kazan Federal University Kazan Russia Information Science and Engineering Department Ritsumeikan University Biwako-Kusatsu Campus Shiga Japan

Soccer tournaments between robot teams are being held around the world to encourage robotic research. An accurate detection and tracking of a ball position, an identification of robots and objects during a game are crucial for robot teams. In this paper, object detection methods for identifying robots and a ball during a robot soccer game are presented. Standard OpenCV library functions were adjusted for a ball and robots' detection. Simulation studies were carried out in Gazebo environment to compare a performance of various methods discussed in this paper.

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：