检索结果-内蒙古大学图书馆

Smart Mechatronics (ICSMech), IEEE International Conference on

作者： Yosua Setiawan Muhammad Nurul Puji Winda Astuti Computer Engineering Department Automotive & Robotics Program BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350368918

ISBN: (纸本)9798350368925

Road accidents have become a problem for many road users in many countries. It may affect human daily activity and tasks, potentially influencing productivity and safety. Therefore, reducing road accidents as swiftly and effectively as possible is critical. For this reason, a Traffic signs detection system has been developed in this work to improve road safety. The detection system can detect traffic signs on the road such as traffic lights, speed limits, and no U-turn signs, and then it will provide users with the corresponding text on an LCD and vibration feedback using a motor. Throughout this work, the You Only Look Once (YOLO) algorithm is proposed for detecting traffic signs on the road. Moreover, a camera is used to extract live videos which serve as an input for the Raspberry Pi 4 model B containing custom YOLOv5 and YOLOv8 models. The system then sends the output to an LCD, a vibration motor, and a radio frequency (RF) module as notifications for users. In the end, the performance of the proposed method has been collected and it is found to produce good accuracy within an inconsiderable amount of 1.677 images and 2.263 annotations. Therefore, the accuracy of 0.69 for YOLOv5 and 0.7 for YOLOv8 were obtained from the training and validation process. Furthermore, the system accurately detects the traffic signs on the road.

关键词： YOLO Vibrations Training Road accidents Accuracy Motors Liquid crystal displays Road safety Safety Videos

来源：评论

学校读者我要写书评

暂无评论

Improvement of Localization Algorithm for Indoor and Outdoor Navigation of Autonomous Robots

引用

Journal of Institute of Control, robotics and Systems 2025年第5期31卷 502-509页

作者： Cho, Joonhyuk Kim, Bongsang Moon, Heechang Industrial Convergence Interdepartmental Program Autonomous Vehicle Intelligent Robotics The Graduate School of Hongik University Korea Republic of Mechanical & System Design Engineering Hongik University Korea Republic of

Location estimation for waypoint-based autonomous driving robots primarily relies on SLAM (Simultaneous Localization and Mapping) and GNSS (Global Navigation Satellite System) technologies. GNSS performs well in open areas but struggles with signal issues, while SLAM offers high accuracy in feature-rich environments but faces challenges in open spaces. This study integrates SLAM and GNSS, enabling seamless switching between systems when one encounters difficulties. The combined system ensures consistency by aligning coordinate systems and directional data. Experiments in indoor, forest, and open environments demonstrate that the switching algorithm enables stable autonomous driving in diverse conditions, effectively leveraging the strengths of both systems. © ICROS 2025.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Consideration of Constructing a Weed Detection Method for an Agricultural Robot in Perilla Fields

Consideration of Constructing a Weed Detection Method for an...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Tatsuya Sugie Noboru Takagi Tatsuo Motoyoshi Kei Sawai Hiroyuki Masuta Graduate School of Intelligent Robotics Program Toyama Prefectural University Toyama Japan Department of Data Science Toyama Prefectural University Toyama Japan Department of Intelligent Robotics Toyama Prefectural University Toyama Japan

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

In recent years, the number of farmers in Japan has been decreasing, and the automation of agriculture using robots, AI, and IoT, known as “smart agriculture,” is being promoted. In this context, Toyama city is promoting a project to build a robot for automatic weeding between plants in a perilla fields. In this research, we are in charge of the system part that detects weeding regions and informs the weeding mechanism. In the field, a wide variety of weeds form vegetation, and it is necessary to prevent food crops from being cut. Therefore, we detect crop regions and the rest of the area should be the weeding regions. In this study, we construct a system to detect crop regions by transfer learning the object detection model YOLO-v8, which is a convolutional neural network (CNN), and evaluate the system in terms of detection accuracy and processing speed.

关键词： Smart agriculture Accuracy Transfer learning Urban areas Crops Vegetation mapping Object detection Real-time systems Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

Investigation of Robot's Eye Gaze Affecting Human Pedestrian Behavior by Robot in Virtual Space

Investigation of Robot's Eye Gaze Affecting Human Pedestrian...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： RYO TAKATA YOTARO FUSE NOBORU TAKAGI BILGUUNMAA MYAGMARDULAM TATSUO MOTOYOSHI KEI SAWAI HIROYUKI MASUTA Graduate School of Intelligent Robotics Program Toyama Prefectural University Toyama Japan Department of Data Science Toyama Prefectural University Toyama Japan Department of Intelligent Robotics Toyama Prefectural University Toyama Japan

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

We investigate the effects of robot's gaze on human behavior when a human and a robot pass each other in a virtual reality space (VR). Nonverbal communication, particularly eye contact, influences physical proximity between individuals in human-to-human interaction. Results of a study indicate that the robot's gaze affects the physical distance between a human and a robot in human-robot communication. Studies on robot's gaze tend to focus on experimental scenarios in which robots and humans communicate. However, robot's gaze in environments with interactions, such as crossing paths, has not been extensively investigated. Therefore, we hypothesize that the robot's gaze exhibits an influence on the physical distance between humans and robots during encounters. In our experiment, we compare three conditions: a robot with a rotating neck and gaze directed at the subject, a faceless robot with a rotating neck, and a faceless robot with a rotating neck and gaze directed at the subject. We analyze the subject's paths of movement and physical distance between the subjects and the robot. Results suggest that the hypothesis that “intimacy equilibrium model” works when humans and robot's cross paths in the VR environment is not supported.

关键词： Solid modeling Pedestrians Human-robot interaction Virtual reality Machine learning Neck Behavioral sciences Mobile robots Robots Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an Internet of Things (IoT)-Based Application and System to Detect Stunting in Infants and Toddlers

Design and Development of an Internet of Things (IoT)-Based ...

引用

HCI and UX Conference in Indonesia (CHIuXiD), International

作者： Theresa Tiffany James Jeremia Zener Sukra Lie Automotive and Robotics Engineering Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350380439

ISBN: (纸本)9798350380446

Currently, the process of monitoring children’s growth in Indonesia relies on manual methods for collecting anthropometric data. These methods pose a risk of data recording errors. Additionally, the ratio of healthcare workers to children in Indonesia is 1:90, a significant disparity that hinders efforts to reduce the prevalence of stunting in the country. To support the third Sustainable Development Goal (SDG), which emphasizes “Good Health and Well-being,” it is crucial to address issues in the stunting management process, from data collection to monitoring. The design and development of this iOS-based mobile application aim to assist in monitoring child growth and provide guidance and steps for prevention and treatment. Besides application development, it also involves the design and development of an Internet of Things (IoT) system to aid in the collection of children’s anthropometric data. The research methodology includes studying stunting cases in Indonesia, anthropometric data calculation methods, stunting prevention and management steps, application design and development, automatic anthropometric data collection, and online data storage and transmission using IoT technology. The developed application and system have been tested and successfully integrated. The IoT device has an accuracy rate of 99.83% for weight measurement calibration and 98.68% for height or length measurement calibration. From the testing results of the child condition calculation method in the application, an accuracy rate of 100% was achieved.

关键词： Weight measurement Pediatrics Accuracy Prevention and mitigation Data collection Mobile applications Calibration Internet of Things Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Trajectory Learning and Demonstration of a Robot Manipulator Based-on Sensor Fusion from a Hand-held Tool

Trajectory Learning and Demonstration of a Robot Manipulator...

引用

2024 International Automatic Control Conference, CACS 2024

作者： Song, Kai-Tai Ou, Szu-Chen National Yang Ming Chiao Yang Ming Chiao Tung University Institute of Electrical and Control Engineering College of Electrical and Computer Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Graduate Degree Program of Robotics Hsinchu300093 Taiwan

ISBN: (纸本)9798350354904

This paper presents a programming system for a robot manipulator using a hand-held demonstration tool. In this system, a user holds the self-designed tool to demonstrate a desired motion path, and the robot arm replicates the learned trajectory. The path-demonstration tool, including optical tags (OT) and an IMU, is designed to collect trajectory data from hand motion. Sensor data fusion allows the system to track accurately the demonstrated trajectory. A calibration procedure is proposed to transform the trajectory from tool's coordinate system to robot's coordinate system. A cubic spline-based trajectory planning method is proposed to ensure smooth reproduction of the learned trajectory in both time and space. Experimental results show that the robot is able to replicate squared and curved trajectories collected from the path-demonstration tool. The average position error is within 2.435 mm in XYZ directions and the average orientation error is within 0.65 degrees. © 2024 IEEE.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Learning-based Adaptive Control of Quadruped Robots for Active Stabilization on Moving Platforms

Learning-based Adaptive Control of Quadruped Robots for Acti...

引用

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

作者： Minsung Yoon Heechan Shin Jeil Jeong Sung-Eui Yoon School of Computing at Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Robotics Program at the Same Institute KAIST

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

A quadruped robot faces balancing challenges on a six-degrees-of-freedom moving platform, like subways, buses, airplanes, and yachts, due to independent platform motions and resultant diverse inertia forces on the robot. To alleviate these challenges, we present the Learning-based Active Stabilization on Moving Platforms (LAS-MP), featuring a self-balancing policy and system state estimators. The policy adaptively adjusts the robot’s posture in response to the platform’s motion. The estimators infer robot and platform states based on proprioceptive sensor data. For a systematic training scheme across various platform motions, we introduce platform trajectory generation and scheduling methods. Our evaluation demonstrates superior balancing performance across multiple metrics compared to three baselines. Furthermore, we conduct a detailed analysis of the LAS-MP, including ablation studies and evaluation of the estimators, to validate the effectiveness of each component.

关键词： Training Measurement Systematics Propioception Trajectory Steady-state Safety Quadrupedal robots Public transportation Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of Ankle Spasticity Through Electromyography Signal

Quantitative Analysis of Ankle Spasticity Through Electromyo...

引用

Medical Technologies National Conference (TIPTEKNO)

作者： Ayse Gurluk Hafiz Muhammad Bilal Elif Hocaoglu Living Robotics Laboratory Graduate School of Health Sciences Physiotherapy and Rehabilitation Program Istanbul Medipol University Istanbul Türkiye Living Robotics Laboratory Graduate School of Engineering and Natural Sciences Electrical-Electronics Engineering and Cyber-Systems Program Istanbul Medipol University Istanbul Türkiye Department of Electrical and Electronics Engineering Living Robotics Laboratory Istanbul Medipol University Istanbul Türkiye

ISBN: (数字)9798331529819

ISBN: (纸本)9798331529826

This study presents a more accurate evaluation method for assessing ankle spasticity compared to conventional goniometric techniques by utilizing measurements obtained from Inertial Measurement Units (IMU) and surface electromyography (sEMG) devices. Integrating IMU and EMG sensors provides substantial benefits for accurately determining the range of motion (ROM) associated with spasticity during targeted movements. In this study, the proposed method provides precise measurement and an objective evaluation of onset time detection of antagonistic muscle co-contraction, and accordingly the ROM of the actuated joint. Moreover, the implementation of cost-effective wearable sensors enables the monitoring of muscle spasticity in clinical environments and can be particularly valuable in regions with limited access to experienced therapists, providing a more efficient approach to tracking spasticity levels.

关键词： Ankle Measurement units Inertial navigation Muscles Electromyography Sensors Reliability Motion control Read only memory Monitoring

来源：评论

学校读者我要写书评

暂无评论

Real-Time Endomicroscopic Image Mosaicking with an EKF-based Sensor Fusion Approach

Real-Time Endomicroscopic Image Mosaicking with an EKF-based...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Jin Kim Hyesung Lee Sang-Rok Oh Sungwook Yang Center for Intelligent and Interactive Robotics Korea Institute of Science and Technology Seoul South Korea Robotics Program Korea Advanced Institute of Science and Technology Daejeon South Korea

This study presents a real-time sensor fusion framework based on the extended Kalman filter (EKF) for accurate and robust endomicroscopic image mosaicking. The sensor fusion framework incorporates an optical tracking system that can track 6-DOF pose of the imaging probe with high accuracy in real time in conjunction with 2D local image registration from image feature matching between two consecutive frames. We evaluated the performance of the real-time image mosaicking based on the sensor fusion compared with the image or tracker only approach. As a result, it could retain the microscopic level of image detail from the image-based approach and also achieve a robust image mosaic without any drift by using the accurate optical tracking system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-View Node Pruning for Accurate Graph Representation

arXiv

引用

arXiv 2025年

作者： Park, Jiseong Kim, Hanjin Kim, Seojin Choi, Jueun BBE KAIST Daejeon Korea Republic of Div. Supercomputing KISTI Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of

Graph pooling, which compresses a whole graph into a smaller coarsened graph, is an essential component of graph representation learning. To efficiently compress a given graph, graph pooling methods often drop their nodes with attention-based scoring with the task loss. However, this often results in simply removing nodes with lower degrees without consideration of their feature-level relevance to the given task. To fix this problem, we propose a Multi-View Pruning (MVP), a graph pruning method based on a multi-view framework and reconstruction loss. Given a graph, MVP first constructs multiple graphs for different views either by utilizing the predefined modalities or by randomly partitioning the input features, to consider the importance of each node in diverse perspectives. Then, it learns the score for each node by considering both the reconstruction and the task loss. MVP can be incorporated with any hierarchical pooling framework to score the nodes. We validate MVP on multiple benchmark datasets by coupling it with two graph pooling methods, and show that it significantly improves the performance of the base graph pooling method, outperforming all baselines. Further analysis shows that both the encoding of multiple views and the consideration of reconstruction loss are the key to the success of MVP, and that it indeed identifies nodes that are less important according to domain knowledge. © 2025, CC BY-NC-ND.

关键词： Knowledge graph

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：