检索结果-内蒙古大学图书馆

IEEE International Congress on Electronics, Electrical engineering and Computing (INTERCON)

作者： Mario Arbulu Geyni Arias Brayan Iñiguez Sofia Dussan Ricardo Barreto José Cornejo Mechatronics Engineering Program CORHUILA Colombia Industrial Engineering Program CORHUILA Colombia R&D Department Robotics 4.0 Colombia Center for Space Emerging Technologies Universidad Nacional de Ingeniería Lima Peru Universidad Tecnológica del Perú Lima Peru

This paper deals with the challenges involved on roof building gutter maintenance robot design, from the problem statement of secure teleoperated semiautonomous navigation on confined gutter spaces, and the best selection of right mechatronics brush to remove the waste on gutter surface; Two concept design have been tested: Passive Brush with Parallel locomotion (PBP), and Active Brush Axial (ABA). The results on our development are shown, as following: secure robot lifting regulation, simulation environment, HMI to teleoperate, mechatronics design. Finally, some tests on simulations and current prototypes are shown, to validate our proposal, and the conclusion that the ABA design allows to remove until 85% gutter waste, instead of PBP design; furthermore, the ABA allows independent brush rotation velocity, instead of PBP design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-UNet: An End-to-End Deep Learning Framework for the Automatic Chronic Diabetic Wound Segmentation

Dual-UNet: An End-to-End Deep Learning Framework for the Aut...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Mustafa Alhababi Gregory Auner Hafiz Malik Lubna Alazzawi Muteb Aljasem Electrical and Computer Engineering Wayne State University Detroit MI USA Department of Smart Sensors and Integrated Microsystems Program Wayne State University Detroit MI USA Electrical and Computer Engineering University of Michigan-Dearborn Dearborn MI USA Electronics and Computer Engineering & Robotics Engineering Bowling Green State University Bowling Green OH USA

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

Foot ulcers are one of the chronic wounds commonly occurring in diabetic patients and are associated with a high risk of major or minor amputations. Evaluation and measurement of such wounds are done manually by experts to assess the wound healing and suggest further treatment. Manual assessment methods can cause infections at times and are less feasible in the existence of pandemic situations. The development of artificial intelligence has brought a revolution in many domains of medical imaging. Deep learning-based computer-aided approaches can be applied to assist clinicians in assessing and monitoring chronic wounds. Wound segmentation helps to measure wound area which is useful for assessing its healing progress. In this research work, a deep learning-based segmentation method, namely Dual-UNet is presented for precisely segmenting the diabetic foot ulcers images. The foot ulcer images are passed to Dual-UNet to generate the mask image having the segmented wound area. We proposed two modified UNets each having a customized encoder and decoder with skip connections, atrous spatial pyramid pooling (ASPP) block, and output block to improve the segmentation results. We assessed our framework by performing experimentation on two benchmark datasets, named the foot ulcer segmentation (FUSeg) challenge and the AZH segmentation dataset. Additionally, we have also assessed our Dual-UNet for cross-corpora validation to demonstrate the generalization capability of the proposed approach. The qualitative and quantitative results highlight the accuracy and effectiveness of the Dual-UN et framework for segmenting chronic diabetic wounds. Future research should focus on the development of large and diverse wound datasets and improving the results for cross-corpora evaluation.

关键词： Deep learning Image segmentation Pandemics Computational modeling Manuals Wounds Diabetes Decoding Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Design for Improvement of Visual SLAM in Dynamic Environments Using Feature-Point Removal of Moving Persons

A Design for Improvement of Visual SLAM in Dynamic Environme...

引用

International Automatic Control Conference

作者： Kai-Tai Song Ching-Hao Meng Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of Robotics College of Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

This paper presents a design to improve the robustness of visual SLAM(vSLAM). A processing step of feature-removal is added to the tracking thread of the conventional ORB-SLAM2 algorithm to improve the localization accuracy of a mobile robot in an environment with moving persons. Instance segmentation and motion tracking are intergrated to identify motion state of people in an image. ORB feature points belonging to moving persons are removed for further processing of the vSLAM pipeline. The advantage of this method is that the vSLAM can remove feature points of moving people, while retain those belonging to static people in the environment, which improves the accuracy of robot pose estimation. The improved ORB-SLAM2 algorithm has been implemented in a NVIDIA Xavier embedded system, which is integrated to a mobile robot. In practical robot navigation experiments, the average positioning error of the proposed method is within 4cm for 22.4m travel distance. Compared with conventional ORB-SLAM2, the average accuracy of our vSLAM method improves 97% in a dynamic environment with moving people.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning with Pedestrian Trajectory Prediction Model for Service Robot Navigation in Crowded Environments

Deep Reinforcement Learning with Pedestrian Trajectory Predi...

引用

International Conference on Advanced robotics and Intelligent Systems (ARIS)

作者： Shih-Hao Wang Yu-Hsiung Wu Tzuu-Hseng S. Li aiRobots Laboratory MS Degree Program on AI Robotics National Cheng Kung University Tainan Taiwan Dept. of Electrical Engineering aiRobots Laboratory NCKU Tainan Taiwan

Safety and effectiveness are crucial considerations in the navigation of robots within crowded environments. Previous research in this field has predominantly focused on an omniscient approach, designing environments with exceptional obstacle avoidance capabilities. However, this approach fails to address the constraints imposed by real-world applications’ limited field of view. Additionally, constructing a robot with a complete field of view can be prohibitively expensive. To tackle these challenges, this paper presents a novel approach that combines a social spatial-temporal graph convolutional neural network (Social-STGCN) with reinforcement learning (RL) to enhance crowd avoidance navigation. This approach offers a more practical and cost-effective solution. Simulations conducted to evaluate our proposed method demonstrate its effectiveness by achieving higher success rates and lower collision rates compared to existing approaches. These results confirm the efficiency and safety of our algorithm for crowd avoidance navigation. In practical applications, we employ the Intel RealSense L515 camera to capture depth and RGB image data, enabling the utilization of the Deep SORT algorithm for pedestrian tracking and recognition. This facilitates the acquisition of accurate position and speed information. To validate the performance of our system, we conducted robot experiments in real-world scenarios, including indoor corridors and elevator lobbies. The results obtained from these experiments clearly indicate that our proposed system successfully accomplishes navigation tasks with improved safety and effectiveness. In summary, this paper introduces an effective crowd avoidance navigation algorithm. By leveraging the Social-STGCN and RL techniques, our algorithm enables robots to navigate tasks with enhanced safety and efficiency, even when their field of view is limited.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Following Robot Based on Object Detection for Aerospace Application

Human Following Robot Based on Object Detection for Aerospac...

引用

Aerospace Electrical engineering and Informatics (ICAAEEI), International Conference of Adisutjipto on

作者： Arwin Datumava Wahvudi Sumari Ahnaf Bagus Aryandika Ndaru Atmi Purnami Denny Dermawan Ika Noer Syamsiana Department of Electrical Engineering Cognitive Artificial Intelligence Research Group State Polytechnic of Malang Malang Indonesia Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Digital System Microprocessor Microcontroller and Programmable Logic Devices Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia

ISBN: (数字)9798331507930

ISBN: (纸本)9798331507947

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications.

关键词： YOLO Tensors Accuracy Prototypes Wheels Cameras Hardware Maintenance Aircraft Aerospace industry

来源：评论

学校读者我要写书评

暂无评论

Neural Network Model of Continuum Soft Robots Based on WaveNets Equipped with Adaptive IIR

Neural Network Model of Continuum Soft Robots Based on WaveN...

引用

International Conference on Electrical engineering, Computing Science and Automatic Control (CCE)

作者： Oscar Federico Garcia-Castro Luis Enrique Ramos-Velasco Vicente Parra-Vega Rodolfo Garcia-Rodriguez Carlos Ernesto Vazquez-Garcia Robotics and Advanced Manufacturing CINVESTAV-IPN Ramos Arizpe Coahuila Mexico Posgraduate Program of Aeroespace Engineering Universidad Politecnica Metropolitana de Hidalgo Mexico Robotics and Advanced Manufacturing CINVESTAV-IPN Coahuila Mexico Facultad de Ciencias de la Administración Universidad Autónoma de Coahuila de Coahuila Mexico

ISBN: (数字)9798350377545

ISBN: (纸本)9798350377552

Soft robots have attracted attention from many areas, such as robotics, materials, automatic control, and artificial intelligence. The particular class of continuum soft robot (cSR) is the most challenging given its highly nonlinear dynamics from the hyperviscoelasticity and varying stiffness, which arise from the modeling of an infinite conglomerate of particles enclosed in a deformable finite-dimensional body based on the lumped parameters assumption and the D’ Alambert principle. The cSR is a complex model that presents a significant challenge in the field. Its nonintuitive structure, variable natural frequency, and parametric uncertainties, including its input matrix and lack of reliable velocity measurements, make it difficult to approximate its dynamics using only input and partial output data. This paper proposes a wavelet-based neural network (WaveNet) with an adaptive infinite impulse response (IIR) output filter. The WaveNet sweeps over modal frequencies, while the IIR enforces feedback and forward loops to propagate current and past neural outputs. The input shapes a controllable canonical output form. Simulations for a 2-degree-of-freedom CSR show that a bounded approximate modeling error is guaranteed at a low computational cost.

关键词： Backpropagation Adaptation models Time-frequency analysis Adaptive systems Uncertainty Computational modeling Neural networks Soft robotics Velocity measurement Tuning

来源：评论

学校读者我要写书评

暂无评论

Accessing Gender Bias in Speech Processing Using Machine Learning and Deep Learning with Gender Balanced Audio Deepfake Dataset

Accessing Gender Bias in Speech Processing Using Machine Lea...

引用

International Conference on Informatics and Computing (ICIC)

作者： Tricia Estella Amalia Zahra Wai-Keung Fung Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia Department of Engineering Cardiff School of Technologies EUREKA Robotics Centre Cardiff Metropolitan University United Kingdom

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

The rapid advancement of AI has led to the rise of Audio Deepfakes (AD), which pose serious ethical and security concerns by accurately mimicking human speech. This research addresses the urgent need for effective AD detection, with a focus on gender bias that can reduce the effectiveness of detection models. We examined how gender affects the performance of both Machine Learning (Support Vector Machine, Random Forest, Logistic Regression, XGBoost) and Deep Learning (Deep Neural Networks, Convolutional Neural Networks) models using the GBAD dataset. Our findings show that models trained on female audio outperform those trained on male audio, likely due to the expressive nature of female voice features and high-pitched artifacts in FAKE audio. This highlights the need for more robust, gender-sensitive detection systems. Future work should focus on developing adaptive models to reduce gender bias, improving security, and creating lightweight models for wider public use.

关键词： Deep learning Support vector machines Deepfakes Adaptation models Logistic regression Computational modeling Security Speech processing Informatics Random forests

来源：评论

学校读者我要写书评

暂无评论

Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint Prediction

arXiv

引用

arXiv 2023年

作者： Choi, Hwan-Soo Jeong, Jongoh Cho, Young Hoo Yoon, Kuk-Jin Kim, Jong-Hwan Robot Intelligence Technology Lab School of Engineering KAIST Daejeon Korea Republic of dSPECTER Seoul Korea Republic of Visual Intelligence Lab Robotics Program Dept. of Mechanical Engineering KAIST Daejeon Korea Republic of

Sensor fusion approaches for intelligent self-driving agents remain key to driving scene understanding given visual global contexts acquired from input sensors. Specifically, for the local waypoint prediction task, single-modality networks are still limited by strong dependency on the sensitivity of the input sensor, and thus recent works therefore promote the use of multiple sensors in fusion in feature level in practice. While it is well known that multiple data modalities encourage mutual contextual exchange, it requires global 3D scene understanding in real-time with minimal computation upon deployment to practical driving scenarios, thereby placing greater significance on the training strategy given a limited number of practically usable sensors. In this light, we exploit carefully selected auxiliary tasks that are highly correlated with the target task of interest (e.g., traffic light recognition and semantic segmentation) by fusing auxiliary task features and also using auxiliary heads for waypoint prediction based on imitation learning. Our RGB-LIDAR-based multi-task feature fusion network, coined Cognitive TransFuser, augments and exceeds the baseline network by a significant margin for safer and more complete road navigation in the CARLA simulator. We validate the proposed network on the Town05 Short and Town05 Long Benchmark through extensive experiments, achieving up to 44.2 FPS real-time inference time. © 2023, CC BY.

关键词： Semantics

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

International Automatic Control Conference

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

ISBN: (数字)9798350354904

ISBN: (纸本)9798350354911

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.

关键词： Trajectory planning Tracking Robot kinematics Transforms Sensor fusion programming Robot sensing systems Manipulators Trajectory Splines (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Optimal plant growth through thermo mechatronic analysis 26

Optimal plant growth through thermo mechatronic analysis

引用

26th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2022

作者： Calderón, J. Alan Tafur, Julio Barriga, Benjamín Alencastre, Jorge Solano, Gonzalo Urbizagástegui, Rodrigo Lozano, John Chancán, Marvin Applied Nanophysics Institute for Physics Technical University of Ilmenau Ilmenau98693 Germany Engineering Department Mechatronic Master Program Pontificia Universidad Católica del Peru Lima15088 Peru Federal University Arkhangelsk163002 Russia Electrical Engineering and Robotics School Queensland University of Technology St LuciaQLD4072 Australia

ISBN: (纸本)9781950492640

This work is described as a proposal to apply modern control techniques and automation tools for optimal plant growth, also it was based on key agricultural strategies that were developed by ancient civilizations such as the Inca Empire. Many of them ancient techniques including the Inca engineering of andenes were forgotten or set aside through time. In this research, however, some of these key techniques are revisited to analyze and evaluate optimal plant growth using sensors and actuators that were not available in ancient civilizations. In addition, predictive and adaptive mathematical models are used for plant growth analysis of thermodynamic parameters such as temperature, humidity and potential of Hydrogen (pH). Furthermore, there were compared performances of sensors (electromechanical sensors) with designed sensors that were based in nanostructures, because of better study of the plant growth techniques. Copyright 2022. © by the International Institute of Informatics and Systemics. All rights reserved.

关键词： Nanostructures

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：